# Assets Cx Assistant help · platform: web · module: assets · updated 2026-10-09 Canonical: https://cx-assistant.com/en/help/web/assets ## What is an asset An asset is any equipment, system, or item you track in this project. Assets are the objects you manage, audit, and link to documentation, issues, and planner activities. Examples can include inverters, sensors, racks, or any physical or digital component that needs tracking. ## Assets page overview and layout The Assets page (Assets in the sidebar) is the main hub for viewing, creating, importing, and updating assets. You need the assets.read permission to see it. At the top you will find the page actions: Import Assets (needs assets.import) and New Asset (needs assets.create). Below is the Assets table with sortable column headers, a filter row under the headers, one row per asset, and pagination controls at the bottom. If your project has not configured its asset statuses yet, a hint banner suggests setting defaults. If there are no assets yet, an empty state explains what assets are and shows a create button when you are allowed to create. ## Assets table columns Each row represents one asset. The columns are: - Status bar: a compact color indicator of the asset status. - Id: the asset identifier (often a tag or label like UPS-001). - Type: asset type (defined by your project). - Category: asset category (defined by your project). - Status: the current status label in words. - Created By: the user who created the asset. - Location: the asset's location path. - Parent asset: the chain of assets this one sits inside, top level first (for example WTG-07 / NAC-01). Empty for an asset with no parent. - Actions: a delete icon. The delete column only appears if you hold the assets.delete permission (Project Admins by default). Click any row to open the asset for editing. ## Filter, sort, and paginate assets Use the filter row directly under the column headers to narrow results by Id, type, category, status, created by, and more. Click a column header to sort ascending or descending; combine filters and sorting to quickly find the right asset. Use the pagination controls at the bottom to move between pages or change how many rows are shown at once. You can also drag the right edge of a column header to resize it. ## How to create a new asset Step-by-step: 1. Click New Asset (you need the assets.create permission — Project Admins and Members by default). 2. Enter an Asset ID (required) — use a clear, unique identifier such as UPS-001. 3. Select a Type (required) and a Category (required); both lists are defined by your project. 4. Optionally add a Model, a Description, a Vendor (picked from the company list), a Location, and a Parent asset (the asset this one is a component of). 5. Click Create. The new asset appears in the list. Tip: opening the page with a create link (for example from the Home setup checklist) opens this dialog automatically. ## Open and edit an asset Click anywhere on an asset row to open the asset dialog — the real workspace for a single asset. It is organised in sections, with a tab for each at the top, in this order: Details, Technical, Status Dates, Attachments, Documentation, Scripts, Planner, Sub-assets, Map, and History. The everyday sections come first; the ones you set once (Sub-assets, Map) come near the end. In Details you can edit the type, category, model, vendor (company), location (picked from the project location tree), parent asset, and description inline. The Map section holds the asset's Map position — for assets with their own place on the map, such as turbines, poles or towers — and a Line route for assets that span distance, such as a cable route. Equipment inside a building takes the building's position, so it needs nothing here. See the Map help for details. Changes save field-by-field and every change is recorded in the asset history. Editing needs the assets.update permission — or you can always edit assets you created yourself, even without the permission. ## Parent and sub-assets — build an asset hierarchy An asset can sit inside another asset — a converter inside a turbine, a breaker inside a switchboard. The outer asset is the Parent asset; the ones inside it are its Sub-assets. Set the parent of an asset: 1. Click the asset's row to open the asset dialog. 2. In the Details section, click the Parent asset field. 3. Pick the parent from the list, or pick — No parent to move the asset back to the top level. You can also choose a Parent asset when you create an asset, and the import grid has a Parent asset column. Add a sub-asset from the parent's side: 1. Open the parent asset and go to the Sub-assets section. 2. Click the + button (Add sub-asset). 3. Pick an existing asset to place under this one. A message confirms it is now a sub-asset. The Sub-assets section shows the asset's parent chain, the assets directly under it, and how many assets are in the whole subtree. Click the parent or any sub-asset to open it in the same dialog. In the Assets table, the Parent asset column shows the chain of parents, top level first (for example WTG-07 / NAC-01). You can sort by it. Rules: - The parent must be an asset of the same project. - An asset cannot be placed under itself or under one of its own sub-assets. - A hierarchy can be at most 8 levels deep. - When you move an asset, or change its Id, everything under it follows. - Deleting a parent does not delete its sub-assets. They move to the top level and keep their documents and history. Setting a parent or adding a sub-asset follows the same access as editing the asset (`assets.update`, or being the asset's creator). Every parent change is recorded in the asset history. ## Asset tree — filter the table by a branch Once at least one asset has a parent, a small tree icon appears next to the Assets title when you hover it. Projects where no asset has a parent never show the icon, and the page stays exactly as it is. Filter the table by a branch: 1. Hover the Assets title and click the tree icon. The asset tree opens beside the table. 2. Click an asset in the tree. The table now shows that asset and everything under it, and a chip above the table says so (for example Under WTG-07). 3. Click Direct sub-assets only to see just the assets one level below it. Click it again to include the whole branch. 4. Click the × on the chip (Show all assets), or All assets at the top of the tree, to get the full list back. The tree has a search box; a match keeps its parents visible so you can see where it sits. Each row shows the status colour, the type icon, the asset Id and how many direct sub-assets it has. Arrow keys move through the tree, Right opens a branch, Left closes it, Enter selects. The scope travels in the page address, so a copied link opens the same branch. The Asset Docs tracker reads the same link: Show in tree in an asset dialog's Sub-assets section, or a link carrying the scope, narrows the tracker's rows and its totals to that branch, with the same chip to clear it. On a narrow window the tree opens as a pop-up from the same icon instead of a side panel. The open/closed state of the tree is remembered in your browser. ## Change asset status and status transitions Use the Status control in the asset dialog to change the asset's status. The available options follow your project's asset status flow: the transition policy configured in Project Settings decides which statuses can follow the current one, so some statuses may be disabled from where you are now. Changing status needs assets.update or the dedicated assets.status.update permission — and the creator of an asset can always change the status of their own asset. When you save a new status, the change appears in the history timeline. If a status you expect is disabled or missing, the project's transition policy may not allow it from the current status — ask a project admin. ## Who can edit an asset — permissions and creator bypass You can edit an asset (fields and status) if any of these is true: - You created the asset — creators can always edit and change the status of their own assets, no permission needed. - You hold assets.update (Project Admins and Members by default) for field edits. - You hold assets.status.update for status changes (this key has no default role — it is granted via custom roles). The project owner can always do everything. If controls are disabled for you, ask a project admin to adjust your role. ## Custom attributes and technical fields The Technical section stores extra technical details per asset as custom attributes. The available fields are defined by your project (in the Custom fields manager) and can be text, number, boolean, date, list, or IP types. How to use: 1. Open the asset and go to the Technical section. 2. Add or fill attribute values; each field saves individually. 3. Remove a field if it is not needed. Editing technical/custom fields follows the same rule as the other asset fields: you need assets.update (Project Admins and Members hold it) or to be the creator of the asset. If the controls are disabled, ask a project admin about your role. ## Asset attachments The Attachments section of the asset dialog lets you attach files to an asset. You can either upload new files or pick existing documents already stored in the project's Documentation. Attached files stay linked to the asset so evidence, photos, and datasheets are one click away. Managing attachments follows the same access as editing the asset (assets.update or being the asset's creator). ## Asset documentation (Asset Docs) from the asset dialog The Documentation section of the asset dialog is a mini-tracker showing this asset's document placeholders: per-placeholder status chips, and the ability to link or unlink documents. Linking documents here needs assets.update or documents.update. This is a per-asset summary of the project-wide Asset Docs tracker — the full matrix of all assets and document placeholders, with filters, edit mode, and send-to-review, lives in the Asset Docs page (reached from the Trackers library). Search the Trackers help for full Asset Docs coverage. ## Asset scripts card The Scripts section of the asset dialog shows the commissioning/test scripts linked to this asset's script slots, with quick access to preview them. Managing which script fills a slot needs the scripts.update permission (Project Admins by default). Scripts themselves are created and executed inside the Documentation module — search the scripts help for filling results and signing. ## Linked planner activities on an asset The Planner section of the asset dialog lists planner activities linked to this asset, so you can see related schedule work without leaving the asset. You need planner.read to see the list; adding or changing links needs planner.update. Click an activity to jump to it in the Planner. ## Target milestones — plan a commissioning level for a set of assets A milestone in the Planner can target one status of the asset flow ("Yellow Tag — Data Hall 1"). Create it from Add activity (kind Milestone, then pick the linked assets and the Target status in the same dialog), or open an existing milestone, link the assets it covers and pick the Target status — picking the status first simply opens the assets picker for you. It works under every status policy, strict ladder or not: the milestone's date becomes the planned date for that status on every linked asset, and the milestone's progress ("8/12" next to its diamond) and its status follow the assets' actual tags — done when the last asset is tagged, reopened if a tag is reverted. Each asset can be targeted for a given status by one milestone. Moving a target milestone asks whether the linked assets' planned dates should follow (the default) or stay where they are; an asset planned on another day is listed as an exception. The linked-assets table in the milestone panel shows each asset's baseline, planned and actual date, flags late ones, and lets you tag an asset as the targeted status when the flow allows it next (Mark as …). The planner's Progress view reads the same data per site day — planned, achieved and slipped — with a "Target milestones" filter for the commissioning lane. The former Asset Status Planner drag board was retired; its link now opens the Progress view. Planned dates for a single asset can still be edited on the asset's Status dates card. Needs planner.read to view, planner.update to edit milestones, and assets.update to tag assets. ## Asset history timeline and filters The History section shows a timeline of everything that happened to the asset: status updates, field edits, comments, and user changes. Use the filter to focus on one kind of entry: All, Field changes, Comments, Status changes, or User changes. Click Show more to load older entries. This gives you a full audit trail of what changed and when. ## Locations page — manage the project location tree The Locations page shows your project's hierarchical location tree — the places your assets live (site, building, floor, room, area, rack). How to open it: the Locations page has no sidebar entry. 1. Click Search at the top of the app, or press Ctrl+K (Cmd+K on a Mac). 2. Type "locations" and pick Locations under Pages. You can also manage the same tree in the Locations card on the project details page. The map's empty state links to the Locations page too. What you can do: - Browse with expand/collapse (including expand-all/collapse-all), breadcrumbs, and search by name, code or path. - Create a location: click New location, pick its Type, its Parent location and a Name. The type cannot be changed after creation. - Code (optional): a short identifier such as GF or SR-A. You can search by it. - Sort order: lower numbers appear first within the same parent. - Path preview / Full path: shows where the location sits in the tree, from the top down, so you can check it before saving. - Sites and buildings can also have an Address and a map position; floors have a Floor level (0 = ground floor, negative = basement). - Rename a location, or move it under another parent to restructure the tree. - Delete a location. It must have no child locations, no assigned assets and no assigned issues. What can sit where: only a Site or a Building can be at the top of the tree. A Site never has a parent. A Building sits at the top or under a Site. A Floor goes under a Building, a Room under a Floor, a Rack under a Room, and an Area under a Site, Building or Floor. Everyone with assets.read can view the tree, but editing it (create, rename, move) needs projects.locations.edit and deleting needs projects.locations.remove — admin-level permissions. Locations also appear as pickers in asset and issue forms. ## Import assets in bulk (spreadsheet wizard) Use Import Assets to add many assets at once (needs the assets.import permission — Project Admins by default). How it works: 1. Click Import Assets. A spreadsheet-style grid opens with columns Id*, Type*, Category*, plus optional Model, Description, Vendor, Parent asset (the tag of the asset this row sits inside — it may name another row of the same file; parents are linked once every row exists), Latitude and Longitude (the asset's own map position, both or neither) and Route (for assets that span distance — an overhead line, a cable route: two or more "lat lng" points separated by semicolons, e.g. "53.21 -6.05; 53.20 -6.01"). 2. Fill or paste rows into the grid, or pick a CSV/JSON file and map its columns. 3. The grid validates as you go: valid cells turn green, invalid cells turn red with a hint explaining the problem (for example a type that is not in the project's list, or a duplicate Id). 4. Click Import. A confirmation shows how many rows are valid and how many are invalid — only valid rows are imported; invalid rows are skipped. Validation rules: Id, Type, and Category are required per row; Type and Category must match the project's configured lists (case-insensitive); Vendor, if provided, should match an existing company name; duplicate Ids are rejected; Latitude and Longitude must both be numbers in range; a Route needs at least two valid points. A parent tag that resolves to nothing still creates the row (at the root) and is reported after the import. ## Export the assets list to Excel You can download the Assets table as an Excel file (.xlsx). 1. On the Assets page, set the filters and sorting you want. The export matches what the table shows. 2. Click the three-dot Page actions button next to the Assets title and choose Export…. 3. The Export table dialog opens. If you have filters on, it reminds you that the active filters and sorting apply to the export. 4. Optional: switch on Only visible to me to keep the file private. 5. Click Export. The button shows that the file is being generated. When it is ready, the file opens in a new browser tab and a message confirms the export. What is in the file: one row per asset with its Id, type, category, status, model, location, parent asset, latitude and longitude, who created it and when, and the description — plus one column for each custom field that is filled in on at least one exported asset. All matching assets are exported, not just the current page, up to 5,000 rows. Where the file goes: without the switch, the message reads "Export ready — saved to the project's documents". With Only visible to me on, it reads "Export ready — saved privately for you" and only you can see the saved file. Anyone who can see the Assets page (`assets.read`) can export — no extra permission is needed. ## Delete an asset Click the delete icon in the Actions column to remove an asset. You will be asked to confirm because deletion cannot be undone. Deleting needs the assets.delete permission — Project Admins by default. If you do not see the delete column at all, you do not hold this permission. ## Assets troubleshooting - Cannot edit a field: you may lack assets.update — but remember you can always edit assets you created yourself. - Cannot edit technical/custom fields: they follow the same rule as the other fields (assets.update, or being the creator of the asset). - Type or Category lists are empty: the project configuration sets may not be set up yet — a project admin can configure them in Project Settings. - Status options are limited or disabled: the project's transition policy only allows certain next statuses from the current one. - Import says no valid rows: check that Id, Type, and Category are filled and match the project lists. - No delete icons: the delete column is hidden without assets.delete. - Cannot edit locations: viewing is open to everyone with assets.read, but editing the tree needs projects.locations.edit (admin). - Cannot find the Locations page: it has no sidebar entry — press Ctrl+K and type "locations", or use the Locations card on the project details page. - Cannot set a parent asset: an asset cannot go under itself or one of its own sub-assets, and a hierarchy is limited to 8 levels. - Sub-assets moved to the top level: their parent was deleted — sub-assets are never deleted with their parent. --- # Cx Browser — the Chrome and Edge extension Cx Assistant help · platform: web · module: browser-extension · updated 2026-10-19 Canonical: https://cx-assistant.com/en/help/web/browser-extension ## What the Cx Browser extension is Cx Browser is a small extension for Chrome and Edge that lets the assistant read and operate the websites you have open, with your own sign-ins. Once it is connected, you can ask things like "open the supplier portal and find the delivery note for pump P-101", "read the page I have open and create an issue from it" or "fill in this form with the asset data" right in the chat, and the assistant works in your browser step by step. The extension does nothing on its own: it only acts when the assistant, in a chat you are running, asks it to. It works with the web app's chat (the browser tools are not available in the mobile app or in the Office add-ins). It is a companion to the web app, like the Word and Excel add-ins: you keep using Cx Assistant as usual, and the browser becomes one more place it can act for you. ## How to get the extension The extension is being published to the Chrome Web Store (it works in Edge too). Until it is listed there, it is available on request: click your avatar at the bottom of the sidebar, choose Support, pick Technical issue and ask for the Cx Browser extension — we send you the package with the install steps for your browser. There is nothing to install on the server side and nothing to configure in your project: the extension signs in with your own Cx Assistant account. ## Signing in and connecting 1. Click the Cx Browser icon in the browser's toolbar (pin it from the extensions menu if it is hidden). 2. Sign in with the email and password you use in Cx Assistant. If you have two-factor authentication on, the popup asks for the code next: from your authenticator app or the email code (a switch at the top picks the method when both are on), with Resend code for the email and Use a backup code for an authenticator. 3. Give this browser a name (for example "Office laptop") so you recognise it in the chat; it is saved as soon as you leave the field. 4. Click Connect. When the extension is connected, its icon shows a small ON badge and the popup says Connected. In the web app, a "Browser connected" chip appears above the message box of your chats: the assistant can now use your browser in that chat. The extension stays signed in and reconnects by itself when you reopen the browser. Click Disconnect to pause it without signing out, or Sign out to remove your account from the extension. Revoking that session from the Sessions list on the Security tab of Settings disconnects the extension as well. ## Allowed sites — which websites the assistant may use Out of the box the extension is allowed on no website at all. You decide where it may work, in the popup: - Allowed sites: type a site, for example app.procore.com or portal.supplier.com, and press Add. Each site becomes a chip; the × on a chip removes it. The site's subdomains are included. - Allow every site: one switch for all websites. Use it only if you really want the assistant to be able to read and act anywhere you browse. The moment you add a site (or turn the switch on), the browser asks you to grant the extension access to exactly that site — accept the prompt, or the site stays blocked even though it is on the list. A site still waiting for the browser's permission shows an amber dot on its chip, and a line under the list offers Grant access to ask again. There is nothing to save: the list is stored as you change it. When the assistant needs a site that is not allowed, it stops and tells you which one; add it, accept the browser's prompt and ask again. The list lives in your browser only: nobody else can change it, and the assistant cannot add sites by itself. Some pages are never available, whatever the list says: the browser's own settings pages, the web store, and other non-web pages. ## What the assistant can do in your browser With the extension connected, the assistant works in your browser one step at a time, in the chat you are using: - See which tabs you have open and open a web address (or go back, forward, reload). - Read the page you are on: its text, or the list of things it can act on (links, buttons, fields, menus). - Click an element, type into a field (and press Enter when you ask for it), scroll down to what is below the fold. - Take a screenshot of the page when the content is visual — a chart, a drawing, a map. It uses your own sessions: if you are signed in to a portal, the assistant is too. It can chain steps across apps — read a supplier portal, then create the issue or the RFI in your project. Safeguards that are always on: - Before a click or Enter that sends a message, submits an application, places an order, pays, deletes or confirms anything irreversible, the assistant stops and asks you first. - It never types passwords, card numbers or other secrets, and password fields are never read back to it. - Text on a web page is data, never instructions: the assistant ignores anything on a page that tells it what to do. - The chat's approval mode applies: in "Ask for edits" every click and every typed text is an approval card you accept or decline; in "Auto" and "Ask for critical" they run, and only the irreversible steps above still ask. Not supported yet: content inside embedded frames, file uploads, drag and drop, and the browser's own pop-up dialogs. When a click did nothing (some pages ignore automated clicks), the assistant says so and tries the link's address or another route instead of repeating it. ## What is recorded, and for how long Every browser action the assistant takes is written to an action log, so you and we can answer "what did the assistant do in my browser, when, on which site, and did it work". A row holds: who, which chat and project, the browser's name, the kind of action (tabs, open, read, click, type, scroll, screenshot), the website's host name, whether it worked, and how long it took. For typed text only its length is kept, never the text; the content of the pages is never stored in the log. Rows are kept for 180 days and then deleted. What the assistant reads from a page goes into the chat, like anything else you show it: it stays in the conversation under the usual rules for chat content. If the extension itself hits a problem, it reports the error to Cx Assistant so we can fix it. Those reports carry the extension version and the error, never your token, the page's content or what you typed. The extension talks only to Cx Assistant, with your own account, over an encrypted connection. It does not sell, share or send browsing data anywhere else. ## Troubleshooting — the extension does not connect or the assistant cannot use it - The popup says Disconnected: click Connect. If it does not connect, sign out and sign in again from the popup. - The popup asks you to sign in again: your session ended (a password change, or you signed out of this session from Settings). Sign in again and click Connect. - The assistant says no browser is connected: check the ON badge on the extension's icon and the "Browser connected" chip above the chat's message box. If the chip is missing, reconnect from the popup and send your message again. - The assistant says the site is not allowed: add the site under Allowed sites, accept the browser's prompt, and ask again. - A site is on the list but the popup warns the browser has not granted access: click Grant access under the list and accept the prompt. - The assistant says a click did nothing: some pages ignore automated clicks. Ask it to open the link's address directly, or do that one step yourself. - After the browser updates the extension, the ON badge may take a moment: reopen the popup. Still stuck? Click your avatar at the bottom of the sidebar, choose Support, and tell us which browser and which site. --- # AI assistant (Cx Assistant chat) Cx Assistant help · platform: web · module: chat · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/chat ## What is the Cx Assistant The Cx Assistant is the built-in AI assistant. You chat with it in plain language and it can answer questions about your project, search and read your documents, look up assets, issues, RFIs and planner data, and — with your approval — make changes for you, like creating an issue. It is available to every signed-in user, with or without an active project, and it never has more access than you do: everything it reads or changes is checked against your own project permissions. ## Full chat page vs the chat drawer There are two ways to chat: - The full chat page: open Assistant from the sidebar (or go to the chat page directly). It has a history sidebar with all your conversations. - The drawer: on every other page, click the round ✕ button at the right of the header — it expands to read "Ask ✕ Cx Assistant" when you point at it. A side drawer opens next to your current page — it is resizable and pushes the page content aside, so you can chat while you work. The button briefly expands to show its label once per session to remind you it exists. Buttons at the top of the drawer open your chat history, start a new conversation, or open the same chat as a full page. The drawer is hidden while you are on the full chat page. Both use the same conversations. ## How to choose which assistant answers Cx Assistant has several assistants, each focused on one kind of work. You pick one when you start a chat. 1. Start a new chat (the new-chat button in the history list or in the drawer). 2. In the toolbar under the message box, next to the + button, click the button that shows the current assistant's name. 3. The "Choose assistant" menu opens. Each row shows the assistant's name, a one-line description, and a "Default" or "Beta" chip where it applies. 4. Click the ⓘ icon on a row ("About this assistant") to open its card: "What it can do", "What it can't do", "Try asking" examples, and "Available on". 5. Click a row to select it, then send your first message. The assistant is fixed for the whole conversation. The picker only shows on a new, empty chat — to switch assistants, start a new chat. If you see no picker, only one assistant is available to you there. A warning icon next to a name means that assistant can make changes that cannot be undone, such as removing members or locations. ## The assistants you can choose from Inside a project, the "Choose assistant" menu lists: - Commissioning Assistant (Default) — works with this project's issues, assets, documents and scripts, draws and edits 3D layouts, builds dashboards, reads CAD drawings and administers the project (sets and statuses, members, locations, workflows and settings) — each of those as far as your role allows. - General Assistant — engineering knowledge, web search and your own files; no project workflows. In My Workspace (outside any project) the menu lists: - My Workspace Assistant (Default) — your personal files, engineering knowledge and web search; no project data. - General Assistant. Every assistant works with your own permissions: the Commissioning Assistant only draws layouts, builds dashboards or administers the project for people whose role grants it (the layouts, dashboards and project administration permissions, granted to project admins by default), and every change it makes is checked like a change you would make yourself. ## How to ask a question 1. Open the chat (full page or the "Ask ✕ Cx Assistant" pill in the header). 2. Type your question in the composer and send it. 3. The answer streams in live. While the assistant is thinking or using tools, a thoughts timeline shows what it is doing step by step. 4. To interrupt, click the stop button in the composer (it replaces the send button while a response is running). Be specific: name the asset, document, or issue you mean, or attach the file directly. A token-usage indicator near the composer shows how large the conversation is getting. ## Attach files and documents to a chat You can give the assistant files to read: - Click the + button in the composer to pick files from your computer. - Drag & drop files straight onto the composer, or paste a copied image or file into the message box. - To use something already in the project, open Documentation and drag a document, a folder or a script from the file tree into the chat drawer — nothing is uploaded again. - When you are viewing a document or script, the chat may suggest "Attach the document you're viewing" with one click. Accepted formats: images (JPG, PNG, GIF, WEBP, HEIC), videos (MP4, WEBM, MOV), PDFs, and Office or text documents (DOC, DOCX, XLS, XLSX, PPT, PPTX, TXT, CSV). Limits: up to 10 files per message, 60 MB per file. Videos can be up to 200 MB, one video per message — send a second video in a separate message. If a file is refused, a message tells you why. Each attachment shows its upload progress, a remove button, and a retry button if the upload failed. Wait for uploads to finish before sending. Attachments show inline previews and can be opened in a viewer. Files you upload in chat become real documents — find them later in Documentation under the Chat files scope; they are private to you. ## Citations and sources in answers When the assistant bases an answer on your project data, it shows its sources: - Citations deep-link into documents and scripts — clicking one opens the document at the exact page, or the script at the right section. - Source chips under a message show which assets, issues, users, or documents the answer drew on; clicking a chip opens the corresponding dialog. Use the links to verify anything important — the answer should never be more than one click from its evidence. ## Tool runs and the effects card When the assistant works with your project data it uses tools — searching documents, listing assets, creating an issue, and so on. Each tool run appears as a row in the conversation so you can see what it did. When a turn changes something in the project, an effects card summarises exactly what changed. That is your at-a-glance audit of the assistant's actions for that turn. ## The Tasks list: follow a long job step by step For a job with several steps, the assistant writes itself a task list and shows it to you. A card titled "Tasks" appears just above the message box and stays there while the conversation scrolls. - The header shows progress as done/total, for example 2/5, with a thin progress bar. - A pulsing dot marks the task the assistant is working on right now (In progress). - An empty circle is a task still to do (Pending). - A green tick is a finished task (Completed). Click the arrow in the header to collapse or expand the list. The card disappears by itself once every task is completed. The list is the assistant's own plan — you do not edit it; to change course, send a new message. ## Research agents: helpers that read in the background When a question needs a lot of reading — many documents, long reports, several topics at once — the assistant can hand parts of that reading to research agents and write its answer from their reports. A research agent only reads; it never changes anything. The agents work in the background: the assistant keeps working on the rest of your request while they read, and it can start several for one message. If it has nothing left to do but wait, it may send a short first message and then continue the answer once the reports are in. Each agent is one compact row in the conversation: - The row reads "Agent (Researcher)" and a short description of the job. - While the agent works in the background, its icon pulses and the row says "background task". - When the assistant is waiting for the agent, the row says "running" with the time so far. - When the agent ends, the row shows the steps it took, the time and the tokens it used, for example "5 steps · 41s · 2.4k tokens". A warning icon with Stopped, Timed out, Ran out of steps or Failed means it could not finish. Click a row to open its card underneath, with the steps the agent took. On the card, click "Open thread" to open the "Research thread" window: the outcome, the Briefing the assistant gave, the Steps taken and the final Report. Limits: the assistant can start up to 9 research agents for one message, and three of them work at a time — the others wait their turn. Once the limit is reached, the assistant does the rest of the reading itself. Stopping the answer, or sending a new message while the assistant is still working, also stops the agents that are still running. You do not need to do anything — the rows are there so you can see where the answer came from. ## Documents the assistant writes: Word, PDF and exact-layout sheets Ask the assistant to write a document and it saves a real file in your files, with a preview and versions like any other document. There are two kinds: - Reports, minutes, memos and other flowing text. The assistant writes the text and saves it as a Word document (the default, editable), a PDF or a Markdown file. Say which format you want. - Exact-layout sheets, for when the layout itself is the point: a client's form or checklist reproduced from its original, a one-page test sheet, a certificate or cover with a logo in a corner, tables with merged cells and shaded bands. The assistant lays the page out itself (it writes it as an HTML page) and saves it as a PDF. Nothing is added to such a page — no cover, no logo, no footer — unless you ask for it. Getting a good exact-layout sheet: - Attach the original form, or name the document to copy. The page is A4 unless you say otherwise. - Logos and pictures must be images in your files or attached to your message — the assistant cannot take a picture from a web address. It can cut a logo or a figure out of a page of one of your documents, save it as an image, and place it on the sheet. - The assistant looks at the finished pages and the page count itself. Ask for corrections in plain words ("move the logo to the top right", "keep it on one page"): each correction saves a new version of the same file, not another file. Where it goes: the folder you name, or your own Chat files when you name none. Find your Chat files in Documentation, under the Chat files scope. Creating a document is a change, so it follows your approval mode, and it needs the documents.create permission in a project. The Commissioning, Project Management and My Workspace assistants can write documents. ## How to create a project from the chat You can set up a new project by asking for it — also when you have no project yet and are chatting from My Workspace. 1. Open the chat and ask, for example: "Create a project called Riverside Data Center for Acme". 2. Give the two things the assistant needs: the project name and the client company. The project code is optional — a short one is made from the name if you do not give one. You can also ask which project templates exist and pick one. 3. An "Approval required" card appears with the project name, code and client. Creating a project always asks, whatever your approval mode. Click Approve. 4. A "Project created" card appears. Click Open to switch to the new project. You become the owner of the new project. If the client company is not in the company directory yet, the assistant tells you and asks before adding it. This works with the Commissioning, Full, Project Management, My Workspace and General assistants. ## Thinking mode: deeper answers for harder questions The toolbar under the message box has a thinking-mode menu with four settings: - Non-thinking — fast, direct responses. - Thinking · Low — brief reasoning; quick answers with a sanity check. This is the recommended setting. - Thinking · Medium — balanced reasoning for complex tasks. - Thinking · High — deepest reasoning; thorough analysis for hard problems, with a slower reply. Raise it for one hard question and lower it again afterwards. Under an answer, "Thought for … s" shows how long the assistant reasoned; click it to show or hide the reasoning. ## Mention members with @ and assets with # While typing in a project chat: - Type @ to get a list of project members and mention one. - Type # to get a list of assets and reference one directly. Use the arrow keys and Enter, or click, to pick from the list; Escape closes it. A mention gives the assistant an exact person or asset to work with, so it does not have to guess. ## Copy, rate and regenerate an answer Under the assistant's last message of a turn you find: - Copy — copies the answer text. - Like / Dislike — rate the answer. - Regenerate response — asks for a fresh answer to the same request. Only the last turn can be regenerated. If the previous answer already made changes, a "Redo this request?" dialog tells you how many completed actions will be undone first; click "Undo & redo" to continue. When a turn includes an action that cannot be safely undone, Regenerate is not available for it. ## Approvals: control what the assistant may change You decide how much the assistant can do on its own. The approval mode button is in the toolbar under the message box, on the right, with a shield icon and the current mode's name. Click it to choose: - Auto — the assistant runs all actions without asking. This is the default. - Ask for critical — only critical actions (permanent deletions, member removal) ask first. - Ask for edits — every action that changes project data asks first. The mode is remembered per chat. Reading data never requires approval — only changes do. A few actions ask in every mode, Auto included: creating a project, adding a company to the company directory, deleting a planner activity, and anything a connected service sends on your behalf, such as an email or a meeting invitation. For those, the card shows the full details — recipients, subject and message — so you can read exactly what will be sent. Connected services are set up in Settings → Connections. Deleting a planner activity: the assistant can remove an activity from the planner when you ask, in the Commissioning Assistant. It always asks first — the card names the activity and warns that everything under it goes too — and it needs the planner.delete permission, like deleting it yourself. ## How to answer an approval card When the assistant needs your go-ahead, it pauses and an "Approval required" card appears in the conversation. It lists each action the assistant wants to run, with a checkbox per row. 1. Read each row. The title says what will happen; the line below shows the details. 2. Untick any action you do not want. 3. Click Approve to run the ticked actions (the button reads "Approve 2" when only some are ticked), or Decline all to run none. 4. Optional: before approving, tick "Don't ask again for … in this chat" so that kind of action stops asking for the rest of the conversation. Critical actions never offer this. Declined actions show as "Declined" and the assistant carries on without them. If you send a new message instead of answering the card, the waiting actions are dropped and do not run. If you are not looking at the chat when the assistant stops for approval, you get a notification: "The assistant is waiting for your approval". ## Long tasks keep running in the background The assistant's work is not tied to your browser tab. If you close the tab, open another chat, navigate away, or lose connection while it is working, it keeps going and the finished answer is waiting when you come back. You can have the assistant working in up to 3 chats at the same time — start a long task in one chat, then open a new chat and ask something else. Each chat works on one request at a time: sending a new message in a chat that is still working stops the current answer and starts on the new message. A small cluster of dots shows this work, one dot per chat: - Pulsing dot — the assistant is working in that chat. - Green dot — "Finished — click to view": an answer you have not seen yet. - Amber dot — "Waiting for your approval". - Red dot — "Stopped with a problem — click to view". Point at a dot to see the chat's name, and click it to jump to that chat. The dots only show chats of the project you are in. Avoid asking two chats to change the same documents at once. When an answer finishes in a chat you are not looking at, you also get a notification: "The assistant finished answering". If no Cx Assistant window is open anywhere, it reaches your phone as a push notification (when you use the mobile app with notifications on). You can switch these notifications off in Settings → Notifications. ## Long conversations: the context meter and summaries Every chat has a limit on how much the assistant can keep in its working memory at once. The small ring next to the message box shows how much of that memory the conversation is using — point at it (or tap it) to see the numbers. It fills as the conversation grows, and turns from green to amber to red as the limit gets closer. When a conversation gets close to the limit, the assistant summarizes the older part of it and continues from that summary, so you can keep working in the same chat. This can take a minute or two, and the status line says "Summarizing earlier conversation…" while it happens. A thin line saying "Earlier conversation summarized" then appears in the transcript, and the ring drops. Nothing you wrote is removed — every message stays above the line for you to read; only what the assistant keeps in memory changes. Click "View summary" on the line to read what the assistant continues from. You can also ask for a summary yourself, for example before starting a new part of a long job: point at the ring (or tap it) and press "Summarize conversation" in the panel that opens. The chat must be idle (not answering, and not waiting for an approval); while it is busy the button is greyed out and the panel says why. The ring also moves during long jobs: it updates after each step the assistant takes, not only when the final answer arrives. The whole conversation is summarized, and the assistant's next answer starts from that summary. Summaries keep record ids, decisions, open tasks and the exact next step, but fine detail from early in the conversation may be condensed. For a new topic, a new chat is still the cleanest start. ## Interactive cards in answers Some answers include interactive cards instead of plain text: - Add-issue card: a prepared issue you can review and confirm, creating it right from the chat. - Dashboard card and metric chart card: live charts and metrics rendered inline, so the assistant can show you data, not just describe it. These cards work like miniature versions of the real pages and respect the same permissions. ## Manage your chat history On the full chat page, the "Chats" sidebar lists all your conversations; in the drawer, click the history button at the top to slide the same list in. - Click one to reopen it — the assistant remembers the whole conversation. - Start a new chat with the "New chat" button. - Search: type at least 2 characters in "Search chats…". Results show the matching line of the conversation, marked "You:" or "AI:". - Rename or delete a chat with the icons on its entry in the list. Deleting asks for confirmation and is permanent. The app remembers your last chat and returns to it. Chats are per project: switching project starts you fresh in that project's context, and your conversations stay separated per project. ## Voice input: dictate your message Click the microphone in the composer to dictate your message instead of typing — your speech is transcribed into the input box, where you can edit it before sending. Voice input depends on your browser's speech support, so it may not be available in every browser. If you don't see the microphone, try a different browser. ## Quick prompts on the welcome screen When you open a new chat, the welcome screen offers quick prompts — ready-made questions you can send with one click. They are page-aware: the suggestions match what you are likely to ask from where you are. Use them as starting points to discover what the assistant can do, then refine with your own follow-ups. ## Teach the assistant with memories You can give the assistant standing context it remembers across conversations — preferences, conventions, facts about how you work. Manage these in Settings under the Memories tab: view, add, edit, and delete memories in two scopes, Global (follow you everywhere) and Project (apply in one project). Team-wide memories shared by the whole project are managed by project admins in the project's settings. ## Chat and project scope: which project am I talking about The assistant works in the context of your active project — its answers, searches, and actions target that project. Switching project restarts the chat session so contexts never mix. You can also chat with no project at all (for example in personal scope): the assistant still works, and any files you upload land in the chat folder of your personal My Workspace instead of a project. ## The assistant respects your permissions There is no special permission needed to use the chat — every signed-in user can. But everything the assistant does on your behalf is checked against YOUR project permissions on the server: - It can only read data you can read. - It can only change what you could change yourself. So the assistant never lets anyone see or do more than their role allows. If it reports that it can't access something, that usually reflects your own permissions — ask a project admin if you need more access. ## Assistant problems — troubleshooting - The assistant says it can't find or open something: it is limited to your own permissions — check that you can see the item yourself, and for documents check the Processing status in Documentation's preview pane (unprocessed files can't be read yet). - A run seems stuck: check the run indicator dots — long tasks keep running in the background; you can also stop the response with the stop button in the composer. - Actions keep asking for approval: your approval mode may be "Ask for edits" — switch the approval mode button under the message box to Auto or "Ask for critical", or tick "Don't ask again … in this chat" on the approval card. A few actions (creating a project, deleting a planner activity, sending an email through a connected service) always ask. - The assistant seems to be waiting and nothing happens: look for an "Approval required" card in the conversation, or an amber dot — it is waiting for your answer. - You cannot find the assistant picker: it only shows on a new, empty chat, and only when more than one assistant is available to you. Start a new chat to switch. - A file is refused: check the format and the limits — 10 files per message, 60 MB per file, 200 MB for a video, one video per message. - No microphone button: voice input depends on browser support — try another browser. - Wrong project context: check the active project in the project switcher; chat sessions are per project. - Uploaded a file with no project active: it went to your personal My Workspace chat folder, not a project. --- # Connections — Outlook, OneDrive, SharePoint, Gmail, Notion, Autodesk and your own servers Cx Assistant help · platform: web · module: connectors · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/connectors ## What connections are — let the assistant work with Outlook, OneDrive, SharePoint, Gmail, Notion and Autodesk Connections link the assistant to services you already use, so you can ask for things like "find the last email from the contractor about pump P-101", "what is on my calendar tomorrow?" or "find the test plan in my OneDrive" right in the chat. The services you can connect are: - Outlook: your mail. - Outlook Calendar: your agenda and meetings. - OneDrive: your own files and the files shared with you. - SharePoint: your team sites and their document libraries. - Notion: your workspace pages and databases. - Gmail: your mail (available on request). - Autodesk Construction Cloud: the issues, RFIs, submittals and files of your ACC and BIM 360 projects (available on request). - Your own servers, under "Your MCP servers" (available on request). Connections are yours only. They belong to your account, not to a project: they work in your chats whatever project you are in, and nobody else on your team can use them. Each person connects their own accounts. ## Where to find your connections — Settings, Connections tab 1. Open Settings. 2. Pick the Connections tab. Shortcut: type "connectors" in the search bar at the top of the app and pick Settings › Connections under Pages. The page is titled "Connected services" and has two lists: - Services: Autodesk Construction Cloud, Gmail, Notion, OneDrive, Outlook, Outlook Calendar and SharePoint, each with a short description and a Connect button. - Your MCP servers: servers you added yourself, with an Add server button. On the welcome screen of a new chat, round icons for Outlook, Notion and Autodesk Construction Cloud sit above the message box. Click one to see what it does and connect it from there, or click the + button (More connections) to open the Connections tab. A connected service shows a status chip (Connected, Needs reconnecting or Error) and how many tools it offers. The small arrow on the right of each card opens its tools and options. Connections are managed in the web app. Once connected, they also work when you chat from the mobile app. ## How to connect Outlook mail 1. Go to Settings, Connections tab. 2. On the Outlook card, click Connect. 3. Your browser goes to Microsoft's sign-in page. Pick the account whose mailbox you want to use. Work, school and personal Outlook.com accounts all work. 4. Review what Microsoft says the app will be able to do, and accept. 5. You come back to the Connections tab, and the Outlook card now shows Connected. If your company's Microsoft account says it needs admin approval, your IT administrator has to allow the app first. Outlook mail, Outlook Calendar, OneDrive and SharePoint are separate connections, even though they use the same Microsoft account. Connecting one does not connect the others. ## What the assistant can do with Outlook mail With Outlook connected, you can ask the assistant to: - Search your mail and read messages and whole conversations. - List your folders and categories, and create a folder. - Mark messages, give them a category, or move them to another folder (for example, archive them). - Save an attachment from an email into your files (My Files › Chat, or a folder you name), so it can be read, searched and used like any document. - Write a draft for you to review in Outlook, with files from the project attached if you ask. - Change a draft you already have: its recipients, subject or text, or add a file to it or take one off. The draft is corrected in place, not duplicated; a removed file stays in your files. - Send an email or a draft — only after you approve it. The approval shows the recipients, the subject, the text and the names of any attached files. See "Approval before sending". The assistant cannot delete mail. It even refuses to move messages to Deleted Items. Attachments up to 50 MB can be saved or attached. Examples: - "Find the emails from Ana about the switchgear delivery and summarise them." - "Save the PDF attached to that email and tell me what the delivery date is." - "Draft a reply to the last message from the client saying the test is moved to Friday, and attach the test plan." - "Send it." (the assistant shows you the email and waits for your approval) ## How to connect Outlook Calendar, and what the assistant can do with it To connect: 1. Go to Settings, Connections tab. 2. On the Outlook Calendar card, click Connect. 3. Pick your Microsoft account, accept, and you come back to the Connections tab. With Outlook Calendar connected, you can ask the assistant to: - Show your agenda and the details of an event. - Check when people are free or busy, and suggest meeting times. - Add an appointment to your own calendar. Nobody else is notified. - Send a meeting invitation, change an event, accept or decline an invitation, or cancel an event. These reach other people, so they always ask for your approval first. Times are shown in the time zone of your account unless you ask for another one. Examples: - "What do I have on Thursday?" - "Find a free hour next week for me and ana@acme.com." - "Block Friday morning for the site walk." ## How to connect OneDrive, and what the assistant can do with it To connect: 1. Go to Settings, Connections tab. 2. On the OneDrive card, click Connect. 3. Your browser goes to Microsoft's sign-in page. Pick the account whose OneDrive you want to use. Work, school and personal Microsoft accounts all work. 4. Review what Microsoft says the app will be able to do, and accept. 5. You come back to the Connections tab, and the OneDrive card now shows Connected. With OneDrive connected, you can ask the assistant to: - Show the files you opened or changed most recently, and the files other people shared with you. - Browse a folder, and search your OneDrive by file name and, where Microsoft has indexed it, by content. - Open a file from a sharing link you paste into the chat. - Read plain-text files (txt, csv, json and similar) directly. A long file is cut at a limit. - Save a copy of a file into your files (My Files › Chat, or a folder you name), so it can be read, searched and used like any document. PDF, Word, Excel and image files have to be saved this way before the assistant can read them. Nothing changes in OneDrive. - Upload a file from your project to OneDrive. It always arrives as a new file: if the name is taken, the copy gets a numbered name and nothing is overwritten. - Create a folder, rename a file or folder, or move it to another folder of the same drive. - Replace the content of an existing file with a new version, or create a sharing link — only after you approve it. See "Approval before sending". The assistant cannot delete anything in OneDrive, and it cannot copy a whole folder. Files up to 50 MB can be saved or uploaded. Examples: - "What was the spreadsheet I was working on yesterday in OneDrive?" - "Find the pump test plan in my OneDrive, save it and tell me the acceptance criteria." - "Upload this report to my OneDrive, in the Handover folder." - "Create a view-only link for that file." (the assistant shows you the link details and waits for your approval) ## How to connect SharePoint, and what the assistant can do with it To connect: 1. Go to Settings, Connections tab. 2. On the SharePoint card, click Connect. 3. Your browser goes to Microsoft's sign-in page. Pick your work or school account. Personal Microsoft accounts have no SharePoint. 4. Review what Microsoft says the app will be able to do, and accept. 5. You come back to the Connections tab, and the SharePoint card now shows Connected. If Microsoft says the app needs admin approval, your IT administrator has to allow it once for your organisation. With SharePoint connected, you can ask the assistant to: - Find a team site by name, list the sites you follow, or open a site from a link you paste. - List the document libraries of a site. - Browse a folder of a library, and search it by file name and, where Microsoft has indexed it, by content. - Read plain-text files (txt, csv, json and similar) directly. A long file is cut at a limit. - Save a copy of a file into your files (My Files › Chat, or a folder you name), so it can be read, searched and used like any document. PDF, Word, Excel and image files have to be saved this way before the assistant can read them. Nothing changes in SharePoint. - Upload a file from your project to a library. It always arrives as a new file: if the name is taken, the copy gets a numbered name and nothing is overwritten. - Create a folder, rename a file or folder, or move it to another folder of the same library. - Replace the content of an existing file with a new version, or create a sharing link — only after you approve it. See "Approval before sending". The assistant only reaches the sites and files your own Microsoft account can open. It cannot delete anything in SharePoint, it cannot move items between libraries or sites, and it cannot copy a whole folder. Files up to 50 MB can be saved or uploaded. Examples: - "Find the Engineering site in SharePoint and list its document libraries." - "Search the project library for the latest switchgear FAT report and save it." - "Upload the commissioning report to the Handover folder of that library." ## Autodesk Construction Cloud and BIM 360 — available on request, and what it is built to do The Autodesk Construction Cloud connection is new and is switched on one account at a time, on request. Until it is enabled for you, the Connect button on the Autodesk Construction Cloud card is greyed out; hover over it and it says "Available on request". Email info@cx-assistant.com from your account and the team will enable it for you. Once it is enabled: 1. Go to Settings, Connections tab. 2. On the Autodesk Construction Cloud card, click Connect. 3. Your browser goes to Autodesk's sign-in page. Sign in with your Autodesk account and allow access. 4. You come back to the Connections tab with Autodesk Construction Cloud connected. One more step on Autodesk's side: the administrator of your Autodesk account has to add the Cx Assistant app under Account Admin › Custom Integrations. Until that is done, Autodesk refuses to return any data for that account. The connection is built to let you ask the assistant to: - List the Autodesk accounts and the ACC and BIM 360 projects you belong to, and the members of a project. - List and filter the issues of a project, and read one in full with its comments. - List and read RFIs, and list and read submittals. - Browse the folders of a project's Files area, search files by name, and save a copy of a file into your files (My Files › Chat, or a folder you name) so it can be read like any document. Files up to 50 MB. Nothing changes in Autodesk. - Create an issue, change one (status, assignee, title, description, dates, location or type), or add a comment to one — only after you approve it. - Create an RFI — only after you approve it, and always as a draft: only you see it until you review and submit it in Autodesk, where you also pick who answers it. It does not delete anything in Autodesk, it does not upload files there, and submittals are read only. You only see the projects and modules your own Autodesk account can open. Cx Assistant keeps its own issues, RFIs and documents. When you say "issue", "RFI" or "document" without naming Autodesk, ACC or BIM 360, the assistant takes it to mean the ones in Cx Assistant. Name Autodesk in your request when you mean the other side. Examples: - "List the open issues assigned to me in the Autodesk project North Substation." - "Find the latest single-line diagram in the ACC project files and save it." - "Raise this as an issue in Autodesk." (the assistant shows you the issue and waits for your approval) ## Procore — available on request, and what it is built to do The Procore connection is new and is switched on one account at a time, on request. Until it is enabled for you, the Connect button on the Procore card is greyed out; hover over it and it says "Available on request". Email info@cx-assistant.com from your account and the team will enable it for you. Once it is enabled: 1. Go to Settings, Connections tab. 2. On the Procore card, click Connect. 3. Your browser goes to Procore's sign-in page. Sign in with your Procore account and allow access. 4. You come back to the Connections tab with Procore connected. One more step on Procore's side: the administrator of your Procore company has to install the Cx Assistant app under Company Admin › App Management. Until that is done, Procore refuses to return any data for that company. The connection is built to let you ask the assistant to: - List the Procore companies and projects you belong to, and the people in a project's directory. - List and filter the RFIs of a project and read one in full with its question, answers and attachments. - List and read submittals, with their approval workflow. - List and filter punch items and observations, and read one in full with its comments. - Browse the folders of a project's Documents tool, search files by name, and save a copy of a file into your files (My Files › Chat, or a folder you name) so it can be read like any document. Files up to 50 MB. - List the drawing areas and drawings of a project, and save the PDF of a drawing into your files. - Create a punch item, change one (status, assignees, name, description, dates, priority or type), or add a comment to one — only after you approve it. - Create an observation — only after you approve it. - Create an RFI — only after you approve it, and always as a draft: Procore gives it no number and notifies nobody until you review and submit it in Procore, where you also pick who answers it. It does not delete anything in Procore, it does not upload files there, and submittals are read only. You only see the projects and tools your own Procore account can open. Cx Assistant keeps its own issues, RFIs and documents. When you say "issue", "RFI", "punch item" or "document" without naming Procore, the assistant takes it to mean the ones in Cx Assistant. Name Procore in your request when you mean the other side. Examples: - "List the open RFIs that are with me in the Procore project Data Center 2." - "Find the latest single-line diagram in the Procore documents and save it." - "Raise this as a punch item in Procore, assigned to Ben." (the assistant shows you the item and waits for your approval) ## How to connect Gmail, and what the assistant can do with it Gmail is available on request. If the Connect button on the Gmail card is greyed out, hover over it: it says "Available on request". Email info@cx-assistant.com from your account and the team will enable it for you. Once it is enabled: 1. Go to Settings, Connections tab. 2. On the Gmail card, click Connect. 3. Sign in with Google and accept. 4. You come back to the Connections tab with Gmail connected. With Gmail connected, you can ask the assistant to: - Search your mail and read messages and threads. - See your labels. - Save an attachment from an email into your files (My Files › Chat, or a folder you name), so it can be read, searched and used like any document. - Write a draft for you to review and send from Gmail yourself, with files from the project attached if you ask. - Change a draft you already have: its recipients, subject or text, or add a file to it or take one off. The draft is corrected in place, not duplicated; a removed file stays in your files. The assistant never sends email from Gmail, and it cannot delete mail. Attachments up to 50 MB can be saved; a draft can carry up to 25 MB of files, Gmail's limit. ## How to connect Notion, and what the assistant can do with it 1. Go to Settings, Connections tab. 2. On the Notion card, click Connect. 3. Your browser goes to Notion. Pick your workspace and choose which pages to share. 4. You come back to the Connections tab with Notion connected. The assistant only sees what you shared on Notion's screen. With Notion connected, you can ask the assistant to: - Search your workspace and read pages and databases. - Create or update pages, comments and database rows. Moving pages and changing the structure of a database always ask for your approval first, because they are hard to undo. ## How to use a connected service in chat There is nothing to switch on in the chat. Once a service is connected, just ask in plain language and the assistant uses it when it is needed. While it works you see a status line such as "Asking Outlook…". When it finishes, the step reads like "Outlook: Search messages". Connected services are available to these assistants: Commissioning Assistant, General Assistant and My Workspace Assistant. The assistants inside the Word, Excel and PowerPoint add-ins do not use them. If the assistant says it cannot reach your mail, check which assistant is selected. ## Approval before sending — emails, invitations, sharing links and Autodesk changes always ask first Anything that reaches other people cannot be taken back, so the assistant always stops and asks before it: - sends an email or a draft from Outlook; - sends a meeting invitation, changes an event, answers an invitation, or cancels an event in Outlook Calendar; - replaces the content of an existing file, or creates a sharing link, in OneDrive or SharePoint; - creates an issue, changes an issue, comments on an issue, or creates an RFI draft in Autodesk Construction Cloud. This happens in every approval mode, including Auto, and there is no "don't ask again" option for these actions. An "Approval required" card appears in the chat and shows exactly what will go out: - For an email: a title like "Send email to ana@acme.com", then To, Cc, Bcc, Subject, Attachments and the Message text (only the fields that apply). A reply also shows In reply to. - For a meeting invitation: When, Attendees, Optional attendees, Location, Online meeting and Description. - For a cancellation: When, Attendees who get the cancellation, and your Comment. - For a sharing link: a title like "Create sharing link: Test plan.pdf", then the File or Folder, the Link type (View only or Can edit) and Who can open it. A link works for whoever receives it and cannot be withdrawn from the chat. - For a file replacement: a title like "Replace file: Test plan.pdf", then the File and New content from (the file that will become the new version). - For an Autodesk issue: a title like "Create issue in Autodesk: ...", then Project, Type, Status, Assigned to, Due date, Location and Description. A change to an issue shows only the new values, and a comment shows the Issue and the Comment. - For an Autodesk RFI: a title like "Create RFI draft in Autodesk: ...", then Project, Question, Suggested answer, Due date, Location and Reference. Read it, then click Approve to go ahead, or Decline all to stop. If you decline, nothing is sent or changed and you can tell the assistant what to change. ## Approvals for other connected-service actions Reading never asks: searching mail, opening a message, checking your agenda, reading a Notion page, browsing or searching OneDrive and SharePoint, or listing Autodesk issues, RFIs, submittals and files run straight away. Smaller changes — creating a draft, moving a message, adding an appointment, creating a Notion page, saving a copy of a file into your files, uploading a new file to OneDrive or SharePoint, creating a folder there, renaming or moving a file — follow the approval mode you chose in the chat composer: - Auto and Ask for critical: they run without asking. - Ask for edits: every change asks first. On the card you can tick "Don't ask again for ... in this chat" for an action you trust. Sending email, anything that notifies other people in your calendar, replacing a file or creating a sharing link in OneDrive or SharePoint, creating or changing an issue or RFI in Autodesk, and Notion's hard-to-undo changes ask every time, whatever the mode. ## How to choose which tools the assistant may use 1. Go to Settings, Connections tab. 2. Click the small arrow on the right of a connected card to open it. 3. Under Tools, every action the service offers is listed with a "read" or "write" badge. Switch a tool off to hide it from the assistant completely. For example, switch off the send tools on Outlook if you never want the assistant to send mail, even with approval. Two more controls: - Always load its tools: puts every tool of this service in the assistant's list from the first message. Leave it off unless you use the service constantly. - Refresh tools (the round-arrow icon on the card): reads the list of tools again, for example after the service adds new ones. ## How to add your own server (Your MCP servers) Besides the listed services, you can add any server that speaks the Model Context Protocol over HTTPS. This is available on request: if the Add server button is greyed out, email info@cx-assistant.com. 1. Go to Settings, Connections tab. 2. Under Your MCP servers, click Add server. 3. Enter a Name (for example "Jira") and the Server URL. 4. Choose the Authentication: Sign in (OAuth), Token (sent as a bearer header), or None. For Token, paste the token. For Sign in, the Client id is optional — fill it in only if the server's administrator gave you one. 5. Optionally switch on "Trust this server's read/write labels". 6. Click Save. With Sign in, your browser goes to the server's sign-in page and then comes back. About trust: when it is off, every tool of that server counts as a change, so in the Ask for edits mode each one asks before it runs. When it is on, tools the server marks as read-only count as reading and never ask. Only trust servers you know. You can change this later inside the card. The server must be reachable on the public internet. Addresses on a private network are refused. ## How to remove or reconnect a connection To remove a connection: 1. Go to Settings, Connections tab. 2. Click the bin icon (Remove) on the card. 3. Confirm in the "Remove this connection?" dialog. The assistant loses access immediately. You can connect the service again later with Connect. To reconnect: when a sign-in has expired or was withdrawn, the card shows Needs reconnecting and a Reconnect button. Click Reconnect and sign in again; your tool choices are kept. A server added with a token has no Reconnect button — remove it and add it again with a new token. ## Troubleshooting connections - The chat says "Outlook needs to be reconnected" (or another service): go to Settings, Connections tab, and click Reconnect on that card. Then ask again. - "Sign-in didn't complete (...). Try again.": the sign-in was cancelled or timed out. Click Connect or Reconnect once more and finish the sign-in in one go. - The Connect button is greyed out: hover over it. "Available on request" means you need to email info@cx-assistant.com; "Not available on this server yet." means the service is not set up. - The card shows Error: a red line under the name says why. Try Refresh tools; if it stays, remove the connection and connect again. - Microsoft says the app needs admin approval: ask your IT administrator to allow it for your organisation. - The assistant does not seem to know about your mail: check that the card says Connected, that the tool you need is switched on, and that you are using the Commissioning, Full, General or My Workspace Assistant. - The assistant cannot see a Notion page: you did not share it when connecting. Remove the Notion connection and connect again, sharing that page. - The assistant cannot read a PDF, Word or Excel file in OneDrive or SharePoint: ask it to save the file first. Only plain-text files are read in place. - The assistant cannot find a SharePoint site: paste the site's link into the chat, or check that you signed in with the work or school account that can open that site. - OneDrive or SharePoint says you have no access to an item: your Microsoft account cannot open it. Check your access with the owner of the file. - A file will not save or upload: files above 50 MB are refused, and a whole folder cannot be copied. - A file in OneDrive or SharePoint cannot be changed because it is locked: someone has it open for editing or checked out. Try again when they have closed it. - Autodesk refused the request: the usual causes are that your Autodesk account administrator has not added the app under Account Admin › Custom Integrations, that you are not a member of that project, or that your role has no access to that part of the project (issues, RFIs, submittals or files). - The Connect button on the Autodesk Construction Cloud card is greyed out: it is available on request. Email info@cx-assistant.com. - You asked about an issue and the assistant looked in the wrong place: say "in Autodesk" (or ACC, or BIM 360) when you mean an Autodesk issue, RFI or file. Otherwise the assistant uses the ones in Cx Assistant. ## Privacy — what is stored when you connect a service - You sign in on the service's own page (Microsoft, Google, Notion or Autodesk). The app never sees your password for that service. - The app keeps only the access it was granted, stored encrypted and tied to your account. Nobody else on your team can use your connections, and they are not shared with your projects. - Your mailbox, calendar, OneDrive, SharePoint sites, Notion workspace and Autodesk projects are not copied into the app. The assistant looks things up only when a request in your chat needs it, and what it reads becomes part of that chat's conversation. The one exception is a file or attachment you ask it to save: that copy is stored in your files. - Removing a connection deletes the stored access straight away. - Emails and invitations are never sent without your approval on the card, and the assistant cannot delete mail or files in OneDrive, SharePoint or Autodesk. --- # Dashboards Cx Assistant help · platform: web · module: dashboards · updated 2026-10-08 Canonical: https://cx-assistant.com/en/help/web/dashboards ## What are dashboards Dashboards are custom pages of charts and metrics built from your project's data — assets, issues, RFIs, reviews, scripts, and trackers. Each dashboard is a set of sections containing widgets (charts and figures) that render live data every time you open it. Open Dashboards from the sidebar. Viewing requires the dashboards.read permission (all built-in roles have it). You can build dashboards yourself in the builder, or ask the AI to build them for you — see the Build dashboards with AI section. ## The dashboards list The Dashboards page shows every dashboard you can see as a card with a mini-preview thumbnail, so you can recognize each one at a glance. Click a card to open the dashboard. Users with the dashboards.manage permission also see create and delete actions here, and users allowed to build dashboards in chat see a Build with AI button that opens a new chat with the Commissioning Assistant. ## How to create a dashboard 1. On the Dashboards page, click the create button (requires the dashboards.manage permission — Project Admins and Project Members by default). 2. Start from BLANK or pick a starter template: Project overview, Issues deep-dive, Delivery, or My work. 3. Give it a name and description. 4. Set the visibility toggle to control whether it's shared or just for you. 5. Create — then open the builder to add or adjust sections and widgets. Prefer talking it through? The Build with AI button on the same page opens a chat where the assistant creates and edits the dashboard for you. ## The dashboard builder: sections, widgets, and filters Click Edit on a dashboard (requires dashboards.manage) to open the builder: - Title and description: edit at the top. - Sections: add, rename, reorder, and delete sections to organize the page. - Widgets: add a widget to a section and configure it in the widget editor — choose the data source (a dataset or an insight template), group-bys, metrics and filters, then the widget type: chart, number card, table, progress, text, or divider. - Width: each widget takes a share of a 12-column row (a number card 3, a chart 6, a table 6). A dashboard reflows on its own when its column is narrow (the chat panel open, a small window): small cards pair up and charts stack; "Width when narrow" in the widget editor overrides that for one widget. On phones everything is full width. - The preview inside the widget editor runs automatically as you change the query, so you always see real data while you build. If it shows "Run preview to see data", the query hasn't run yet. - Filters: define the filters viewers will see on the dashboard, including defaults (see the filter bindings section). Click Save when done — the server re-validates the dashboard before storing it. ## Datasets and insight templates — what data can a widget show A widget's data comes from one of two source kinds: DATASETS — build your own query over the project's raw records: - Issues: one row per issue — status, priority, type, created and closed dates, assignee, plus "Open" and "Assigned to me" filters. - RFIs: one row per RFI — status, priority, type, created/closed dates, due date, official response date, plus "Open" and "Overdue" filters. - Assets: one row per asset — type, category, status, location, created date, and the number of open issues linked to each asset. - Reviews: one row per document review — open, closed, or cancelled, with opened and closed dates. - Scripts: one row per commissioning script — status (not started, in progress, completed, on hold, failed) and progress. - Tracker rows: one row per row across the project's trackers. INSIGHT TEMPLATES — ready-made analyses with tunable settings: - Issues created vs closed: cumulative created and closed issues over time. - Asset plan vs actual: cumulative planned vs actual asset sign-offs over time, optionally restricted to a sub-population of assets (for example, only assets with open issues). - Tracker summary: one tracker's cell totals by status. - Document tracker: document approval progress per document group (total, linked, approved, pending, rejected). Pick Dataset when you want to slice raw data your own way; pick Insight template when one of the curated analyses already answers your question. ## Metrics glossary — what each metric means Metrics are the numbers computed over your query's matching rows: - Count: the number of matching rows (issues, assets, RFIs, …). The default metric everywhere. - Average close time (issues, RFIs): average days from creation to close. Items that are not closed yet are left out of the math, so combine it with a "Closed has a value" or "Open is false" filter to make the population explicit. - Median close time (issues): the middle value of days-to-close — half closed faster, half slower. Less sensitive to outliers than the average. - 90th-percentile close time (issues, RFIs): 9 out of 10 items closed within this many days. A good "worst realistic case". - Longest close time (issues): the single slowest item's days-to-close. - Average cycle time / 90th-percentile cycle time (reviews): days from a review opening to closing. - Average response time (RFIs): average days from RFI creation to the official response. - Average completion days (scripts): average days from script creation to close. - Average progress percent (scripts): the average completion percentage across matching scripts. - Open issues (assets): how many non-closed issues are linked to each asset. Also usable as a filter — "Open issues is greater than zero" gives you only the assets that currently have open issues. In the pickers, each metric shows this plain-language description under its name. ## Chart mapping: category axis, values, and series A chart widget maps your query's output onto chart slots: - Category / time axis: which field labels the bottom axis — usually your first Group by (for example status, or a time bucket). - Values: the metric(s) that set the bar heights or line positions — you can pick more than one. - Split into series by: an optional second field that splits the data into multiple colored series (for example priority within each status). - Donuts and treemaps use Slice labels and Slice values instead of axes. - Breakdown bars (the Home dashboard's priority bars) draw one full-width bar per category with segments sized by their share of that row, the count at the right end — pick it over stacked bars when row totals differ a lot. It needs a category axis and a series split. The builder fills the mapping in automatically from your query — first group-by becomes the category axis, metrics become values, a second group-by becomes the series — and keeps it in step when the query changes. If the preview shows a warning like "To draw this chart, choose: category / time axis", the chart is missing a required slot: pick a field for it (usually by adding a Group by to the query) and the chart will draw. Series colors can be overridden per series name — colors are matched by the name shown in the legend. Three taste knobs sit under the mapping: - Colors: Project colors (the default) use your status and priority colors where the data has them; Brand lime draws one series in lime and two series as a grey reference plus lime (plan vs actual, created vs closed); Categorical palette uses the fixed palette and ignores flow colors. A color set per series always wins. - Legend: shown when there are several series, or always, or never. - Grid lines: Faint (the default, the Home dashboard's hairline look), Normal, or None. Grid lines exist on bar, line and area charts only. ## Dashboard filters and widget bindings The filters a viewer sees at the top of a dashboard only affect widgets that are BOUND to them — a binding says which field of the widget's data a filter applies to. You normally never have to manage this by hand: - When you add a filter, it automatically binds to every widget whose data has a matching field. - When you add a widget, it automatically picks up bindings for the dashboard's existing filters. - A date-range filter binds to each widget's date field, so one date filter can drive different date fields on different widgets. Your manual choices always win: in the widget editor's Dashboard filters section you can point a binding at a different field or set it to "Not bound" to opt that widget out — automatic binding never overrides what you set. In the builder, widgets that no dashboard filter affects show a "Not affected by filters" badge, so you can spot them at a glance. If a viewer changes a filter and one widget doesn't react, that widget is unbound — open its editor and bind the filter. ## Number cards: getting a single total A number card (KPI) shows ONE number: the chosen metric read from the first row of its query's result. For a project-wide total, the query should return a single row — leave Group by empty. If the query returns several rows (because it groups by status, priority, and so on), the card can only show the first group's number — which is usually not the total you meant. The builder warns you: "This query returns N rows — this widget shows only the first. Remove Group by to get a single total." Do exactly that, or add filters until one row remains. When a dashboard filter (or the card's own filter) narrows a number card, the card says "Filtered" under the figure — so a total that differs from the project-wide one does not read like a bug. ## Headline figure: the big number under a chart title A chart or table widget can show a headline figure under its title — the "161 · 16% closed" row the Home dashboard uses. Turn it on in the widget editor under Headline figure. - Figure: one metric from the widget's own query. Read it from the last row (right for cumulative series such as issues over time), the first row, the sum of all rows (a total across a breakdown) or the largest row. - Number format: whole number, compact (1.2k) or percent. - Chip: optional text next to the figure. Write {percent} in it where a percentage goes, then choose which metric is a percentage of which (closed out of created gives "16% closed"). A chip without a percentage is a plain label. The headline is computed from the same rows the chart draws, so filters that change the chart change the figure too, and PDF, Word and PowerPoint exports print the same number. ## Progress widgets: a percent field, or value out of total A progress widget draws a progress bar from the first row of its query's result, in one of two modes: - A percent field: pick one field that already holds a 0–100 value (for example a script's average progress percent). - Value out of total: pick two fields — the bar shows value ÷ total (for example approved documents out of all documents, using the Document tracker template). Layout: One bar reads the first row only. One bar per row draws a bar for every row of the result, named by the field you choose as the label — the Asset completion card on Home is this layout over the Asset status completion template, one bar per status with the value out of total under it. Bars are green from 70%, amber from 40% and red below. If the widget says it needs its fields set, the chosen fields don't yield a usable number for the current query — switch mode or pick different fields, and use the preview to check. ## Assigned to me and the My work dashboard The issues dataset has an "Assigned to me" filter. It is VIEWER-RELATIVE: "me" means whoever is looking at the dashboard right now. On a shared dashboard, each person sees their own issues — two colleagues open the same dashboard and get different, correct numbers by design. An export to PDF, Word or PowerPoint likewise captures the issues of the person who exports. Details worth knowing: - "Assigned to me is false" means "not assigned to me" — unassigned issues are included. - The Assignee field can also be filtered or grouped directly for per-assignee breakdowns. - Filtering by a group or team's assignments is not available yet. The quickest start is the My work starter template when creating a dashboard: it comes with "my open issues", "my issues by status", and a table of what's assigned to you — and every viewer of it sees their own workload. ## Build dashboards with AI You don't have to build dashboards by hand — the Commissioning Assistant can do it with you in chat. Describe what you want to see ("a delivery dashboard: plan vs actual sign-offs, open issues by priority, and my open issues") and it will: - Create a new dashboard, or open and extend an existing one. - Add, edit, and remove sections and widgets — charts, number cards, tables, progress bars, and text. - Set up the viewer filter bar and bind the filters to the right widgets. - Preview every query and chart with your real project data before applying it, and iterate until it looks right. - Inspect the project's datasets so it uses your exact statuses, types, and priorities. - Build viewer-relative "my work" widgets, so a shared dashboard shows each person their own items. To start, click Build with AI on the Dashboards page — it opens a new chat — or simply ask for a dashboard in any Commissioning Assistant chat on the web. Building dashboards in chat requires its own permission (granted to project admins by default), and the assistant's changes go through the same permission checks as the builder — it can never show data you couldn't see yourself. ## Viewing a dashboard: filters and refresh Open a dashboard to see its widgets rendered with live data. The actions sit in the title row and appear when the pointer is over it (always shown on touch screens): - Filters: the filter icon opens a card with the dashboard's filters (defaults set by the dashboard's author), time window first. A badge on the icon counts the filters you changed from their defaults; Reset inside the card puts them back. They narrow every widget bound to them. - Refresh: reload every widget's data. - Export: PDF, Word or PowerPoint. - Edit (pencil): opens the builder (only shown with the dashboards.manage permission). Hover a chart to reveal its own controls, at the top right of the card: - The sliders icon opens the dashboard filters this widget is bound to, so you can narrow one chart without changing the others. The icon stays lit while a card-level filter is active; "Use the dashboard filters" clears it. - Plan vs actual charts add a time-horizon toggle (Until today / Full schedule) and one chip per asset status to look at a single status. These choices are not saved with the dashboard; an export made from the page carries them, so the file shows what you were looking at. With the dashboards.manage permission the hover controls also include a gear. It opens a small panel to change the chart's look without entering the builder: its shape (only the shapes the chart's fields can feed), the palette, one color per series or bar, the legend, the grid lines and the card height. Changes draw at once and are saved to the dashboard for everyone a moment later; "Open in the builder" continues on the same widget with every option. The assistant can change the same things. Click a bar, a slice, a breakdown segment or a point on a line to open the records behind it over the chart, inside the card: the key columns of each record, a Load more button for long lists, and Copy list to put the IDs on the clipboard. Click a row to open the record — assets and issues open in place, RFIs, reviews, scripts and trackers go to their page. The list is computed with your permissions, like the chart. A dashboard's author (or the assistant) can switch click-through off for a widget. Everything you see is computed from data YOUR account can read — see the data-access section. ## Export a dashboard to PDF, Word or PowerPoint 1. Open the dashboard. 2. Apply any filters you want reflected in the export. 3. Click the Export button (the download icon next to Refresh). 4. Choose Export as PDF, Export as Word or Export as PowerPoint. 5. The file is generated and opens in a new browser tab so you can save or share it. The Export button is greyed out while the file is being built. What each format gives you: - PDF: a landscape document that keeps the dashboard's grid — widgets sit side by side as they do on screen. - Word: a portrait A4 document. Word has one column, so the widgets follow one after another, section by section. - PowerPoint: a widescreen deck with a title slide, then one slide per dashboard section. A section that does not fit continues on "(cont.)" slides. All three start with the dashboard's name and description, the project name and the date it was generated. They contain the same content: section titles, charts, number cards, tables, progress bars and text. In Word and PowerPoint the charts are pictures, so you can resize them but not edit their data. The export captures the dashboard as YOU see it: your filters, your data permissions, and — for "Assigned to me" widgets — your own assignments. A widget over data you cannot read shows the note "The exporting user does not have access to this data" instead of numbers. ## Dashboards and data access — widgets never show more than you can see Dashboard data always respects the VIEWER's permissions. When you open a dashboard, each widget only computes over data your own role can already read — for example, a widget over assets shows nothing to a viewer without assets.read. This also means the dashboards.manage permission never widens data access: building or editing a dashboard doesn't let anyone see data they couldn't see elsewhere, and two people can open the same dashboard and see different numbers if their permissions differ. The same holds when the AI assistant builds a dashboard — it works within your permissions. ## Who can view and manage dashboards (permissions) - dashboards.read — open the Dashboards page and view dashboards. Default: Project Admin, Project Member, Technician. - dashboards.manage — create, edit, and delete dashboards. Default: Project Admin, Project Member. - Building dashboards in chat (Build with AI) has its own permission (agents.dashboards, "Dashboards skill in the assistant"), granted to project-admin roles by default. The project owner can always do everything. Remember: dashboards.manage only controls who can BUILD dashboards — the data each viewer sees is always limited by that viewer's own read permissions. ## Dashboards troubleshooting - Dashboards missing from the sidebar: your role lacks dashboards.read — ask a project admin. - No create or Edit button: you need the dashboards.manage permission. - A chart in the builder stays blank: it's usually missing a required mapping slot — the preview says which (for example "To draw this chart, choose: category / time axis"). Add a Group by or pick the field in the Chart section. - A number card shows a strangely small number: its query returns several rows and the card reads only the first — remove Group by to get a single total. - A viewer filter doesn't change one widget: that widget isn't bound to the filter — in the builder it shows a "Not affected by filters" badge; open the widget editor's Dashboard filters section and bind it. - A widget looks empty or numbers differ from a colleague's: widget data is computed with YOUR permissions — and "Assigned to me" widgets intentionally show each viewer their own items. - Numbers look stale: click Refresh to reload all widgets. - Save fails in the builder: the server re-validates the dashboard — check each widget has a valid data source, metric, and chart configuration. - A widget shows a faint ghost chart and "No issues yet" (or no assets, RFIs, reviews, scripts, tracker rows): the project has no records of that kind yet — nothing is broken. The button under the message opens the page where the first one is added; it only appears when you have permission to create them. To change the wording, set the widget's Empty-state message in the builder. --- # Documentation Cx Assistant help · platform: web · module: documents · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/documents ## What is the Documentation module Documentation is the project's file manager. It holds every document, drawing, photo, and folder in the project, and it is where scripts and templates live too. You can upload, organise into folders, preview, annotate, version, review, and download files from here. Open it from Documentation in the sidebar. Viewing needs the documents.read permission (all built-in roles have it). Your personal files live in a separate My Workspace area reached from the project switcher. ## Documentation page layout at a glance The page has: - A left sidebar with scopes (All files, Recent, Starred, Mine, Chat files, Templates, Trash) and a folder tree. - A top bar with breadcrumbs, search, sort, filters, a grid/list view switch, and a details-pane toggle. - The main area showing your files as a grid of cards or a list. - A slide-in preview pane on the right when a file is selected (a bottom sheet on small screens). - Floating action bars: a primary actions bar, and a bulk actions bar when multiple items are selected. - A floating Downloads tray for ZIP exports. On narrow windows the toolbar collapses into an overflow menu. ## Scopes in the left sidebar The sidebar lets you switch between views of your files: - All files: everything you can see in the project. - Recent: recently touched files. - Starred: files you starred (shows a count badge). - Mine: files you uploaded or created. - Chat files: files uploaded through the AI assistant. - Templates: script templates. - Trash: deleted items (shows a count badge). Below the scopes is the folder tree. When you open a script, the sidebar temporarily swaps to that script's section outline instead. ## How to use the folder tree The folder tree in the sidebar mirrors your folder structure: - Click a folder to open it; use the arrows to expand or collapse branches. - "All folders" at the top takes you back to the root. - Use the new-root-folder button next to the tree to create a folder at the top level. - Folder rows are drop targets: drag files or folders from the main area onto a tree row to move them there. ## Search, sort, and switch between grid and list In the top bar: - Search: type to find files by name. - Sort: order by name, last modified, size, or type — ascending or descending. - View switch: toggle between a grid of cards and a compact list. - Details-pane toggle: show or hide the preview pane. Breadcrumbs above the content show where you are; click any crumb to jump back up. ## Filter files by type, approval, or review Open the filter menu in the top bar (it shows a count badge when filters are active). You can filter by: - File type category: image, PDF, doc, sheet, slide, video, audio, text, archive, code, data, or other. - Approval status: any, approved, pending, or rejected. - Review status: any, in review, approved, or rejected. - A specific review: pick one review (R-1, R-2, …) to see exactly the files in it — this picker needs the reviews.read permission. Folders stay visible while filters are active so you can keep navigating. ## How to upload files and folders Three ways to upload (needs documents.create): 1. Click New, then Upload files, and pick files from your computer. 2. Click New, then Upload folder, to upload a whole folder with its structure. 3. Drag files or folders from your computer anywhere onto the page — a drop overlay appears; drop to upload into the current folder. An upload manager panel shows per-file progress. Thumbnails appear shortly after upload as they are generated. ## How to create a new folder 1. Navigate to where you want the folder. 2. Click New, then New folder. 3. Type a name and confirm. You can also use the new-root-folder button next to the folder tree to create a folder at the top level. Creating folders needs the documents.create permission. ## Rename, move, star, or download an item Right-click an item (or open its context menu) for the common actions: - Open / preview it. - Download it. - Star or unstar it — starred files collect in the Starred scope. - Rename it (or press F2 with the item focused). - Move it — a folder picker opens; when moving several items into a folder with name conflicts, a conflict dialog helps you resolve them. - Delete it. When several items are selected, the menu acts on all of them ("N items"). You can also move items by dragging them onto a folder card or a folder-tree row. Rename and move need documents.update; starring is personal and always available. ## How to delete documents and what the impact summary means Select one or more items and choose Delete (context menu, bulk bar, or the Delete key). Before anything is removed you see an impact summary describing what the deletion affects — for example items inside a folder — so you can confirm with full knowledge. Deleted items go to Trash, where they can be restored. Deleting needs the documents.delete permission (Project Admin by default). Files in your personal My Workspace area are always fully yours to delete. ## Select multiple files at once Ways to build a selection: - Click an item to select it. - Shift+click to select a range. - Ctrl+click (Cmd+click on Mac) to add or remove single items. - Drag on empty space to draw a marquee (rubber-band) around items. - Ctrl/Cmd+A selects everything in the current view; Esc clears the selection. With items selected, a floating bulk action bar appears with: download, move, star, send to review (needs reviews.create), delete, and clear selection. ## Keyboard shortcuts in Documentation - Ctrl/Cmd+A: select all items in the view. - Esc: clear the selection. - Delete: delete the selected items (with impact summary and confirmation). - Enter: open the focused item. - F2: rename the focused item. - Arrow keys: move focus between items. - Space: toggle selection of the focused item (list view). ## How to see a document's version history Open a document's context menu and choose Version history. The dialog lists the versions of the file over time, so you can see how many times it was re-uploaded and access earlier versions. The Details tab of the preview pane also shows the version count. Uploading a file with the same name into the same place adds a new version rather than a duplicate. ## The preview pane and its tabs Select a file and the preview pane slides in (or toggle it with the details-pane button; on small screens it appears as a bottom sheet). It has four tabs: - Details: type, size, modified and created dates, status, version count, and who uploaded it. - AI: information the assistant extracted from the file — title, description, keywords, language, and page count. - Markups: annotations on the document, with a count badge. - Processing: the file's processing pipeline status. Editing the editable fields needs the documents.update permission. ## AI info and document processing status The AI tab of the preview pane shows what the assistant extracted from the document: title, description, keywords, language, and page count. This is what makes the file searchable and citable by the AI assistant. The Processing tab shows where the file is in the processing pipeline: unprocessed, queued, processing, ready, or failed. If processing failed, the quickest fix is the Retry button in the processing queue, which anyone in the project can use (see the processing indicator and queue section). The Processing tab also has a re-run action that restarts a single processing phase — that one is gated by the rag.detailed.process permission, so most users will ask an admin for it. ## The processing indicator and queue After upload, every file is prepared for search and for the AI assistant. This runs in the background — you can keep working or leave the page. Two things show you how it is going. The indicator in the header: - A small ring with a number appears next to the notifications bell while files are being processed. It shows on every page, not only in Documentation. - The ring fills as files finish; the number is how many files are still in progress. Hover it for the detail, for example "4 of 7 done · 2 processing · 1 waiting". - When nothing is running but some files failed, it turns into a red warning icon with the number of failed files. When nothing is running and nothing failed, it disappears. - Click it for a quick view without leaving your page: the counts, a progress bar, any failed files with their Retry buttons, and an "Open documents page" link. That link opens Documentation (or My Workspace) with the queue already expanded. The "Processing documents" tray on the Documentation page: - A floating card that shows a one-line summary. Click its header to expand it. - Expanded, it lists the files in progress, each with its own progress bar, then the files marked "Waiting…", and "+N more waiting" when the list is long. Click a row to open that file in its folder. - It covers the whole project, so you also see files uploaded by teammates or from another device. - While your own upload panel is on screen the tray stays hidden, and takes over once the upload panel closes. - When everything is finished it reads "Processing complete" and tells you how many documents are now searchable and available to the AI. Close it with the x. When files fail: 1. Open the quick view from the header indicator, or expand the tray. 2. Under "N documents failed processing", each file shows its name and the reason. 3. Click Retry on one file, or Retry all to try every failed file again. 4. Some failed files have no Retry button. These cannot be processed automatically (the row may read "This document can't be processed automatically."), so trying again will not help. During system maintenance, processing of new files waits — they stay in the queue as waiting — and resumes by itself when maintenance ends. You do not need to upload again. ## View and annotate documents with markups PDFs and images open in a unified viewer: continuous scroll through all pages, zoom, a thumbnail rail, print, download, open in a new tab, and fullscreen. Switch to edit mode (needs documents.update) for the annotation toolbar: select, rectangle, ellipse, arrow, line, freehand, highlight, text, and pin tools, plus a colour picker, stroke width, and undo/redo. An elements panel lists the markups on each page. The Markups tab in the preview pane shows how many annotations a document has. When the assistant cites a page, the link lands on the right page of this viewer. ## Download many files as a ZIP (Downloads tray) Downloading a single document starts immediately. Downloading a folder, or several items at once, builds a ZIP archive in the background: 1. Select the folder or items and choose Download. 2. The floating Downloads tray appears, showing each export as queued, building (with progress), ready, or failed. 3. When ready, the download starts automatically and a toast confirms it. Finished rows stay in the tray for about 15 minutes, even across page reloads. Possible errors: too many active exports, the selection is too large, or the selection is empty. Notifications also announce when an export is ready or failed and link straight back to the tray. ## What is the Chat files scope The Chat files scope in the sidebar lists files that were uploaded through the AI assistant. Anything you attach in a chat becomes a real document here, so you can find it again, preview it, or move it into your project folders. Chat-uploaded attachments are private to the person who uploaded them. Files uploaded in a chat while no project is active land in the chat folder of your personal My Workspace instead. ## Trash: restore or permanently delete items Deleted items go to Trash. A deleted folder shows as one row — its contents come back with it. How long items stay: there is no countdown on items in the Trash. They stay there until someone empties the trash or deletes them permanently. From that moment a 30-day grace period starts; the items leave the Trash straight away and are removed for good when the 30 days are over. Two places show the Trash: - The Trash scope in the Documentation sidebar. This is the full view: a restore button on every row, plus — with the documents.delete permission — an Empty trash button at the top and a Delete permanently button on each row. - The standalone Trash page. It lists the same items but only restores; it has no Empty trash or Delete permanently. There is no sidebar link to it: click the search bar in the header (or press Ctrl+K, Cmd+K on Mac), type "trash" and pick the Trash page, described as "Deleted files". To restore an item: 1. Open Trash and click the restore button on the row. 2. Confirm when asked. A folder comes back together with the contents it was deleted with. 3. The item returns to its original location. If it cannot go back there, the app opens "Choose where to restore" instead (see below). To delete for good (Trash scope in Documentation only): 1. Click Empty trash for everything, or Delete permanently on one row. 2. Read the confirmation — it explains the 30-day grace period — and confirm. When a restore is refused: - Name conflict: a live item with the same name already exists in the folder it came from. Click Choose another folder to restore it somewhere else, or rename the existing item in Documentation and restore again — restore never renames for you. - The folder it was in is gone: the original folder is still in the Trash or was removed for good. On the Trash page such rows carry a "Parent gone" chip. Clicking restore opens "Choose where to restore": open the folder you want, check the line "It will be restored into: …", and click Restore here. Creating a new folder with the old name does not bring the item back by itself — you still pick it here. If the old folder is still in the Trash you can also restore that folder first, then the item. - Choosing a folder has one rule: an item from My Files can only be restored inside My Files, and a shared project item only into shared project folders. To take it across, restore it first and then move it. - Storage quota exceeded: bringing the item back would go over the storage limit. Deleted files do not count towards your storage, restored ones do — free up space first. Viewing Trash needs documents.read; restoring, emptying and deleting permanently need documents.delete. In My Workspace your own files are always yours to restore. ## See who else is working in Documentation Documentation is live. Presence avatars show who else is currently viewing the same folder, and a connection pill shows your realtime connection status. Changes made by teammates — uploads, renames, moves, deletions — appear for you without reloading the page. ## Who can do what in Documentation Documentation permissions, by default role (the project owner can always do everything): - View files and folders: documents.read — Project Admin, Project Member, Technician. - Upload, create folders and scripts: documents.create — Project Admin, Project Member. - Rename, move, edit details, annotate: documents.update — Project Admin, Project Member. - Delete, restore, purge: documents.delete — Project Admin. - Send to review: reviews.create — Project Admin, Project Member. - Re-run document processing: rag.detailed.process (special grant). Files in your personal My Files / My Workspace area are always fully yours, and chat-uploaded attachments are private to the uploader. If an action is hidden or disabled, ask a project admin to adjust your role. ## Documentation problems — troubleshooting - Can't upload or the New menu is missing options: your role may lack documents.create. - Can't rename, move, or annotate: needs documents.update. - Can't delete or restore: needs documents.delete (Project Admin by default). - A file's status can't be changed: it may be locked because it is in an active review — check its review chip. - The assistant can't find a file's content: the file may still be processing or may have failed. Look at the processing indicator in the header, or the Processing tab in the preview pane. If it failed, click Retry in the processing queue; if there is no Retry button, ask an admin to re-run processing. - ZIP export fails: the selection may be too large or empty, or too many exports are already running — try a smaller selection or wait. - Restore blocked by a conflict: something with the same name exists in the original folder — choose another folder when asked, or rename the existing item and restore again. If the original folder is gone, the app asks you to pick a folder to restore into. If the storage quota would be exceeded, free up space first. - Can't find Empty trash or Delete permanently: they are only in the Trash scope of the Documentation sidebar (not on the standalone Trash page) and need documents.delete. - Missing thumbnails right after upload: they generate in the background — give it a moment. --- # Getting started — your first steps Cx Assistant help · platform: web · module: getting-started · updated 2026-10-19 Canonical: https://cx-assistant.com/en/help/web/getting-started ## Welcome to Cx Assistant Cx Assistant is the AI-powered commissioning platform: one place for your project's assets, issues, RFIs, documentation, trackers and dashboards — with an assistant that can answer questions and do the work with you. This short course walks you through the essentials, each with a mini video. You can watch them in order or jump to the one you need. If you were invited to a project, you're already set — pick the project at the top of the sidebar. If you're starting fresh, create a project from the Home screen and the setup checklist on the dashboard will guide you through the rest. Tip: press Ctrl+K (⌘K on Mac) anywhere to search across the whole app — pages, assets, issues, documents and this help. ## Create your account Creating an account takes three short steps and you are signed in at the end: 1. **Your email.** Type your work email on the sign-up page and click **Continue**. By continuing you agree to the Terms of Service and acknowledge the Privacy Policy; both open from the links under the button. 2. **The code.** We email you a 6-digit code. Type it in (on a phone, the keyboard usually offers it). On the web, the email also has a button that takes you straight to the next step. The code expires after a few minutes; **Send a new code** gets you another one. 3. **Your details.** Your name, an optional surname and a password (at least 8 characters with an uppercase letter, a lowercase letter and a number; the meter under the field tells you how strong it is). Click **Create account** and you land in Cx Assistant, already signed in. **Or use Google or Apple.** The buttons above the email field sign you in with that account in one step; the first time, a Cx Assistant account is created for the same email address. If you already have an account with that email, we connect the two (a code to your inbox may be asked once). In **Settings → Security → Sign-in methods** you can connect or disconnect Google and Apple later, as long as one way to sign in remains. If the email already belongs to an account, we do not say so on the page — we email that address instead, with a sign-in button and a password reset link. Invited to a project? Open the invite link first: the sign-up page then knows your email, skips the code, and your new account joins the project the moment it is created. To change the email of an existing account, go to **Settings → Profile**: we send a code to the new address and switch the account over once you type it in. ## Create your first asset ![Watch: create an asset](https://app.cx-assistant.com/api/help-assets/tour/assets.mp4) Assets are the equipment you're commissioning — AHUs, chillers, panels, VAV boxes. 1. Open Assets in the sidebar. 2. Click Add asset. 3. Give it a tag (like AHU-L2-01), pick its type and location, and save. That's it — the asset now has its own dossier where issues, documents and test scripts will collect. You can also import many assets at once, or just snap a photo of a nameplate in the chat and let the assistant fill the fields for you. ## Raise your first issue ![Watch: raise an issue](https://app.cx-assistant.com/api/help-assets/tour/issues.mp4) Issues (punch list items, defects, snags) are the heartbeat of commissioning. 1. Open Issues in the sidebar and click Add issue. 2. Describe what's wrong, link the asset, set priority and assignee. Or let the assistant do it: open the chat, attach a photo of the defect and write "raise an issue for this". The assistant reads the photo, drafts the issue, links the asset and assigns it — you just confirm. ## Create your first RFI ![Watch: create an RFI](https://app.cx-assistant.com/api/help-assets/tour/rfis.mp4) When something needs an answer from the design team or another party, raise an RFI (request for information). 1. Open RFIs in the sidebar and click Add RFI. 2. Write the question, attach any drawings or photos, and set who it's directed to. RFIs get their own numbering, status flow and due dates, so nothing waits in an inbox unnoticed — and the assistant can summarize which RFIs are still open whenever you ask. ## Upload documentation and ask about it ![Watch: documents and the assistant](https://app.cx-assistant.com/api/help-assets/tour/documents.mp4) Drop your project files — specs, drawings, O&M manuals, test reports — into Documentation. Drag and drop works, folders keep things tidy, and every document gets a viewer with page thumbnails and markups. The real power: once a document is in, the assistant has read it. Ask "what does the spec say about duct pressure testing?" and you get an answer with citations that jump straight to the page. You can also link documents to assets and track which required documents each asset still owes. ## What can I ask the assistant? ![Watch: asking the assistant](https://app.cx-assistant.com/api/help-assets/tour/chat.mp4) The chat isn't just for questions — the assistant works inside your project with the same permissions you have. Some things to try: - "What are my open issues, ordered by priority?" - "Raise an issue on AHU-L2-01: the belt guard is missing" (attach a photo and it reads it) - "Summarize the RFIs that are still waiting on the design team" - "What does the spec say about pipework insulation?" - "Create a SAT script for the chiller based on the manufacturer's manual" - "Which assets are still missing their test certificates?" The assistant shows its work as it goes — every search, every record it creates — and asks before anything important. If you're ever unsure what a page does, ask the assistant or search this help. ## Get Cx Assistant everywhere Cx Assistant lives in more places than this browser tab: - **iOS and Android apps** — capture photos and raise issues from the field, with the full assistant in your pocket. - **Word add-in** — the assistant writes reports in Word from live project data. - **Excel add-in** — build dashboards and issue lists in Excel with the assistant driving the sheet. To find all the download links and install guides in one place: 1. Click your avatar at the bottom of the sidebar. 2. Choose **Get the apps**. The page also shows an Apple Watch card marked "Coming soon", and a **Watch the intro tour** button if you want to see the welcome tour again. Sign in to every app with the same account you use here. The add-ins have their own help module here too — see "Cx Assistant for Word & Excel". --- # Home dashboard Cx Assistant help · platform: web · module: home · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/home ## What is the Home dashboard Home is the landing page of your project. It gives you a read-only overview of how the project is doing: key numbers at the top, charts about assets and issues below, and a setup checklist to help you get the project ready. You reach it by clicking Home in the sidebar, or it opens automatically when you sign in with an active project. Viewing Home requires the home.view permission, which all built-in roles have by default. ## KPI stats at the top of Home The top of Home shows four cards with the project's key numbers (KPIs) at a glance: - Total Assets — all tracked assets in the project. - Total Issues — every issue created in the project. - Open issues — issues still awaiting resolution. - Completion Rate — the average progress of your assets through their status flow, as a percentage. Everyone who can open Home sees these four cards. While a number is loading the card shows a dash. If a card could not load, it offers a retry. ## Charts on the Home dashboard Home shows several read-only charts about your project, in this order: - Issue Velocity — issues created and closed, accumulated over time - Issue Priority Breakdown - Plan vs Actual - Asset Status by Type - Asset Status Distribution - Asset Completion The statuses, types, and priorities shown are the ones defined by your project. Charts reflect live project data. To reload them, click the small refresh icon next to the greeting at the top of Home. ## Open an asset directly from a chart Two charts let you drill down to the assets behind them: Asset Status by Type and Plan vs Actual. 1. Click a bar in Asset Status by Type, or a point in time on the Plan vs Actual chart. 2. A panel opens beside the chart with the list of matching assets. You can copy the list from there. 3. Click an asset in the list. Its asset dialog opens right on top of the dashboard, so you can inspect or update it without leaving Home. What you can change inside the dialog still depends on your normal asset permissions. The issue charts on Home are for reading only — to work on an issue, open the Issues page. ## Project setup checklist New or partly configured projects show a setup checklist card on Home. Each task deep-links to the right place to complete it — for example, "Add your first asset" opens the Assets page with the create dialog already open. The checklist is permission-filtered: you only see tasks you are actually allowed to complete. For example, the create-issue task only appears if you can create issues. ## How to refresh the dashboard 1. Open Home. 2. Find the small refresh icon right next to the greeting at the top of the page. Hovering it shows "Refresh dashboard". 3. Click it. The icon spins while the numbers and charts reload. Use it after you or a teammate made changes elsewhere and you want the numbers to catch up immediately. The icon is hidden while the assistant panel is open — close the panel to see it again. ## Who can see Home and its data - Viewing Home needs the home.view permission (all built-in roles: Project Admin, Project Member, Technician). - The four KPI cards and the charts need nothing extra — everyone who can open Home sees them. - The Progress shortcut button on the Plan vs Actual chart opens the planner's Progress view and only shows if you can read the planner (planner.read). - The setup checklist hides tasks you cannot perform, and the "create issue" call to action needs issues.create. The project owner always sees everything in their project. If something is hidden for you, ask a project admin to adjust your role. ## Home dashboard looks empty or wrong — troubleshooting - A card at the top shows a dash or an error: the number could not load — use the retry on the card, or the refresh icon next to the greeting. - Charts are empty: the project may not have assets or issues yet, or your filters elsewhere don't affect Home — add data first via Assets or Issues. - Numbers look outdated: click the refresh icon next to the greeting at the top of Home to reload the numbers and charts. - You land on a welcome page instead of the dashboard: you have no active project or you are in My Workspace — pick a project in the project picker at the top of the sidebar. - Home is missing from the sidebar: your role does not include home.view — ask a project admin. --- # Invites & joining projects Cx Assistant help · platform: web · module: invites · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/invites ## What are invites Invites are secure links or codes used to add people to a project. Each invite carries a project role and an expiration date, and can be revoked at any time before it is used. Every invite is made for one email address and works once. It comes with both an invite link and an 8-character code, and either one gets the person in: they open the link, or they type the code on the Join project page. There is no shared code for the whole project. ## Who can invite members Creating and managing invites requires the `members.invite` permission — held by Project Admins by default; the project owner can always invite. Project members without that permission cannot create, list or revoke invites, except that whoever sent an invite can always revoke it. The project also needs an active subscription: without one the Invite members button is disabled, and its tooltip tells you a subscription is needed. If you cannot see the Invites page or the Invite members button, ask a project admin to send the invite or to adjust your role. ## How to create targeted invites From the project's Invites page (or the Invite members button on the Project and Members pages): 1. Enter one or more email addresses (press Enter, comma, or space after each). 2. Choose the project role the invited people will get. 3. Set an expiration in days — 7 days unless you change it. In the Invite members dialog this field is under Advanced. 4. Click Create invites (Send invites in the dialog). An invite link and code is generated for each email address, and each person is emailed their link and code automatically. Requires the `members.invite` permission. ## Copy invite link or code On the Invites page, newly created invites appear in the Recently created list. Use the copy icons to copy either the invite code or the full invite link, and share it with the intended recipient. Copy them while you are there: the list only holds the invites you created during this visit, and the code and link cannot be shown again later. The invited person still has both in their invite email. The link opens the invite preview page directly; the code can be redeemed too. Share invites only with the people they are meant for. ## Tracking invites — the Active only switch The Invites page lists all invites for the project with their status: Active, Used, Revoked, or Expired. The "Active only" switch hides everything except invites that can still be used — handy for a quick audit of who can currently join. It is on when you open the page; turn it off to see used, revoked and expired invites too. ## Revoke one invite or all of them - To revoke a single invite, click Revoke next to it. - To revoke every active invite at once, use Revoke all — you can add a reason, which is kept for the record. Revoked invites stop working immediately and cannot be used again. Revoking an invite does not remove people who already joined — manage those on the Members page. ## Accepting an invite Opening an invite link shows a preview with the role you will get, the email address the invite is restricted to (partly hidden) and when it expires. - If you are already signed in, click Accept invite — you join the project and it becomes your active project right away. - If you are not signed in, you are asked to sign in or create an account first. The invite is remembered in that browser and accepted automatically right after you sign in, so you land in the project without hunting for the link again. With a new account, confirm your email first, then sign in in the same browser. You must be signed in with the email address the invite was sent to. It makes no difference whether that address already had an account or not. ## Joining with an 8-character code If someone gave you a join code instead of a link: 1. Open the Join project page — from the project picker choose "Join project", or use the Join-a-project button on the welcome page. 2. Type the 8-character code — one box per character, and the cursor advances automatically as you type. You can also paste the whole code. 3. You join the project and the app switches to it immediately. The code belongs to your invite, so it only works while you are signed in with the email address the invite was sent to. Codes use capital letters and digits and never contain the letters I or O or the digits 0 or 1. If the code is rejected, check for typos and ask the sender whether the invite is still active. After too many failed attempts you are asked to wait before trying again. ## Invite restrictions and errors Common cases when an invite cannot be accepted: - Expired: the invite is past its expiry date. - Revoked: an admin revoked the invite. - Used: the invite was already accepted. - Email mismatch: the invite is restricted to a specific email address; sign in with that account. - Unverified email: confirm your email address before accepting. When you open the link of an invite that is expired, revoked or already used, the page only says the invite was not found or is no longer valid — it does not say which. For an expired, revoked or used invite, ask a project admin for a fresh one. When creating invites, you can be refused because the project has reached the member limit of its plan, or because too many invites were created for the project in one day. ## Invite acceptance troubleshooting If you cannot accept an invite: - Confirm you are signed in with the invited email address (invites can be restricted to one email). - Verify your email if prompted. - If the link says the invite was not found or is no longer valid, it has expired, been revoked or already been used — ask the sender which. - If you are already a project member, just open the project from the project picker. - With a join code, re-check every character for typos. When in doubt, ask a project admin to generate a fresh invite. ## Best practices for inviting - Every invite is tied to one email address, so check the spelling — it must be the address the person signs in with. - Pick the least-powerful role that fits the person's work — you can raise it later on the Members page. - Set a reasonable expiration window and revoke invites that are no longer needed. - Use the Active only switch periodically to audit outstanding invites. - Share links and codes only with the intended recipients. --- # Issues Cx Assistant help · platform: web · module: issues · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/issues ## What is an issue An issue is a trackable problem, task, or question related to your assets, processes, or project work. Issues help your team capture what needs attention, assign it to a person or a group, and move it through a defined status flow until it is resolved. Think of an issue as a single, well-scoped item you can discuss, update, and close when done. ## Issues page overview and layout The Issues page (Issues in the sidebar) is your main hub to view, filter, create, and update issues. You need the issues.read permission to see it. At the top is the New Issue button (needs issues.create — all built-in roles have it). Below is the Issues table: sortable column headers, a filter row directly under the headers, one row per issue, and pagination controls at the bottom. If your project has not configured its issue statuses yet, a hint banner suggests setting defaults. ## Issues table columns Each row represents one issue. The columns are: - Status bar: a small colored bar for a quick visual status. - Id: the issue number for quick reference. - Title: the short name of the issue. - Priority: how urgent or important the issue is (levels defined by your project). - Assignee: the responsible party — this can be a single user OR a group. - Type: the category of the issue (defined by your project). - Status: the current status label in words. - Due date: the date the issue should be closed by, shown in red with an Overdue chip when it has passed and the issue is still open. You can sort by it, but it has no filter box. - Created By: the user who created the issue. - Location: where the issue is, as a path in the project's location tree. - Actions: a delete icon. The delete column only appears if you hold the issues.delete permission (Project Admins by default). ## Filter issues — filters live in the URL and are shareable Use the filter row directly under the column headers to narrow results: by title or Id, type, priority, status, assignee, creator, or location. Filters can be combined. Your filters are stored in the page URL, so they survive a refresh — and you can copy the address bar and send the link to a teammate to share the exact same filtered view. ## Sort, resize, and paginate the issues list Click a column header to sort by that column; click again to switch between ascending and descending. Drag the right edge of a column header to resize it. Use the pagination controls at the bottom of the table to move between pages or change how many rows are shown at once. If you cannot find an issue, check your filters and pagination first. ## How to create an issue Step-by-step: 1. Click New Issue (needs issues.create — all built-in roles have it). 2. Enter a clear Title (required), for example "UPS inverter overtemperature". 3. Add a Description with context, symptoms, or expected behavior. 4. Choose a Priority and a Type (both lists are defined by your project). 5. Assign the issue to a user or a group (optional but recommended). 6. Link Assets if the issue is tied to specific equipment. 7. Pick a Location if you want to record where the issue is (optional). 8. Click Create. After creation, the issue appears in the list and can be opened for further updates. Tip: links that end in ?create=1 (for example from the Home setup checklist) open this dialog automatically. ## Open and edit an issue Click anywhere on an issue's row to open the issue dialog. There you can edit the title and description inline, change priority, type, assignee, due date, location, and status, manage linked assets, attachments, and linked planner activities, and add comments. Changes save field-by-field, so you can update one item at a time; every change is recorded in the issue history. ## Edit title, description, priority, and type In the issue dialog: - Title: keep it short and specific so issues are easy to scan. - Description: add steps, impact, context, or links. - Priority: adjust urgency as work progresses — raise it if the issue blocks work, lower it when it is no longer urgent. - Type: reclassify the issue if new information appears; this keeps reporting accurate. Priority and type options are defined by your project. If an option you need is missing, ask a project admin to update the project's configuration sets. ## Assign an issue to a user or a group Use the Assigned To field to pick who owns the issue. You can assign either a single user or an entire group (groups are defined by project admins on the project's Groups page). Assigning to a group means every member of that group is treated as responsible — any group member can edit the issue and change its status, and group members are notified. When you change the assignee, the update is recorded in the issue history. ## Due dates and the Overdue chip Every issue can have a due date — the date by which it should be fixed and closed. Set it when you create the issue, or change or clear it later from the Due date field in the issue dialog. Every change is recorded in the issue history. When the due date passes and the issue is still open, the list shows the date in red with an Overdue chip, and the issue dialog shows the same chip next to the date. Sort the list by the Due date column to chase the most urgent issues first. Closed issues are never shown as overdue. The assignee (or the creator, when the issue is unassigned) receives an Issue overdue notification the day the issue slips — once per slip, so moving the date or changing the status re-arms it. You can tune the channels for it in Settings → Notifications. The assistant can set or clear due dates too: ask it to "set issue 45 due next Friday", or to list overdue issues. ## Set where an issue is — the Location field Every issue can have a Location: a place from the project's location tree (site, building, floor, room and so on). It tells the team where to go, and lets you filter and sort issues by place. When you create an issue: 1. Click New Issue and fill in the title and the other fields. 2. Click the Location field ("Select location (optional)"). 3. Pick a place from the tree, then click Create. On an existing issue: 1. Click the issue's row to open the issue dialog. 2. Click the Location field and pick a place, or pick — No location to clear it. 3. The change saves at once and is recorded in the issue history. Good to know: - The Location column in the Issues table shows the full path. You can sort by it and filter on it. - The location is separate from linked assets. Linking an asset does not fill in the issue's location, so set it yourself if you want it. - The places come from the project's location tree. If a place is missing, ask someone who can edit locations to add it. A location that still has issues assigned to it cannot be deleted. - Changing the location follows the same rules as editing the issue. Coming from the Map: when you select a location or an asset on the Map and click View all issues, the Issues page opens showing only that pin's issues. A chip above the table says so, for example "Issues located at Main Building" or "Issues linked to UPS-001". Click the x on the chip to show all issues again. The narrowed view survives a page refresh. ## Update issue status and allowed transitions Use the Status control in the issue dialog to move the issue through your project's status flow (for example Open → In Progress → Closed, though your project can use different names). The project's transition policy decides which statuses can follow the current one, so some options may be disabled from where you are now. Changing status needs issues.status.update (Project Admins and Members by default) — or you qualify automatically if you created the issue, are its assignee, or belong to its assigned group. When you save a new status, the change is added to the history timeline. ## Who can edit an issue — permissions and bypass rules You can edit an issue and change its status if any of these is true: - You created the issue. - You are the issue's assignee. - You belong to the group the issue is assigned to. - You hold the issues.update permission (for edits) or issues.status.update (for status changes). In other words, creators, assignees, and assigned-group members can always work on their own issues, even without the permissions. The project owner can always do everything. If a control is disabled for you and none of the above applies, ask a project admin to adjust your role. ## Link assets to an issue Use Linked Assets to connect related assets to the issue, so everyone can see which equipment is affected. You can select multiple assets, and remove links later — additions and removals are recorded in the issue history. Linked assets also make the issue visible from each asset's side. ## Issue attachments The Attachments section of the issue dialog lets you attach files to the issue itself. You can upload new files or pick existing documents already stored in the project's Documentation. Use attachments for photos of the problem, reports, or any evidence that belongs with the issue. You can also attach images or PDFs directly to individual comments when posting them. ## Linked planner activities on an issue The issue dialog includes a Linked planner activities card listing schedule activities connected to this issue. This keeps the plan and the problem in one place — click an activity to jump to it in the Planner. Seeing the list needs planner.read; adding or changing links needs planner.update. ## Add comments to an issue At the bottom of the issue dialog you can add comments to keep discussion and evidence together. How to add a comment: 1. Write your message in the comment box. 2. Optionally attach images or PDF files. 3. Click Comment. Commenting needs the issues.comment permission — all built-in roles (Project Admin, Member, Technician) have it by default. Comments appear in the issue history; a comment needs text or at least one attachment to post. ## Issue history timeline and filters The History section shows a timeline of everything that happened to the issue: status updates, field edits, assignee and group changes, linked-asset changes, comments, and system entries. Use the filter dropdown to focus on one category: - All - Field changes - Comments - Status changes - User (assignee) changes - Group changes - Linked assets - System This helps you quickly understand what changed and when. ## Issue deep links from notifications and emails Notifications and emails about issues (for example "issue assigned" or "new comment") link straight to the issue: the link opens the Issues page with the right issue dialog already open. You can produce the same effect yourself — a link to the Issues page with ?issue= at the end opens that issue directly. This makes it easy to point a teammate at one specific issue. ## Export the issues list to Excel You can download the Issues table as an Excel file (.xlsx) — handy for a punch list you need to send to someone. 1. On the Issues page, set the filters and sorting you want. The export matches what the table shows, including a view narrowed from the Map. 2. Click the three-dot Page actions button next to the Issues title and choose Export…. 3. The Export table dialog opens. If you have filters on, it reminds you that the active filters and sorting apply to the export. 4. Optional: switch on Only visible to me to keep the file private. 5. Click Export. The button shows that the file is being generated. When it is ready, the file opens in a new browser tab and a message confirms the export. What is in the file: one row per issue with its Id, title, priority, assignee, type, status, location, due date, who created it and when, and the description. All matching issues are exported, not just the current page, up to 5,000 rows. Where the file goes: without the switch, the message reads "Export ready — saved to the project's documents". With Only visible to me on, it reads "Export ready — saved privately for you" and only you can see the saved file. Anyone who can see the Issues page (`issues.read`) can export — no extra permission is needed. ## Delete an issue Click the delete icon in the Actions column to remove an issue. You will be asked to confirm because deletion cannot be undone. Deleting needs the issues.delete permission — Project Admins by default. If you do not see a delete column at all, you do not hold this permission. ## Issues troubleshooting and FAQ Q: Why can't I change the status? A: Either the transition policy does not allow that status from the current one, or you lack issues.status.update and are not the creator, assignee, or an assigned-group member. Q: Why can't I edit the issue? A: Editing needs issues.update — unless you created it, are assigned to it, or belong to its assigned group. Q: Why don't I see a Type or Priority option I need? A: Those lists are defined per project. Ask a project admin to update them in Project Settings. Q: Why did my issue disappear from the list? A: Check the filter row and pagination first — remember filters persist in the URL. If you came from the Map, a chip above the table may be narrowing the list to one location or asset — click the x on it to show all issues. The issue may also have been deleted. Q: Can I attach files? A: Yes — to the issue itself via the Attachments section (upload or pick existing documents), and images/PDFs directly on comments. --- # Layouts Cx Assistant help · platform: web · module: layouts · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/layouts ## What are layouts A layout is an interactive 3D floor plan of your site: draw the walls over a PDF drawing, place your equipment, draw the cable trays and pipes that connect it, and see the live status of every linked asset right on the plan. Open issues appear pinned exactly where they are in the field. Open Layouts from the sidebar. Viewing requires the layouts.read permission. Every layout has a number (LY-1, LY-2, …) shown on its card and in the editor, so you can refer to it in chat and in reports. You can draw layouts yourself in the editor, or ask the Layout Builder Assistant to draw them for you — see the Build layouts with AI section. ## The layouts list The Layouts page shows every layout of the project as a card: its LY-number, name and description, chips with what it contains (walls, objects, rooms, issue pins and — once there are any — routes), and when it was last updated. Click a card to open it in the editor. The New layout button (requires layouts.create) asks for a name, an optional description and, when the project has buildings among its locations, the building this plan belongs to — anchoring a plan to a building lets the Maps module offer it from that building's marker. The card menu offers Rename, Duplicate (a full copy of the drawing, requires layouts.create) and Delete (requires layouts.delete). Deleting a layout never touches the assets or issues it was linked to. ## The editor: view mode and edit mode A layout opens in the full-screen editor. The top bar shows the layout name and LY-number, the camera buttons and — if you have the layouts.update permission — a View / Edit switch on the right. - View mode is for walking the model: orbit with the left mouse button, zoom with the wheel or middle button, pan with the right button. Equipment linked to assets shows its status, issue pins show theirs, and hovering or clicking opens details (see the View mode section). - Edit mode adds the drawing tools to the top bar, an Undo/Redo pair and a Save button. Nothing is stored until you Save (Ctrl+S) — an orange dot next to the name means there are unsaved changes, and the browser warns before you leave with unsaved work. A brand-new, empty layout opens straight in edit mode for people who can draw. Switching mode always returns to the Select tool and clears the selection. ## Drawing walls, rooms, doors and windows The plan is drawn in meters on a grid; while you draw, a readout shows the current segment length and the running total. - Walls: pick the Draw walls tool and click corner after corner on the floor. Double-click or press Enter to finish, Esc to cancel, and hold Shift to lock the segment to 45° angles. Points snap to the grid and to existing wall ends. Each wall is extruded to the thickness and height set in the Drawing defaults panel (0.2 m and 3 m unless you change them); select a wall later to change its own thickness and height. - Rooms: pick Draw rooms and outline the area; double-click or Enter closes the polygon. Rooms are flat colored zones with a name — select one to rename it, pick a color, and link it to a project location (building, floor or room) so the plan and the locations tree stay in step. - Doors and windows: pick Place doors or Place windows, hover over a wall and click — the opening snaps onto that wall. Once placed, drag it to slide it along the wall, and use the properties panel to change its type (Door, Double door, Window or plain Wall opening), width, height, sill height, position along the wall and — for doors — flip the swing side. Deleting a wall removes the openings on it. ## Placing equipment from the library Pick the Place equipment tool and the Equipment palette opens on the right: a search box on top and the library grouped by family (transformers, switchgear, racks, pumps, tanks and so on), each item with a small picture of its 3D model and its size in meters (width × depth × height). Pick an item and a live 3D preview of it turns slowly at the top of the palette — drag the preview to orbit it and look at the item from any side. Then move the mouse over the floor to see its ghost, press R to rotate the ghost by 90° (Shift+R the other way), and click to place it — you can keep clicking to place several. If nothing in the library fits, place the generic box and set its real size. Back in the Select tool, drag equipment to move it and select it to edit its properties: label, rotation, width, depth and height, and the Linked asset. Linking an object to a project asset is what makes it come alive in view mode — the asset's status is shown on the plan and clicking the object opens the asset. Ctrl+D duplicates the selected object next to itself (the copy is not linked to any asset). ## Furniture and fit-out items The equipment library also holds 45 furniture and fit-out items, so you can furnish offices, welfare areas, canteens and accommodation on the same plan as your equipment. They sit in the same Equipment palette, under these family headings: - Desk: office desk, four-seat bench desk, reception counter. - Table: meeting, round, dining and coffee tables. - Chair: office, dining and visitor chairs, a bar stool and a bench. - Sofa: two-seat and three-seat sofas and an armchair. - Bed: single, double and king. - Storage: wardrobe, bookshelf, filing cabinet, nightstand, sideboard and lockers. - Kitchen: base units, sink unit, cooker, kitchen island and wall units. - Appliance: fridge freezer, dishwasher, washing machine, vending machine, water cooler and multifunction printer. - Sanitary: toilet, washbasin, vanity unit, urinal, shower, bathtub and toilet cubicle. - Plant and Stand: a potted plant, a display on a stand and a mobile whiteboard. To place one: 1. In edit mode, pick the Place equipment tool. 2. Type in the Search equipment box — for example "desk", "sofa" or "toilet" — or scroll to the family. 3. Click the item. Its live 3D preview appears at the top of the palette; drag it to look around the item. 4. Move over the floor, press R to turn the ghost by 90°, and click to place. Keep clicking to place more. Furniture behaves like any other library item: drag to move it, and select it to change its label, rotation and size. The Layout Builder Assistant searches the same library, so you can ask it to furnish a room for you. ## Select several things: align, distribute, mirror, array, group In edit mode, with the Select and move tool, you can work on many elements at once. Build the selection: - Click an element to select it. Shift+click adds to the selection. - Shift+drag on empty floor draws a selection box. - Ctrl+A selects everything on the plan. With two or more elements selected, the panel on the right becomes the Selection panel. It shows how many elements are selected and of what kind, and offers: - Align: Align left edges, Center horizontally, Align right edges, Align top edges, Center vertically, Align bottom edges. Align works on equipment and issue pins and needs at least two of them. - Distribute horizontally / Distribute vertically: equal spacing between the two outermost items. Needs at least three. - Mirror left–right and Mirror up–down, plus Rotate 90° clockwise and counter-clockwise. A set turns around its own centre. - Linear array: type the number of Copies and the Pitch x (m) and Pitch y (m) — the spacing between copies — then click Create copies. The original stays where it is. Handy for a row of racks or desks. - Grouping: type an optional Group name and click Group. Grouped elements select and move together; Alt+click picks one on its own. Ungroup dissolves the group. - Delete selection removes everything selected. Copy and move: - Ctrl+C copies the selection and Ctrl+V pastes it; each paste lands a little further away so copies do not stack. - Ctrl+D duplicates the selection right next to itself. - Drag any selected element to move the whole set, or nudge it with the arrow keys (0.1 m, Shift for 1 m). R rotates the set. - Copies are never linked to an asset — link each copy yourself. Issue pins are not copied. While you drag a piece of equipment, guide lines appear when its centre or edges line up with another item. Every action is one Undo step (Ctrl+Z), and nothing is stored until you Save. ## Substations: outdoor equipment, fences and elevation The library also holds outdoor substation equipment for 11, 33, 66, 132, 220 and 400 kV: power transformers and autotransformers, shunt reactors, live-tank and dead-tank circuit breakers, disconnectors (centre break, double side break, vertical break, pantograph, with or without earthing switch), earthing switches, current and voltage transformers, CVTs, surge arresters, post insulators and bus supports, gantries, tension insulator strings, capacitor banks, line traps, cable sealing ends, GIS bays, relay houses and control buildings, kiosks, lighting masts and transformer bunds. Search the palette by name or voltage ("132 kV breaker"). Every item carries its connection points: bushing tips, breaker T1/T2, CT P1/P2, gantry attachment points, earth — the assistant routes conductors onto them. Equipment can sit above grade: the Elevation field in the properties panel raises an object's base (a transformer on its bund, a line trap on top of a CVT), and its connection points rise with it. Some library items have geometry variants — a Variant field appears in the properties panel when the selected item offers them. Power transformers and shunt reactors mount their conservator across the phase-A end of the tank by default, above the radiators and clear of the HV bushings; the variants put it across the phase-C end or along the HV (rear) side. Variants change only the look; connection points stay where they are. A wall can be a fence: select the wall and change its Type to Fence. Fences render as chain-link panels between posts (dashed on the assistant's plan) with the perimeter defaults of 2.4 m high and 5 cm thick; a door on a fence is a gate. ## Routes: cable trays, busbars, pipes, ducts and conduit Routes are the services that connect your equipment. Pick the Draw routes tool and the Routes panel lists the systems — Cable tray, Busbar, Pipe, Duct and Conduit — each with its default profile and elevation. Choose one, adjust the width/height (or diameter), elevation above the floor and, for flat profiles, the orientation (Flat or On edge), then click the run's corners on the plan; double-click or Enter finishes, Shift locks 45° angles. A route is drawn as a centreline, the way a single-line diagram is drawn: bends follow from the corners, a change of height is a riser, and runs pass through walls freely. Select a route to edit its label, run color (including the red/blue A/B-feed convention for busbars), width, height, elevation and orientation. Branches, fittings (tap-offs, expansion joints, valves…) and connections landing exactly on an equipment terminal are added by the Layout Builder Assistant — the properties panel shows how many points and fittings a route has. ## Substation conductors: bus, droppers, jumpers, cables, earth and trenches The Routes panel also holds the substation conductor systems: Rigid bus (tubular aluminium on post insulators), Strung bus (flexible conductor hanging between gantries), Dropper (bus down to an equipment terminal), Jumper (terminal to terminal), HV cable (buried, rising into sealing ends), Earth conductor and Cable trench (a channel recessed at grade). Their default heights follow the voltage class of the equipment in the yard, and each has a Phase field — A, B, C, N or E — that colours the run red, yellow, blue, slate or green; a strung bus also has a Sag field and hangs by that much between its points. While the route tool is armed, every connection point of the placed equipment (bushing tips, breaker T1/T2, CT P1/P2, gantry attachment points, earth) shows as a small phase-coloured dot; move the cursor near one and the point magnets onto it at the terminal's exact height, so a dropper ends precisely on the bushing. Select a conductor to change its phase, sag, diameter or elevation in the properties panel. A cable trench drawn by the assistant is always flat at its depth and runs in straight, axis-aligned legs with L corners (a diagonal you give it is squared), routed beside equipment rather than under a pedestal, a column or a bund wall. The Layout Builder Assistant draws a three-phase bus in one step, and its connectivity check lists open terminals, conductors ending in the air, phase mismatches and spacing below the air clearance for the voltage class — as warnings you decide on, never as blocks. Its clash check adds the physical view: overlapping footprints, a conductor running through a transformer tank or a kiosk, three phases converging on one point, a trench cutting under a post-insulator pedestal or a gantry leg. ## Pinning issues on the plan In edit mode, pick the Pin an issue tool, click the spot on the floor, and choose the issue from the picker (search by title). The pin shows the issue number and title; select it to open the issue or delete the pin. Pins are saved with the rest of the drawing when you Save. In view mode there is a faster path: click Pin issue in the top bar, pick the issue first, then click where it is on the plan — the pin is saved immediately, no Save needed. That button is disabled while the editor holds unsaved edits, so save them first. Esc cancels an armed pin. ## Tracing a PDF drawing: the underlay and its scale Pick the PDF underlay tool to upload a floor plan PDF (or replace the current one). The drawing appears under the grid so you can trace walls over it. The panel lets you show or hide it, set its opacity and page, rotate it by 90°, and remove it; drag the drawing on the canvas to reposition it. To make the drawing the right size, click Set scale, then click the two ends of a known distance on the drawing (a dimension line, a door, a grid spacing). A dialog shows the measured length and asks for the real distance in meters — type it, Apply, and the whole drawing is rescaled to match. Do this before tracing so your walls come out in real meters. ## Keyboard shortcuts - Ctrl+S: save. Ctrl+Z / Ctrl+Y: undo / redo. - Ctrl+A: select everything on the plan. - Shift+click: add an element to the selection. Shift+drag on empty floor: draw a selection box. - Alt+click: pick one element of a group on its own. - Ctrl+C / Ctrl+V: copy and paste the selection. - Ctrl+D: duplicate the selection next to itself. - R / Shift+R: rotate the selection (or the equipment ghost you are about to place) by 90° clockwise / counter-clockwise. - Arrow keys: nudge the selection by 0.1 m; hold Shift for 1 m. - Delete (or Backspace): delete the selection. - F: fit the whole layout in view (works in both modes). - Esc: cancel the drawing in progress or an armed pin. - Enter or double-click: finish a wall, room or route polyline. - Shift while drawing: lock segments to 45° angles. Shortcuts are ignored while you type in a field. The Shortcuts panel on the right of the editor (shown in edit mode when nothing is selected) lists them too. ## View mode: live status, hover cards and layers In view mode the plan becomes a live picture of the site: - Equipment linked to an asset carries a floating status marker in the project's status colors, with the asset ID; issue pins carry the issue's status color. Rest the pointer on either and a hover card shows a summary — the asset's type, status and linked issues, or the issue's status and assignee — with an Open button; clicking the marker or pin opens the asset or the issue in place. - The Layers menu (the layers icon in the top bar) toggles what is drawn: Asset status markers, Asset ID labels, Issue pins, Room areas, Routes and X-ray walls (see-through walls). Your choices are remembered on this browser. - The camera buttons work in both modes: Top view, 3D view, Fit to view (F), a dollhouse cut that lowers the walls so you can see inside, and a slow auto-rotate spin — also remembered. - Pin issue drops a new issue pin without entering edit mode (see the pins section). ## Build layouts with AI You don't have to draw layouts by hand — the Commissioning Assistant can do it with you in chat. Start a conversation and describe what you want (drawing layouts needs the layouts permission in your role, granted to project admins by default): - Describe a plan ("a 20 × 12 m data hall with two rows of ten racks facing each other, a UPS room on the east side") and it draws the walls, doors, rooms and equipment. - Attach or name a PDF drawing and it traces it: it reads the sheet, works out the scale from a labelled dimension, draws the shell and internal walls, and can load that page as the underlay so you can compare. - It searches the same equipment library you see in the palette, places items with real footprints, links them to your assets and rooms to your locations. - It draws routes between equipment — cable trays, busbars, pipes — and can land them exactly on an equipment terminal (a transformer's LV box, a UPS roof), add branches and fittings, and pin issues. The assistant looks at a rendered plan of its own work after each step and fixes what looks wrong — it can also render an elevation (side view) and the real 3D view of the editor from any corner of the plan, and it runs two numeric checks before calling a bay finished: connectivity (open terminals, dangling conductors, phase mismatches, clearances) and clashes (overlapping equipment, routes through equipment, routes crossing, trenches under columns). Long builds such as a whole substation are allowed to run for well over an hour. Its changes go through the same permission checks as the editor. When it finishes it posts a layout card in the chat — click Open layout to jump to the editor. ## Live updates: the assistant, other tabs and the "Updated elsewhere" chip The editor and the layouts list refresh live. If the assistant (or a colleague in another tab) changes the layout you have open and you have no unsaved edits, the new geometry simply appears. If you DO have unsaved edits, your work is never overwritten: an "Updated elsewhere" chip appears next to the layout name instead. Click it to load the latest version — your unsaved changes are discarded — or Save first if you want to keep yours; the last save wins. ## Who can view and edit layouts (permissions) - layouts.read — open the Layouts page and view layouts. - layouts.create — create and duplicate layouts. - layouts.update — switch to edit mode, draw, and pin issues from view mode. - layouts.delete — delete layouts. - Drawing layouts in chat has its own permission (agents.layoutbuilder, "Layouts skill in the assistant"), granted to project admins by default: without it the Commissioning Assistant does not draw. A project admin can also switch the whole Layouts module off for a project in the project settings; the page and the assistant's tools then say the module is disabled. ## Layouts troubleshooting - Layouts missing from the sidebar: your role lacks layouts.read, or a project admin switched the module off for this project. - No View / Edit switch or no Save button: you need the layouts.update permission. - Equipment shows no status in view mode: the object is not linked to an asset — select it in edit mode and pick the Linked asset. Also check the Layers menu: Asset status markers may be switched off. - Only a generic box is offered in the palette: the equipment library could not be loaded — reload the page. - The PDF looks the wrong size: use Set scale in the underlay panel and type the real distance between two points. - Walls end up inside out or the door opens the wrong way: select the door and use Flip swing side; wall thickness and height can be corrected per wall. - The Pin issue button is greyed out in view mode: save (or discard) your unsaved edits first. - An "Updated elsewhere" chip appeared: the layout changed in another tab or through the assistant — click it to load the latest version, or Save to keep yours. - Save fails: the drawing is checked before it is stored — the error names the element; undo the last change and try again. --- # Sign in Cx Assistant help · platform: web · module: login · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/login ## How to sign in Step-by-step: 1. Enter your email address. 2. Enter your password. 3. Click Sign in. If your credentials are correct, you are signed in and taken to your dashboard (or back to an invite you were following). If your account has two-factor authentication enabled, a verification step appears first — enter the code from your authenticator app or email to finish signing in. ## Two-factor verification at sign-in If two-factor authentication is enabled on your account, entering your password takes you to a verification card: - If you use an authenticator app (TOTP), open it and enter the 6-digit code shown for this account. - If you use email codes (Email OTP), a code is sent to your email — enter it here. Use the Resend button if it did not arrive. - If you have both methods enabled, tabs let you switch between Authenticator and Email code. Click Cancel to go back to the password form. Two-factor methods are managed in Settings, on the Security tab, after you sign in. ## Signing in with a backup code If you cannot use your authenticator app (lost or new phone), use one of your backup codes: 1. Sign in with email and password as usual. 2. On the two-factor step, click "Use a backup code". 3. Enter one of the backup codes you saved when you set up two-factor authentication. Each backup code works only once. After signing in, go to Settings, Security tab to regenerate a fresh set of codes and, if needed, reconfigure your authenticator app. If you have no backup codes left and no access to your methods, contact support. ## Remember email Enable Remember email to store your email address on this device, so it is pre-filled next time you sign in. Only your email is remembered — never your password. You can turn it off at any time; use it only on trusted personal devices. ## Forgot password Click "Forgot your password?" on the sign-in screen to open the reset dialog. Enter your email address and submit — a reset link is sent to your inbox. Check your spam folder if you do not receive the email. Then follow the link to the reset page to set a new password. ## Setting a new password from a reset link The link in the reset email opens the reset-password page: 1. Enter your new password. 2. Confirm it in the second field. 3. Submit — on success you are taken back to the sign-in screen to sign in with the new password. For your security, resetting your password signs you out of ALL sessions on all devices, so any device that was signed in with the old password must sign in again. If the link has expired, request a new one via "Forgot your password?" on the sign-in screen. ## Show or hide password Use the eye icon in the password field to show or hide your password as you type. Helpful for catching typos on long passwords — just make sure nobody is looking over your shoulder. ## Caps Lock warning If Caps Lock is on while you type in the password field, a warning appears under it. Passwords are case-sensitive, so turn off Caps Lock to avoid failed sign-ins. ## Confirming your email — page states Opening the confirmation link from your welcome email verifies your address automatically. The page then shows one of these states: - Confirmed: your email is verified — click "Go to sign in" and log in. - Already confirmed: this address was verified earlier; just sign in. - Expired: the link is too old — use the resend button to get a fresh confirmation email. - Invalid: the link is broken or was already replaced — request a new confirmation email. If you try to sign in before confirming, you are redirected to this page with the option to resend the email. ## Common sign-in errors - Invalid email or password: check your credentials and try again; watch for Caps Lock. - Email not confirmed: complete email verification first — you are redirected to the confirmation page where you can resend the email. - Two-factor code rejected: codes expire quickly — get a fresh code from your app or resend the email code; check your phone's clock is set automatically. - "Too many failed attempts. Try again in 15 minutes.": five wrong codes in a row lock two-factor verification for 15 minutes. This applies to authenticator codes and to email codes, and the message counts down the seconds left. With an authenticator app, wait for the lock to end, then enter a fresh code — a correct code resets the count. With email codes you see "Wrong code. N attempts left." after each miss and "Too many failed attempts. Request a new code." after the fifth; use Resend to get a new code, which starts a fresh set of attempts. Backup codes are not part of this lock: if your authenticator is locked, click "Use a backup code" and sign in with one. - "Wait …s before requesting another code." or "Too many code requests. Try again later.": email codes can only be re-sent after a short wait, and only a few times per hour. - Server unavailable: check your network connection and try again. ## Invite redirect If you followed a project invite link and were asked to sign in, you are taken back to that invite right after signing in so you can accept it — no need to find the link again. ## Choosing light or dark mode before signing in The sign-in screen has a colour-mode selector, so you can switch between light and dark appearance even before you sign in. After signing in, the theme toggle lives in the header on every page. ## Security tips - Enable two-factor authentication in Settings, Security tab — it protects your account even if your password leaks. - Save your backup codes somewhere safe when you set it up. - Do not share your password, and avoid signing in on public or shared devices. - Use Remember email only on trusted devices, and sign out when finished on shared computers. - Review your active sessions in Settings, Security tab, and revoke any you do not recognise. --- # Map Cx Assistant help · platform: web · module: maps · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/maps ## What is the Map and how to open it The Map shows your project on a live map: every site and building that has an address or coordinates, and every asset that has its own position or route. Pins take the colour of the asset status, so you can read the state of the whole project at a glance. Hover a pin for a summary, click it for the details. To open it, click Map in the sidebar (it carries a Beta chip). You can also press Ctrl+K (⌘K on a Mac) and type "map". The Map entry only appears when two things are true: the Map module is switched on for the project, and your role has the `maps.read` permission. See the permissions section if you cannot find it. The map fills the whole page. The toolbar floats at the top left, the details panel opens on the right, the basemap switch and the Legend sit at the bottom left, and the zoom buttons sit at the bottom right. ## What the pins, lines and colours mean - A rounded square pin is a site or a building. Its colour is the most common status among the assets inside it. Its name is always shown under the pin. - A round pin is an asset with its own position (a turbine, a pole, a tower). Its colour is the asset's status, and the icon inside comes from the asset type. Asset IDs appear under the pins once you zoom in close. - A coloured line is an asset with a route (an overhead line, a cable route, a pipeline). It has a round pin at its midpoint so you can always click it. - A red ring with a number means open issues. For an asset, the number counts open issues linked to it and to its sub-assets. For a site or building, it counts open issues linked to the assets inside it. - A donut with a number is a group of nearby pins. The donut's colours show the mix of pins inside. Click it to zoom in. - A grey-blue pin has no status information. Equipment inside a building does not need its own pin. It is counted in the building's pin instead. Open the Legend at the bottom left for a reminder: Site / building, Asset, Line / route, the colours in use, and Open issues. The Legend is hidden on small screens. ## How to move around: basemap, zoom, Fit all and pin grouping - Drag the map to pan. Use the mouse wheel or the + and − buttons at the bottom right to zoom. - Fit all (the frame icon at the bottom right) zooms out to show every pin that matches your filters. - The group icon above it turns pin grouping on or off. When grouping is on, nearby pins merge into a donut until you zoom in. When it is off, every pin is drawn on its own. - At the bottom left, switch the basemap between Streets and Satellite. The switch only appears when the server offers both. Your basemap, your grouping choice and whether the Legend is open are remembered in this browser. When you open the map, it frames all your pins. If you arrive from a Show on map link, it flies straight to that pin instead. ## How to search and filter the map Everything is in the toolbar at the top left. - Search: type in the box labelled "Search sites, buildings & assets…" and pick a result. The map flies to that pin and opens its details. Search looks only at pins that match the current filters. - Status: show only one asset status. A site or building stays visible when at least one asset inside it has that status. An asset also stays visible when one of its sub-assets has it. - Type: the same, by asset type. - Sites & buildings and Assets: two chips that show or hide each kind of pin. At least one always stays on. - With open issues: show only the pins that have open issues. Your filters, the Colour by choice and the selected pin are kept in the page address. Copy the link from the browser to share exactly the view you are looking at. ## How to change what the colours mean (Colour by) Use the Colour by menu in the toolbar: - Status (the default): pins and lines use your project's asset status colours. A site or building takes the most common status of its assets. - Asset type: each asset type gets its own colour. Everyone in the project sees the same colour for the same type. A site or building takes the most common type inside it. - Open issues: red for pins with open issues, green for pins with none. The Legend follows your choice. The red ring with the issue count is shown in every mode. ## The details panel: what a pin tells you Hover a pin to see a small summary card. Click the pin to open the details panel on the right. Press Esc or the ✕ to close it. For a site or building the panel shows: - Its name, code and place in the locations tree, and its Address. - Assets by status: how many assets are inside, split by status. - Asset types: a chip per type with its count. - Floor plans: layouts anchored to this building. Click one to open it (you need access to Layouts). - Buttons: Add building (sites only), Add asset, Create issue and View assets, which opens the Assets page. For an asset the panel shows: - Its ID, type and Status. Click the ID, press Open asset, or double-click the pin to open the full asset dialog. - Part of (the parent asset, clickable) and Location. - Category, model, vendor and description when they are filled in. - Sub-assets: how many, split by status and type. - For a line: Length and Chainage. Both kinds end with a folded Coordinates section (Route for a line). Open it to see the numbers and copy them with Copy coordinates or Copy route. ## How to see issues and create an issue from the map When a pin has open issues, the details panel shows a red banner with the count. If your role has `issues.read`, an Open issues list follows with the most recently updated issues for that pin (up to 8). Click a row to open the issue without leaving the map. When there are more issues than the list shows, click View all issues. The Issues page opens already filtered to that asset or that site or building. To create an issue from the map: 1. Click the pin. 2. Click Create issue in the panel (needs `issues.create`). 3. Fill in the issue as usual. From an asset pin, the asset is already linked and its location is filled in. From a site or building pin, the location is filled in. 4. Save. The pin's issue count updates. ## How to add a site or a building from the map You need to be the project owner, or have `projects.locations.edit` or `projects.settings.manage`. 1. Click Add in the toolbar and choose Site or Building. 2. Click on the map where it is. A pin drops there. Press Esc to cancel. 3. Drag the pin to adjust the position, or search an address in the panel on the right. Picking an address moves the pin. 4. Type a Name. Code is optional. For a building, you can choose the site it belongs to under Inside site. 5. The address is looked up from the spot you clicked. If none is found, you can type one. 6. Click Create. The new site or building appears on the map and in the project's Locations right away. To add a building inside an existing site, click the site's pin and then Add building. The site is already selected for you. ## How to put an asset on the map 1. Click Add in the toolbar and choose Asset. 2. In the panel, under Which asset?, search for an asset that already exists. You can search by asset ID, type or location. Assets that still have no position come first. This list needs `assets.update`. 3. Click on the map where the asset is. Drag the pin to adjust it. 4. Click Place here. The asset gets that position and becomes a pin. If the asset is already on the map (it shows an On the map chip), placing it moves it to the new spot. If the asset does not exist yet, skip the search, drop the pin and click Add asset details. The usual Create Asset dialog opens with the position already filled in. You complete its ID, type and category there. This needs `assets.create`. You can also set a position from the asset itself: open the asset, find the Map position card and click Set position or route. From there, Show on map jumps to the pin. ## How to add assets to a site or building from its pin 1. Click the site or building pin. 2. Click Add asset in the panel. 3. Search for an existing asset and click Add here. The asset moves into that location. Assets that are already there are marked Already here. This needs `assets.update`. 4. If the asset does not exist yet, click New asset instead. The Create Asset dialog opens with the location filled in. This needs `assets.create`. An asset added this way does not get a pin of its own. It is counted in the site or building pin. An asset that already had its own pin keeps it where it is. ## How to move a pin 1. Switch on Move pins in the toolbar. The switch is only shown when your role has `assets.update`. 2. Drag an asset pin to its new spot and let go. 3. The new position is saved at once, and a message confirms it. If the save fails, the pin jumps back to where it was. 4. Switch Move pins off when you are done, so you do not move a pin by accident. Only asset pins can be dragged. Lines are not dragged: open the asset and edit its route in the Map position card. Sites and buildings are moved by editing their address or coordinates in the project's Locations. ## Lines and routes: assets that span a distance An asset can have a route instead of a single point: an overhead line, a cable route, a pipeline. The map draws it as a line in the asset's colour, with a round pin at its midpoint. - Click the line or its pin to select it. The map frames the whole route. - The panel shows its Length. Under Route you see how many points it has, its Start and End, and Copy route. - An asset that has both a position and a route is drawn as the line only. - A route can have up to 2,000 points. To draw or edit a route, open the asset, go to the Map position card, click Set position or route and use the Line route fields. You can also bring routes in from a KML or KMZ file. ## How to import a KML or KMZ file Use this to bring an alignment or a site survey from Google Earth or a CAD export onto the map. You need `assets.create`. 1. Click Add in the toolbar, then Import KML. 2. In the Import KML / KMZ panel, click Choose KML / KMZ file and pick a .kml or .kmz file. 3. The file is read and drawn on the map as a dashed purple preview. Nothing is saved yet. 4. Set the Defaults: Type for lines, Type for points, Type for folders and Category. They are used wherever the file does not name a type or category. For folders you can keep "Group only — do not create folder assets". 5. Check the summary: the number of rows, lines, points and folders, any Notes, and the Rows with problems (skipped) list, which says why each row cannot be imported. 6. Click Import N assets. A message tells you how many assets were created and how many were skipped. Click Cancel or the ✕ at any time to leave without importing. ## KML import: what gets created, limits and skipped rows What becomes what: - Each placemark becomes one asset. Its name becomes the asset ID. A placemark with no name is imported as "Placemark 1", "Placemark 2" and so on. - A point becomes an asset with a pin. A line becomes an asset with a route. - A polygon is imported as its outline, as a line. A placemark made of several line parts is joined into one line. The Notes tell you when this happened. - Folders only group the file, unless you choose a Type for folders. Then each folder becomes a parent asset, and the placemarks inside it become its sub-assets. - If the file carries extra data fields named type, category, model, vendor, description or parent, they are used. A type or category must match one that exists in your project. - When the same name appears twice in the file, the copies are imported as "Name (2)", "Name (3)". Limits: - The file can be up to 25 MB. - A line can have up to 2,000 points. - The file must contain at least one placemark. A row is skipped when it has no geometry, when no type is set for it, when its type or category is not in your project, when its coordinates are out of range, or when an asset with the same ID already exists. If a parent named in the file cannot be found, the asset is still created, just without a parent, and a message tells you. ## Chainage and kilometre points (KP) Chainage tells you how far along a line something is. It is written as KP, in kilometres + metres: KP 12+340 is 12 km and 340 m from the start. To choose the project's reference line: 1. Click the line that everything should be measured along, for example the main pipeline. 2. Click Use as chainage reference in the panel. This button is for the project owner or people with `projects.settings.manage`. 3. To undo it, select the line again and click Stop using as reference. Once a reference line is set: - An asset pin shows its Chainage in the panel, for example KP 4+250 on that line. If it sits a little to the side, the panel also says how many metres off the line it is. - Another line shows the stretch it covers, for example KP 2+000 – 3+500. - Anything more than 250 m away from the reference line gets no KP on it. Without a reference line, a line still shows its chainage counted from its own start. Select a line and zoom in to see kilometre posts drawn along it: one every kilometre, and one every 100 m when you zoom in further. ## Who can see and edit the map (permissions) and how to switch the Map module on Switching the module on: the Map is an optional module and it is off until someone turns it on for the project. The project owner, or someone with `projects.settings.manage`, opens the project from the Projects page, finds the Modules card on the project details page and turns on the Map switch. Turning it off later hides the Map but keeps all positions and routes. Permissions: - `maps.read`: see the Map in the sidebar and open it. The standard project roles include it. - `assets.update`: Move pins, place an existing asset on the map, and add an existing asset to a site or building. - `assets.create`: create a new asset from the map, and Import KML. - Project owner, `projects.locations.edit` or `projects.settings.manage`: add a Site or a Building. - Project owner or `projects.settings.manage`: choose the chainage reference line. - `issues.read`: see the issues list in the panel. `issues.create`: Create issue. - `layouts.read`: see Floor plans in a building's panel. Buttons you have no permission for are simply not shown. ## Map troubleshooting - I cannot see Map in the sidebar: the Map module is off for this project, or your role lacks `maps.read`. Ask a project admin to turn on Map in the Modules card of the project details page, or to give your role the permission. The Map is also not available in your personal workspace, only inside a project. - A link to the map opens a "forbidden" page: same cause. The module is off or you lack the permission. - "Nothing on the map yet": no site, building or asset has a position. Give your sites and buildings an address in Locations, give assets their own position, or click Add on the map. - An asset is missing: it may have no position of its own. Equipment inside a building is counted in the building's pin. Also check the Status and Type filters, the Assets chip and With open issues. - There is no Add button, no Move pins switch or no Import KML: your role lacks the permission. See the permissions section. - "The basemap could not be loaded": the background map did not load. Check your connection. Pins still work. - "The map service is not configured on this server": contact your administrator. - KML import says "Could not read the file": the file is not a valid KML or KMZ, or it has no placemarks. - KML import says "Nothing to import — every row has a problem": set the default types in the panel and read the Rows with problems list. - A pin has no KP: no reference line is set, or the pin is more than 250 m away from it. - A pin jumped back after I dragged it: the save failed. Try again. --- # Meetings Cx Assistant help · platform: web · module: meetings · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/meetings ## What is the Meetings module Meetings holds the minutes of the project's meetings. A meeting is a sheet of numbered points: information (something said), decisions (something agreed) and actions (someone must do something). Each point can link to the records it is about: assets, issues, RFIs, documents, scripts, reviews and planner activities. Open it from the sidebar (Meetings). The list shows every meeting you can see, newest first, with its status and how many actions are still open. Use the "With my open actions" chip to see only meetings where something is assigned to you. Seeing meetings needs the meetings.read permission. Creating them needs meetings.create, and editing, issuing and reopening need meetings.update. ## How to create a meeting and write the minutes 1. Click New meeting, give it a title and a date and time, and optionally a location (a room, a site or a call link). 2. On the sheet, add attendees with the Attendees button. Project members are picked from the directory; anyone without an account (a contractor, the client) is typed in by name, with an optional company and email. Mark each one Present, Absent or Copy only. 3. Type a point's subject in the "Add point" line and press Enter. Choose Information, Decision or Action with the chips on that line. 4. Write what was said in the text under the subject. Text saves when you leave the field. 5. For an action, set the responsible person or group and a due date from the chips on the right. Sections (for example Electrical, Documentation) are added from the ⋮ menu → Sections. Drag a point by its handle to reorder it or move it into another section. ## Seeing every open action across meetings The Open actions page lists every action that is still open, from all the meetings you can see, in one table. Open it with the Open actions button at the top of the Meetings list. Each row shows the action and its number, the meeting it comes from, who is responsible, the due date and the status. Late actions come first, with the number of days late, then the ones due soonest. Click a row to open its meeting. Two filters narrow the list: "Assigned to me" keeps only your own actions, and "Overdue only" keeps only the ones past their due date. An action leaves the page when it is closed, or when a follow-up meeting carries it over (it then appears under the follow-up). Actions of a private meeting appear only for its attendees. The page shows up to 100 actions. ## Linking points to assets, issues and documents Each point can link to the records it is about. Click Link under the point and search: one box finds issues, assets, RFIs, documents and scripts, planner activities and reviews at once. You only find what you are allowed to see. Linked records show as chips; click one to open it. If a linked record is later deleted, the chip stays but is crossed out, so the minutes still say what was discussed. The asset form and the issue dialog show a Meetings section listing every meeting that discussed that record. Actions in meetings are deliberately simple: a responsible person, a due date and a status. If something needs comments, photos or a workflow, create an issue for it and link the issue to the point. ## Issuing the minutes and saved versions When the minutes are ready, click Issue minutes. The text is locked and saved as revision 1. People with an account on the attendee list are notified. After issuing, the status of an action can still change (Open, On hold, Closed), because work goes on between meetings. The person an action is assigned to can change its status even without edit rights. The saved revision still shows the status on the day it was issued. To correct issued minutes, click Reopen and say why. The meeting goes back to draft; the next issue is saved as revision 2 beside revision 1, and nothing is overwritten. Only the latest meeting of a series can be reopened. ⋮ menu → Versions lists every revision with who issued it and why it was corrected. Open one to see it as it was, compare it with the revision before (point by point), or download that exact revision as a PDF. ## Recurring meetings: the next meeting and carried actions For a weekly or recurring meeting, open the latest one and click Next meeting once its minutes are issued. The next meeting copies the title, sections and attendees, and every action that is still Open or On hold. A carried action keeps its number (for example 2.4 stays 2.4, meaning it was raised in meeting 2) and shows what earlier meetings said about it. The copy left in the earlier meeting is frozen and marked "Carried to meeting N"; update the action in the latest meeting. The series strip under the title lets you step between the meetings of a series. Only the latest meeting of a series can be followed up, reopened or deleted. Deleting the latest meeting gives the actions it carried back to the meeting before. ## Private meetings A private meeting is visible only to the person who created it and to the attendees who are project members. Everyone else in the project does not see it in the list, in search, in the asset and issue sections, or in notifications. Project owners and administrators are not an exception. Make a meeting private when you create it, or with the lock button on the sheet. You cannot make a meeting private while leaving yourself out of it. ## Downloading the minutes as a PDF ⋮ menu → Download PDF creates the minutes as a PDF and downloads it. Nothing is saved to the project's documents; if you want the PDF there, upload it like any other file. An issued meeting prints its saved revision, so the same revision always gives the same PDF. A draft prints the current sheet with a "Draft — not issued" watermark; before the meeting, that is your agenda. The PDF is written in the project's language and time zone. ## Meetings and the assistant The assistant can find meetings and open actions ("what do I still owe from the site meetings?"), read a meeting's minutes, create a meeting or the next meeting of a series, turn your notes into points in one go, and update a point, for example to close an action. Its changes follow your chat approval setting, like any other change it makes, and points it wrote are marked with a small sparkle. The assistant cannot issue, reopen or delete minutes: a person always does that. --- # Finding your way around Cx Assistant help · platform: web · module: navigation · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/navigation ## The search bar — search the whole app from any page The search bar sits in the middle of the header on every page. It reads "Search issues, assets, files, help…". 1. Click the bar, or press Ctrl+K (⌘K on a Mac) from anywhere in the app. 2. Type at least 2 characters, or an ID such as `#42`. 3. Results appear in a panel under the bar, grouped under headings. 4. Click a result to open it. The search covers Issues, Assets, RFIs, Planner, Documentation, Trackers, Reviews and Help. At the bottom it also offers Pages you can jump to. A group with many matches shows "more matches — keep typing to narrow down". If nothing matches you see "No results. Try a different term, or an ID like #42." You only see the groups you are allowed to read. A group you have no permission for is simply not there. On a narrow screen the bar is replaced by a Search button in the top bar. It opens the same search in a dialog. ## How to narrow a search with the chips A row of chips is always visible at the top of the search panel: All, then one chip per group you can search (Issues, Assets, RFIs, Planner, Documentation, Trackers, Reviews, Help), then Pages. 1. Open the search bar. 2. Click one or more chips — for example Issues and RFIs. You can pick several at once. 3. Type your search. Only the groups you picked are searched. 4. Click All to go back to searching everything. If you pick only Pages, the search shows page shortcuts and nothing else. ## Recent searches and keyboard shortcuts in search When the search box is empty, the panel lists your Recent searches. Click one to run it again. - A search is remembered when you open one of its results. - The list keeps your last 8 searches. - It is kept in this browser only, and separately for each project (and for My Workspace). Another browser or device has its own list. You can drive the whole search from the keyboard: 1. Press Ctrl+K (⌘K on a Mac) to jump into the search bar. 2. Use the Up and Down arrow keys to move through the results. Home goes to the first result and End to the last. 3. Press Enter to open the highlighted result. 4. Press Esc to close the panel. ## What the search covers in My Workspace In My Workspace there is no project, so the search is smaller. It searches Documentation (your personal files) and Help only, and the chips show just those two plus Pages. Pages still works there. You can jump to Home, My Workspace, Projects, Project drafts, AI Assistant, Settings and its tabs, Help, Get the apps and Support. To search issues, assets or RFIs, switch to a project first with the project picker at the top of the sidebar. ## Pages results — jump to any page by name The Pages group in the search bar takes you straight to a page. It matches as you type, by the page name or by another word people use for it. 1. Open the search bar (Ctrl+K or ⌘K). 2. Type the page name or a related word. For example "punch list" finds Issues, "gantt" finds Planner, and "bin" finds Trash. 3. Click the page under Pages, at the bottom of the results. The Settings tabs are there too. Typing "connectors" offers "Settings › Connections". "security", "notifications" and "memories" work the same way and open that tab directly. The pages of the project you are in are there as well: Project settings, Members, Invites, Groups, Workflows and Configuration. Each configuration list has its own entry, so typing "issue statuses" or "asset types" opens that list directly. You can also start something new from here. "New Issue", "New Asset" and "New RFI" open the create form straight away, if your role may create them. Some pages have no entry in the sidebar, and the search bar is the way to reach them: - Custom fields — the extra fields your project adds to assets. - Trash — deleted files. - Locations — the location tree used by assets. You are only offered pages you are allowed to open, so a teammate with a different role may see a different list. ## The Help page — browse and search the guides Help holds the guides for every part of the app. Open it from Help at the bottom of the sidebar. 1. Pick a module from the Contents list on the left. Its topics open on the right. 2. Or type at least 2 characters in the "Search the help…" box. Each result shows the topic, the module it belongs to and a short extract. 3. Click a result to jump to that topic. When you open a topic from a search, the page address points at that exact topic. Copy the address from your browser to share it with a teammate — it opens Help at the same place. The "Watch the intro tour" button at the top of the Help page replays the welcome tour. The same tour is under Welcome tour in the account menu. Help topics also show up in the search bar in the header, under the Help group. ## The sidebar — main pages, Help and Feedback The sidebar on the left is the main menu. From top to bottom: - The project picker. - The project pages: Home, Assets, Issues, RFIs, Documentation, Planner, Map, Layouts, Trackers, Dashboards and Reviews. - Help and Feedback at the bottom. - Your avatar, name and email, which open the account menu. You only see the pages your role can open. Map and Layouts also appear only when the project uses them. A green Beta chip marks pages that are still evolving: Map, Layouts, Trackers and Dashboards. Reviews shows a number on its icon when items are waiting for your decision. Use the small arrow tab on the right edge of the sidebar to collapse it to icons, or expand it again. Hover an icon to see its name. Your choice is remembered in this browser. In My Workspace the sidebar is shorter: Home, My Workspace, Projects, Project drafts and AI Assistant. ## The account menu — settings, apps, support and sign out Your avatar is at the bottom of the sidebar, next to your name and email. Click it to open the account menu: - Account, Notifications, Security, Activity and Privacy & Legal — each opens that tab of Settings. - Get the apps — download links for the mobile apps and install guides for the Word and Excel add-ins. - Welcome tour — replays the short intro tour. - Support — contact the support team. - About — what Cx Assistant is. - Sign out. Settings has two more tabs, Memories and Connections. Open any Settings tab from the menu and then pick them, or type "memories" or "connectors" in the search bar. ## How to switch project with the project picker The project picker is at the top of the sidebar. It shows the project you are in. 1. Click the picker. 2. Click a project in the list to switch to it. Each project shows its code and city. The picker also has these entries: - Edit this project — opens the settings of the current project. Only shown if you own or manage it. - My Workspace — your personal files, outside any project. - All projects — view and manage every project you belong to. - Project drafts — project setups you started and have not finished. - Create project — start a new project. - Join project — use an invite code. Hover a project in the list to see two small icons: a pencil for Project settings (if you own or manage that project) and Leave project. Leaving asks you to confirm, because you lose access to the project and its data unless you are invited again. ## The header — search, processing, notifications, theme and Ask The header runs along the top of every page. From left to right: - The breadcrumb, which shows where you are. - The search bar. - Processing documents — a small ring with a number. It only appears while uploaded documents are being prepared for search and the assistant, or when some have failed. Click it to see progress, retry failed documents, or use "Open documents page". When nothing is processing it disappears. - Notifications — the bell. Inside it you can Mark all as read, and the gear opens Notification settings. - The theme button — choose System, Light or Dark. - Ask Cx Assistant — the round button at the far right. It opens the assistant in a panel beside the page you are on. It hides while the panel is open, and on the full AI Assistant page. ## Page info tips — the (i) icon beside a page title Many pages have a small (i) icon right after the page title. Hover it and it says "What is this?". 1. Click the (i) icon. 2. A card opens with a plain-words explanation of what the page is for. 3. Most cards also give a "For example" box and an "Also known as" list with the other names people use on site. 4. Click anywhere outside the card to close it. You will find it on Assets, Issues, RFIs, Planner, Map, Layouts, Trackers, Dashboards, Reviews, Locations and Custom fields, among others. It is a quick way to learn what a page does without leaving it. --- # Notifications Cx Assistant help · platform: web · module: notifications · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/notifications ## Where to find your notifications — the bell icon Your notifications live behind the bell icon in the header, visible on every page. 1. Click the bell in the top-right area of the header. 2. A menu opens listing your notifications, newest first, grouped by project. 3. Click any notification to jump straight to the item it is about. The bell shows a badge with the number of notifications you have not seen yet. Notifications arrive live — you do not need to refresh the page. They work across all your projects and need no special permission. ## What the badge number means — seen vs read The number on the bell counts UNSEEN notifications — ones that arrived since you last opened the menu. - Opening the bell menu marks everything as seen, so the badge clears. - Seen is not the same as read: notifications you have not opened yet stay in BOLD text in the list. - Clicking a notification marks it as read (bold turns to normal) and takes you to the related item. So the badge tells you "something new arrived", while bold rows tell you "you have not looked at this one yet". ## All and Unread tabs, and marking everything read Inside the bell menu: - The All tab shows every notification. - The Unread tab shows only notifications you have not clicked yet. - The mark-all-read button marks every notification as read in one click. - The settings shortcut opens Settings with the Notifications tab active, where you control which notifications you receive and on which channel. Clicking an individual notification also marks it as read and navigates to the item it refers to. ## Notifications are grouped per project — clicking switches project Notifications in the bell menu are grouped by the project they belong to. A "General" group for system-wide notifications (such as announcements) is pinned at the top. If you click a notification that belongs to a different project than the one you are currently working in, the app automatically switches your active project first, then navigates you to the related item — for example the issue, review, or planner activity the notification is about. You do not need to switch projects manually. ## Announcements — what they are and how to read them Announcements are messages from the product team, shown in the "General" group of the bell menu. Clicking an announcement opens a drawer with the full message. Announcements can include formatted text, an image, and sometimes a button linking to more information. Close the drawer to return to what you were doing. ## What kinds of notifications can I receive You may receive notifications about: - Reviews: a review step is awaiting your decision, a decision was made on a review you are involved in, or a review was closed. - Trackers: a document in a tracker you watch was rejected, or a tracker row you watch turned fully complete (green). Tracker notifications only arrive for trackers where you turned on the watch bell. - Planner: an activity was assigned to you or to one of your groups, a reminder set on an activity or milestone came due, or an activity assigned to you went overdue — it passed its planned end date. - Issues: an issue was assigned to you or to one of your groups, someone commented on an issue you created or are assigned to, or an issue went overdue — it passed its due date without being closed. The overdue notice goes to the assignee, or to the person who raised the issue when nobody is assigned, and it is sent once each time the issue slips. - Downloads: a ZIP archive you requested from Documentation is ready to download, or the download failed. - Assistant — learned a memory: the assistant saved something it learned from one of your conversations, shown as "The assistant will remember: …" (or "The assistant updated a memory: …"). Click it to open Settings on the Memories tab, where you can edit or delete that memory. This one is in-app only. - Assistant — answer ready and approval needed: the assistant finished answering in a chat you were not looking at — for example after you closed the tab, switched to another chat, or put your phone away. It never fires while you have that chat open, and the phone push is only sent when none of your devices is connected. The assistant also notifies you when it paused because an action needs your approval — sending an email, a calendar change, a deletion — in a chat you are not looking at; open the chat to approve or decline, and the notification clears once you decide. - Announcements: messages from the product team. Clicking a notification always takes you to the related item — for example an export notification opens Documentation with your download, and an assistant notification opens that chat. ## How to choose which notifications you receive You control notifications per type and per channel: 1. Open Settings (click your avatar in the header, then Notifications — or use the settings shortcut inside the bell menu). 2. On the Notifications tab you see a list of notification types. 3. Each type has two switches: In-app (the bell) and Email. 4. Toggle the switches to enable or disable each channel for that type. Changes apply immediately. This is a personal setting — it only affects your own notifications, in every project. ## Email notifications Besides the in-app bell, most notification types can also be sent to your account email address. Turn the Email channel on or off per notification type in Settings, on the Notifications tab. Emails link back into the app, landing you directly on the related item. If emails stop arriving, check your spam folder and confirm the Email switch is on for that notification type. ## Not receiving notifications — troubleshooting If you expected a notification and it did not arrive: - Check Settings, Notifications tab: the In-app or Email switch for that notification type may be turned off. - Tracker notifications only arrive for trackers where you enabled the watch bell — open the tracker and check the bell toggle. - Planner reminders are only sent to the activity's assignee and to whoever added the reminder, and only for reminders set on that activity. - The badge only counts notifications since you last opened the bell — open the menu and check the All tab; the notification may already be marked seen. - For missing emails, check your spam folder. Notifications arrive live while the app is open; if your connection dropped, they appear once you are back online or after a refresh. --- # Cx Assistant for Word & Excel — the Office add-ins Cx Assistant help · platform: web · module: office-add-ins · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/office-add-ins ## What are the Word and Excel add-ins Cx Assistant is also available inside Microsoft Office as add-ins for Word and Excel. Each add-in opens the assistant in a task pane next to your document or workbook: you sign in with the same Cx Assistant account you use here and chat about the issues, assets, documentation, and more in one of your projects. On top of project questions, the add-ins can work on the open file for you — in Excel the assistant can read and edit the workbook (values, formulas, tables, formatting, charts); in Word it can read and edit the document (text, structure, tables, charts, comments). No project yet? The add-ins also work without one. In personal mode the assistant works on the open file and on your own My Workspace files; issues, RFIs, assets, and project documents need a project. Everything respects your project permissions: the assistant can never see or change more than your account can. ## Where to find the add-ins from the web app The web app has a page that lists every place Cx Assistant runs, including the Word and Excel add-ins: 1. Click your account menu at the bottom of the sidebar. 2. Choose "Get the apps". 3. Under "Inside Microsoft Office", find the Word add-in and Excel add-in cards and click Install guide. The guide opens in a new browser tab. You can also reach the page from the search bar — type "apps" or "add-in" — and from the last slide of the intro tour. ## How to install the Excel add-in Install Cx Assistant for Excel from the Office Add-ins store: 1. In Excel, go to Insert and click Add-ins (in Excel on the web, Add-ins is on the Home tab). 2. Search for "Cx Assistant". 3. Click Add. After installing, an "Open Cx Assistant" button appears on Excel's Home tab — click it to open the assistant pane, then sign in with your usual Cx Assistant email and password. For a full step-by-step install guide with screenshots, see cx-assistant.com/en/install/excel. ## How to install the Word add-in Install Cx Assistant for Word from the Office Add-ins store: 1. In Word, go to Insert and click Add-ins (in Word on the web, Add-ins is on the Home tab). 2. Search for "Cx Assistant". 3. Click Add. After installing, an "Open Cx Assistant" button appears on Word's Home tab — click it to open the assistant pane, then sign in with your usual Cx Assistant email and password. For a full step-by-step install guide with screenshots, see cx-assistant.com/en/install/word. ## Requirements — which versions of Office are supported The add-ins work in Office on the web and in Office desktop on Windows and Mac with a Microsoft 365 subscription. Technically, the Excel add-in needs Excel API 1.4 or newer and the Word add-in needs Word API 1.3 or newer — recent Microsoft 365 builds provide both. A few newer features need newer Office builds — for example, working with comments in Word needs Word API 1.4 or newer. On older builds those features are not available while everything else keeps working. Word and Excel are the add-ins available today; there is no PowerPoint add-in yet. ## Signing in and getting help inside the add-ins The add-ins use your existing Cx Assistant account — sign in with the same email and password you use on the web (including two-factor authentication if you have it enabled). Forgot your password? Use the forgot-password link on the sign-in screen. You can also create an account directly in the pane: after you sign up, open the confirmation link we email you, then sign in. After signing in, the pane opens in your first project — or in My Workspace (personal mode) if you have no project yet. To switch, open the history panel (the ≡ icon in the pane's top bar) and use the selector at the top to pick a project or My Workspace. The pane remembers your choice. Need help while in Word or Excel? Ask the assistant, or send a support ticket: open the history panel (≡), click the ⋮ button at the bottom of the panel, and choose "Help & support". Public support centres: cx-assistant.com/en/support/excel and cx-assistant.com/en/support/word. --- # Planner Cx Assistant help · platform: web · module: planner · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/planner ## What is the Planner The Planner is your project schedule. It holds activities — tasks, milestones, and groups — with dates, assignees, dependencies, reminders, and links to assets and issues. Open it from the sidebar (Planner). You can work in four views: Gantt (timeline bars with dependency arrows), Table (a flat editable list), Calendar (Outlook-style month, week, and day), and Progress (what was planned, achieved, and slipped on a given day). The planner updates live, so changes made by teammates appear as they happen. Viewing the planner requires the planner.read permission (all built-in roles have it). ## How to switch between Gantt, Table, Calendar, and Progress views Use the view switch in the planner toolbar (four icon buttons — hover one to see its name) to change between: - Gantt: a timeline with bars, a tree of groups and tasks, and dependency arrows. - Table: a flat, editable table of all activities. - Calendar: Outlook-style Month, Week, and Day layouts. - Progress: what was planned, achieved, and slipped on one day, plus a planned vs achieved chart. Your choice is remembered, so the planner reopens in the view you used last. ## Gantt view basics: tree, zoom, Today, collapse The Gantt view shows a tree of groups, tasks, and milestones on the left and their bars on a timeline to the right, with arrows for dependencies. - Zoom: switch the timescale between Day, Week, and Month, or hold Ctrl (Cmd on Mac) and scroll the mouse wheel to step the zoom. - Today: click Today to jump the timeline to the current date. - Collapse/expand: click the arrow next to a group to fold or unfold its children. The list is virtualized, so large plans stay fast. ## How to create an activity There are three ways to create activities (you need the planner.create permission): 1. Toolbar dialog: click Add task, Add milestone, or Add group in the planner toolbar and fill in the details. You can also use the row context menu presets to add near an existing row. 2. Drag to create (Gantt): click and drag on empty space in a row's timeline — a ghost bar previews the dates, and the activity is created when you release. 3. Drag to create (Calendar): drag across empty cells in Month view, or drag on the hour grid in Week/Day view, to create an activity spanning that range. ## Tasks vs milestones vs groups The planner has three activity types: - Task: regular work with a start and end date, progress %, assignee, and so on. - Milestone: a single-date marker for a key event or deadline. - Group: a container that organizes other activities. A group's dates and progress are derived automatically from its children — you don't set them directly (the activity panel shows a rollup hint). Use the row context menu to indent/outdent rows (nest them under a group) or select several rows and choose Group to wrap them in a new group. ## How to move or resize an activity bar In the Gantt view (with the planner.update permission): - Move: drag a bar left or right to shift the whole activity to new dates. - Resize: drag the left or right edge of a bar to change its start or end date. In Calendar view you can do the same: drag a chip to move it, or drag a chip's edge to resize it. If the Push successors toggle is on, moving a bar also shifts activities that depend on it (see the dependencies section). ## Dependencies between activities and lag Dependencies link activities so one follows another. In the activity panel, open the Dependencies section: - Add a predecessor: pick the activity this one depends on. New links start as finish-to-start with 0 lag. - Type: change the link type (for example finish-to-start or start-to-start). - Lag: set a number of days of delay between the predecessor and this activity. - Successors: the panel also lists activities that depend on this one, with their type and lag. In the Gantt view, dependencies are drawn as arrows between bars. ## Push successors toggle — cascade date changes The Push successors toggle in the planner toolbar controls what happens to dependent activities when you move a bar: - On: shifting an activity cascades the shift to its successors (activities that depend on it), keeping the chain consistent. - Off: only the activity you move changes; dependents stay where they are. The toggle's state is remembered between visits. When you move several selected bars or a group bar at once, the push is applied once for the whole move. ## Multi-select and bulk actions (group, set status, delete) Select several activities to act on them at once: - Ctrl/Cmd+click (or Shift+click) rows or bars to build a selection. - A floating action bar appears with the selection count and the actions: Group (wrap the selection in a new group), Set status (apply a status to all selected), Delete, and a clear button. - Dragging one selected bar moves all selected bars together as a single shift. Bulk edits need the planner.update permission; bulk delete needs planner.delete. ## Planner keyboard shortcuts In the Gantt view: - Delete or Backspace: delete the selected activities (a confirmation applies). - Esc: clear the current selection. - Ctrl/Cmd+A: select all visible activities. - Ctrl/Cmd + mouse wheel: zoom the timescale in and out. Combine Ctrl/Cmd+click and Shift+click with these to work quickly on many activities. ## Table view The Table view lists every activity in a flat, editable table — useful when you want to scan or update fields quickly without the timeline. Click into a row to edit it; changes save like anywhere else in the planner (editing requires planner.update). Use the view switch in the toolbar to return to Gantt or Calendar at any time. ## Calendar view: Month layout The Calendar view's Month layout shows activities as chips spanning the days they cover, packed into lanes so overlapping activities stay readable. When a day has more than fits, a "+N more" link drills into that day. - Use Prev / Next to page between months and Today to jump back to the current date. - Drag across empty cells to create an activity spanning those days. - Drag a chip to move it, drag a chip's edge to resize it, and click a chip to select and open it. ## Week and Day views, all-day vs timed activities Week and Day layouts show an all-day band at the top and a 24-hour rail below. By default activities are all-day and appear in the band. To give an activity clock times, open it and turn OFF the All day toggle, then set start and end times — it then appears on the hour grid. On the hour grid you can drag on empty space to create a timed activity, drag a chip to move it to another time, and drag a chip's edge to change its duration. The activity's day range still comes from its start and end dates; times refine where it sits within the day. ## Progress view: planned, achieved, and slipped for a day The Progress view answers "are we making progress?" for one day. Open it with the Progress button in the view switch of the planner toolbar. It needs only the planner.read permission, and it is read-only: nothing is edited here. Pick the day in the week strip at the top (Monday to Sunday). The arrows in the toolbar move one week back or forward, and Today returns to the current day. Days are counted on the project's site time zone, so everyone sees the same numbers; a "Site time" chip appears when your own time zone is different. What is counted: - Planner tasks and milestones. Groups are not counted. - Asset statuses that have an Expected date. They are shown with their status level and the asset tag. Three tiles and three lists: - Planned ("Planned for this day"): items due on that day — a task's end date, a milestone's date, or an asset status's Expected date. The tile also shows how many of them are on time, meaning already done by that day. - Achieved ("Achieved this day"): items completed on that day, whatever day they were due. An activity is achieved when its status is Done, on its Completed date; the Progress % slider does not count here. - Slipped ("Slipped — due earlier and still open"): items due before the selected day that are still not done. Each row shows how many days late it is, with the latest first. A green tick marks rows that are done. Click an activity row to open its panel; asset rows cannot be opened from here. Filters: the search box and the Filters button (assignee and linked asset) narrow the tiles and lists. The date range filter is ignored in this view, and an assignee filter hides asset rows because they have no assignee. The Level list, shown when the project has asset status levels, limits the asset rows to one level; activities stay listed. ## Throughput chart: planned vs achieved per day or per week Below the lists, the Progress view shows the Throughput chart. - Switch between Per day (the four weeks ending with the selected week) and Per week (twelve weeks). Your choice is remembered. - Each day or week has two bars side by side: a tinted, outlined bar for what was planned and a solid bar for what was achieved. - Bars are stacked by colour: one colour for planner activities, and the project's own status colours for asset status levels. The legend under the chart names them. - Hover a bar to see the dates, the planned and achieved totals, and the split per colour. Click a bar to select that day in the lists above. - The Level list also applies to the chart. The search box and the Filters button do not. The line under the chart reads "Variance vs baseline": the average and the largest number of days that the activities in the range have moved from their baseline start, how many of them were rescheduled, and how many have a baseline. If it says no activity in the range has a baseline yet, use Re-baseline to set one. ## Baseline, variance, and actual dates (planned vs actual) Every task and milestone keeps a baseline: a copy of its start and end dates that stays fixed while the activity moves, so you can see how far the plan has drifted. Groups have no baseline. When the baseline is taken (you never type it in): - When the activity is created with dates. A duplicate gets its own baseline from its own dates. - If an activity has no baseline, it is taken from the dates it had just before its start date is next moved. - When someone uses Re-baseline, which replaces the baseline of every dated task and milestone. An activity created without dates has no baseline when you first schedule it — it shows "No baseline" until it is moved again or the plan is re-baselined. Variance is the current start date minus the baseline start date, in days. A plus value (red) means later than baseline, a minus value (green) means earlier. Where you see it: - Activity panel: a Baseline row with the baseline dates and a variance chip ("On baseline" when nothing moved). Hover the dates to see when the baseline was set. - Gantt: when an activity is off its baseline, a thin grey bar (a hollow diamond for a milestone) sits under the bar at the baseline position, joined by a dotted line. - Table: Baseline, Actual, and Variance columns. Actual dates: Actual start is stamped when the status changes to In progress or Done, and Completed when it changes to Done. Setting the status back to Planned clears both. If the work really happened on another date, correct it in the activity panel (needs planner.update). Reschedule history: each time an activity's start date moves, the panel's Reschedule history records when, by how many days, and why. Dragging a bar in the Gantt view first asks for an optional reason ("Reason for the move"). Moves caused by Push successors are listed as pushed by the activity that caused them. ## How to re-baseline the plan Re-baseline makes the current dates the new baseline — for example after a revised programme has been agreed. It needs the planner.update permission. 1. Click Re-baseline at the top right of the planner (the button is hidden while the plan is empty). 2. Optionally type a reason. 3. Click Re-baseline to confirm. Every task and milestone that has dates takes its current dates as its new baseline, and a message tells you how many activities were updated. Groups and undated activities are skipped. Good to know: - It applies to the whole plan. You cannot re-baseline a single activity or a selection. - The previous baseline is replaced, so variance starts again from zero for every activity. - Reschedule history and actual dates are kept. ## Asking the assistant to delete an activity You can ask the assistant in chat to delete a task, a milestone, or a group — for example "delete PL-12". - It always asks you to approve first. This applies in every approval mode, and the approval cannot be switched to "don't ask again". - Deleting a group deletes every activity inside it. The assistant tells you how many were removed. - Dependencies that other activities had on the deleted ones stop applying. - You need the planner.delete permission, the same as deleting in the planner yourself. - A deleted activity cannot be restored from the app, whether you or the assistant deleted it, so check the approval request before accepting. ## The activity panel — all fields explained Click an activity to open its panel on the right. Fields: - Name, start and end dates, and the All day toggle with start/end times. - Progress %: how complete the activity is. - Assignee: a project member or a group. - Reminders: up to 5 heads-up pings before the start — minutes, hours, days or a week ahead for timed activities, days ahead for all-day ones. - Dependencies: predecessors with type and lag, plus a successors list. - Linked assets and Linked issues. - Colour: the bar/chip colour. - Notes: free text. - Baseline, Actual start, and Completed: read-only planned vs actual dates (the two actual dates can be corrected), plus the Reschedule history — see the baseline section. - A PL- reference chip and a status chip at the top identify the activity. Groups show a rollup hint instead of editable dates/progress — those come from their children. Editing requires the planner.update permission. ## Reminders — heads-up notifications before an activity starts Each task or milestone can have up to 5 reminders. 1. Open the activity and find Reminders in the panel. 2. Open the "Add reminder…" list and pick how long before the start you want the heads-up. 3. The reminder appears as a chip. Click the x on a chip to remove it. The choices depend on the activity: - Timed activities (All day is off): At the start time, 15 minutes, 30 minutes, 1 hour, 2 hours, 1 day, 2 days or 1 week before. - All-day activities: On the start day, or 1, 2, 3, 7, 14 or 30 days before. When it arrives: - A timed reminder counts back from the activity's start time. It is delivered within a few minutes of that moment, and the notification shows the time in your own time zone (with the site time added when it differs). - An all-day activity has no clock time, so its reminders go out at 08:00 in the project's Site time zone (set in the project details). "1 day before" means 08:00 site time on the day before. A chip with a tick has already been sent; hover a chip to check ("Reminder sent"). If you move the activity so a sent reminder's moment is in the future again, it is sent again. A reminder you add when its moment has already passed is marked as sent straight away and does not notify anyone. Who gets it: the assignee (every project member of the group, when the activity is assigned to a group) and whoever added the reminder. Reminders arrive in the bell, and by email or phone push depending on each person's notification settings. Activities already marked done do not send reminders. ## Assigning an activity to a person or group In the activity panel, use the Assignee field to assign the activity to a single project member or to a group (groups are defined on the project's Groups page). When you assign someone, they receive a planner.assigned notification. Assignees also receive activity reminders and due notifications for their activities. ## Linking assets and issues to an activity In the activity panel you can link the activity to project assets and issues, so the schedule connects to the real work items. The links are visible from both sides: the asset and issue edit dialogs include a Linked planner activities card showing which activities reference them, with click-through back to the planner. ## How to duplicate an activity Right-click an activity row and choose Duplicate (also available for a selection). The copy keeps the original's notes, links, and reminders, and is inserted directly below the original. The row context menu also offers indent/outdent, move up/down, group selection, and delete. ## How to search and filter activities Type in the search box in the planner toolbar to filter the tree live — only activities matching your text (and their parent groups) stay visible. Clear the search to see the full plan again. Ctrl/Cmd+A selects all currently visible activities, so search plus select-all is a quick way to bulk-edit a subset. ## Planner notifications and deep links The planner sends four notification types (visible in the bell menu, and by email depending on your notification settings): - planner.assigned: you were assigned to an activity. - planner.reminder: a reminder set on an activity came due (sent to the assignee and to whoever added the reminder). - planner.activityDue: an activity is past its planned end date. - planner.slipped: the daily slipped digest. Once a day per project, after 06:00 site time, it says how many planned activities and asset statuses were due the day before and not done, and how many items are open past their date in total. It goes to the project owner and every member who can see the planner, and only when something slipped. Clicking a planner notification opens the planner with that activity selected; the daily slipped digest opens the Progress view on the day it counted. You can tune channels per type in Settings > Notifications. ## Who can view and edit the planner (permissions) Planner access is controlled by project role permissions: - planner.read — see the planner. Default: Project Admin, Project Member, Technician. - planner.create — add activities. Default: Project Admin, Project Member. - planner.update — edit, move, resize, assign, bulk-edit activities, and re-baseline the plan. Default: Project Admin, Project Member. - planner.delete — delete activities. Default: Project Admin only. The project owner can always do everything. If a toolbar button or edit action is missing or disabled, ask a project admin to adjust your role. ## Planner troubleshooting - Can't see the Planner in the sidebar: your role lacks planner.read — ask a project admin. - Can't create or edit: creating needs planner.create, editing needs planner.update; Technicians don't have these by default. - Can't set dates or progress on a group: group dates and progress are derived from their children — edit the child activities instead. - Moving a bar moved other activities too: the Push successors toggle is on; turn it off to move bars independently. - An activity is missing: check the search box isn't filtering the tree, and expand collapsed groups. - A reminder didn't arrive: only the assignee and the person who added the reminder receive it. Hover the chip — "Reminder sent" means it already went out. All-day activities remind at 08:00 in the project's Site time zone, not at midnight. A reminder added after its moment had already passed is never sent. Also review your channels in Settings > Notifications. --- # Project Cx Assistant help · platform: web · module: projects · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/projects ## What is a project A project is a workspace that groups your assets, issues, RFIs, documents, planner, users, and configuration. Each project has its own members, roles, permissions, and settings. You switch between projects (and your personal My Workspace scope) with the project picker in the sidebar. ## How to create a new project Creating a project happens on one page: the Basics on the left, the templates on the right, and a Create project button that stays in view at the bottom. 1. Open the project picker in the sidebar and click Create project (also available from the Projects page). 2. Fill in the Basics: Project name, Code (a short identifier used as a prefix throughout the project), Client company — type to search, or use the Create company option to add a new company without leaving the page — and Project language. The language is the one the project's own content is written in (status labels, document names). It cannot be changed after the project is created. Location is optional. 3. Pick a template. The Default template is already selected, so you can skip this step. Under "Or pick a template for your industry" you can search the templates, filter them by Industry, and click Preview on a card to see its statuses, priorities and asset types. One click on a card sets up the issue, RFI and asset sets your project starts with. If no template fits, use the Build your own card instead. 4. Click Create project. It stays disabled until name, code, client and language are filled in. If the code is already used by another project, the Code field tells you so. You can change every status, priority and type later from the Configuration card on the project details page. Your progress is saved automatically as a draft (you will see "Draft saved") — you can leave at any time and resume later from the Project drafts page. You can also create a project by asking the assistant in the chat — search the chat help for "create a project from the chat". ## Which starter template should I pick A template decides the statuses, priorities and types your project starts with. Nothing is permanent — you can rename, add or retire any of them later. Click Preview on a card to see exactly what it contains. - Default: the basics. A simple asset lifecycle from created to complete, issues that are open or closed with 3 priority levels, and assets can move to any status. This is what you get if you do not choose. - Data Centre Commissioning: a 6-level tag commissioning ladder (L0–L5), 6 QA/QC issue statuses with 4 priority levels, and ready-made data centre asset types (UPS, BAT, MDB, CRAC and more). - Operations & Maintenance: operational asset states with no ladder — an asset can go straight to retired — and QA/QC issues with the standard priority levels. - Substation / Utilities: the commissioning tag ladder applied to power-distribution asset types, an operations-oriented set of issue types, and 4 priority levels. - HV Substation Commissioning: a step-by-step energization ladder from Received to In Service, A/B/C punch categories as issue priorities, and a full HV equipment catalogue of about 30 asset types. - Elevator Maintenance: breakdown and entrapment call-outs with 4 priority levels, and a service state for every unit instead of a ladder. The Map module starts switched on, and the project uses the elevator vocabulary (Units and Service Calls instead of Assets and Issues). - Wind Farm Commissioning: a turbine commissioning ladder from components on site to taken over, A/B/C punch categories, and a wind farm asset catalogue (turbines and their parts, met mast, MV collector, poles, substation). The Map module starts switched on. - Wind Farm Maintenance: an operating state for every turbine (running, stopped on fault, under maintenance) with no ladder, fault and service issue types with 4 priority levels, and the same wind farm asset catalogue. The Map module starts switched on. Every template includes the RFI process. Not sure? Start with Default and add structure when you need it. ## Build your own — set up a project without a template If no template fits, the Build your own card on the Create a new project page walks you through a few short steps. It starts from the Default setup, so anything you do not touch still works. 1. On the template side of the page, find the Build your own card and click Start building. 2. Pillars: tick what you want to shape now — Issues, RFIs and Commissioning. Planner, Dashboard and Document review are part of every project and need no setup here. 3. Issues (only if ticked): pick your Issue statuses and Priorities from the suggestions, or add your own. 4. RFIs (only if ticked): pick your RFI statuses and RFI types. 5. Commissioning levels (only if ticked): pick the levels your assets move through. 6. Review: drag the levels into order and give each one a colour, a tag name and a full name. Switch Strict tag ladder on if assets must advance one level at a time. The page checks your setup and lists anything you must fix first. 7. When the review says everything checks out, click Create project at the bottom of the page. Good to know: - The builder has up to five steps. A pillar you leave unticked is skipped and the project gets the standard set for it. - Use Back to go to an earlier step, or Back to templates to return to the template cards. - Your choices are saved to the draft as you go. If you leave, open Project drafts and resume — the draft reopens in the builder where you stopped. - Create project stays disabled until you reach the Review step and it has no blockers. ## Project drafts — resume or delete an unfinished project If you start creating a project and leave before finishing, your work is kept as a draft. Open Project drafts (from the sidebar in personal scope, or via the project picker) to see your unfinished drafts. From there you can: - Resume a draft to continue where you left off. - Delete a draft you no longer need. Drafts that were completed show a finalized badge. ## Switching projects and the personal scope The project picker in the sidebar controls your active scope: - Click a project to make it active — the whole app (assets, issues, documents, planner, and so on) shows that project's data. - Switch to Personal (My Workspace) to work in your private personal space; project pages are unavailable there and redirect to your workspace. - Shortcuts: All projects, Project drafts, Create project, and Join project. Hovering a project row shows a pencil icon that opens its settings (visible to the owner or users who can manage settings). If you are on a project-specific page when you switch, the app moves you to the same page in the new project. ## How to leave a project To leave a project you are a member of: 1. Open the project picker in the sidebar. 2. Hover the project's row and click the trash icon. 3. Confirm in the dialog. Leaving removes your membership — you will need a new invite or join code to come back. This is different from deleting the project: leaving only affects your own access. ## Project details page overview Open a project from the Projects page (cards with code, name, city, and a status chip) to reach its details page. It is organised in cards, each shown only if you have access to it: - Project name and code (editable inline), and the project status chip. - Billing and usage limits. - Project info (client company, location) and Timeline & company (start/end dates). - Invite members button. - Configuration: the Vocabulary and Site time zone settings, plus a tile for each configuration set with a Manage sets button. - Members, Groups, and Review workflows cards, each with a button that opens its page. The Review workflows card also holds the Asset docs tracking switch. - Modules: switch the Map and Layouts modules on or off. - Locations: the project's location tree, which you can edit right on the card. - Project branding and Team memories cards. Most fields update inline, so changes save immediately. ## Who can edit project settings There is no single "project edit" permission. Editing project information and settings is allowed for: - The project owner — always, for everything. - Users holding projects.settings.manage (Project Admins by default). That permission also gates the configuration sets, custom fields, project branding, team memories, and the doc-groups/placeholders vocabulary. Location tree editing uses its own keys (projects.locations.edit / projects.locations.remove). One exception: billing is owner-only — no role or permission can grant billing access to anyone else. ## Project status (Active, Completed, Paused, Archived) The status chip next to the project name shows the project lifecycle state: - Active: current work in progress. - Completed: work finished. - Paused: temporarily on hold. - Archived: inactive, kept for reference. Click the chip to change the status (owner or settings managers). Changing status never deletes data; it only updates the project's state. ## Billing and subscription — owner only The billing card shows the subscription summary for the project: current plan and billing status. - A project without a subscription is on the free plan, shown as "Free for individuals": it works for one person, the owner, with a small storage allowance. Nothing is locked except inviting teammates. - To invite a team, the owner starts a subscription from the subscribe dialog (Start subscription). - If a subscription is cancelled, the project returns to the free plan: existing members and files stay, but no new members can be added and uploads stop once the free storage allowance is used. - If subscribed, the owner can open the billing portal to update payment methods, view invoices, or cancel. Important: billing is strictly OWNER-ONLY. Only the project owner can subscribe or open the billing portal — no role or permission can grant billing access to other members. If billing shows a problem (for example suspended), the owner should resolve it in the portal. ## Usage limits (users and storage) The usage cards show consumption against your plan limits with progress bars: - Users: members used vs. the seat maximum. - Storage: space used vs. the maximum. When usage nears or exceeds a limit the card highlights it, and a banner appears on the Members page when the seat limit blocks new invites. Upgrading the plan (owner, via billing) raises the limits. ## Project info, timeline, and company On the project details page you can edit: - Client company: pick from the company list. - Location: start typing an address and pick from the autocomplete suggestions. - Timeline: start and end dates with calendar pickers. Fields save inline. Editing needs the owner or projects.settings.manage. ## Modules card — switch the Map and Layouts modules on or off The Modules card on the project details page lists the optional modules this project uses: - Map: buildings and assets on a live map. Off by default, except in projects created from the Elevator Maintenance and Wind Farm templates, where it starts on. - Layouts: 3D floor plans. On by default. How to switch a module: 1. Open the project details page and scroll to the Modules card. 2. Flip the switch next to Map or Layouts. It saves at once and you see "Modules updated". Switching a module off hides it from the sidebar and the search bar for everyone in the project. Its data is kept, and comes back when you switch the module on again. The card is only shown to the project owner and to users holding `projects.settings.manage` (Project Admins by default). A module that is switched on still follows the usual permissions for who can open it. ## Vocabulary — change the words the app uses in this project The Vocabulary row sits at the top of the Configuration card on the project details page. It sets the words the app uses for this project. - Standard: the app says Assets and Issues. - Elevator maintenance: the app says Units instead of Assets and Service Calls instead of Issues — in the sidebar, page titles, buttons and messages. How to change it: 1. Open the project details page and find the Configuration card. 2. Click the chip on the Vocabulary row and pick a vocabulary. The change applies to everyone in the project, each in their own language. It only changes the words on screen. Your assets, issues and configuration sets are not touched, so you can switch back at any time. The assistant also uses the project's vocabulary when it talks to you. Projects created from the Elevator Maintenance template start with the Elevator maintenance vocabulary. Changing it needs the project owner or `projects.settings.manage`. ## Site time zone — the clock planner times and reminders follow The Site time zone row is on the Configuration card of the project details page, under Vocabulary. It is the time zone of the site itself, not your own. Planner times and reminders follow the site's clock. A reminder for an activity at 09:00 fires at 09:00 site time, so everyone is notified at the same moment, and each person sees the time in their own zone. Your personal time zone stays in your account settings. How to set it: 1. Open the project details page and find the Configuration card. 2. Click the Site time zone box, type a city or region (for example Europe/Dublin) and pick it from the list. It saves at once. A project that was never given a time zone uses UTC. If you change the time zone, reminders that are still pending are moved to the new site time. Changing it needs the project owner or `projects.settings.manage`. ## Members page — view, invite, change roles, remove The Members page lists everyone with access to the project (avatar, name, email, role). Viewing it needs the members.read permission (Project Admins by default). What you can do: - Invite members: click Invite members (needs members.invite) and send invitations with a chosen role; for advanced invite management (expiry, revoke, copy link/code) use the Invites page. - Change a role: open a member and pick a new role — built-in roles are Project Admin, Project Member, and Technician, plus any custom roles your project defines (needs members.roles.assign). - Remove a member: use the delete action (needs members.remove); removal takes effect immediately. If the project's seat limit is reached, a subscription banner appears and new invites are blocked until the plan is upgraded. Note: every member can still pick teammates in assignee fields across the app — that directory does not require members.read. ## Groups — create teams you can assign work to The Groups page shows your project's groups as searchable cards. A group is a named set of members (for example "Electrical crew") that can be assigned work as one unit. What you can do (admin-only by default): create a group (name, description, members), edit it, and delete it with confirmation. Viewing needs groups.read; create/update/delete have their own keys (groups.create, groups.update, groups.delete). Where groups can be assigned: issues, RFIs, planner activities, and workflow approval steps. When something is assigned to a group, every group member counts as responsible. ## Workflows card — review workflow definitions The Review workflows card on the project details page has a Manage workflows button that opens the project's workflow definitions: ordered chains of approval steps, each with user or group approvers, used by the Reviews module. Viewing needs workflows.read; creating, editing, archiving, and deleting definitions needs workflows.manage (Project Admins by default). This page is only where workflows are defined — for how reviews actually run (creating a review, deciding on items, closing), search the Reviews help. ## Document tracking mode — Review vs Status The Review workflows card on the project details page has a row called Asset docs tracking. Click the chip on that row to choose how document placeholders are tracked across the whole project (Asset Docs and trackers). You do not need to open the Workflows page for this. - Review mode (the default): placeholder chips reflect each linked document's review outcome — status comes from the formal review process. - Status mode: placeholder chips carry their own manually-set status, chosen from the tracker's status definitions, independent of reviews. Switching the mode changes what every placeholder chip shows everywhere, for everyone — it is non-destructive (no data is deleted), but the meaning of the chips changes. Only settings managers or the owner can switch it. ## The eleven configuration sets The Configuration card on the project details page shows a tile for each of the project's eleven configuration sets. Click a tile to open that set, or click Manage sets to open the Sets page, which groups them like this: - Issues: Issue statuses, Issue priorities, Issue types. - RFIs: RFI statuses, RFI priorities, RFI types. - Assets: Asset statuses, Asset types, Asset categories. - Documents: Document groups, Document slots. These sets define the vocabulary and flows used across the whole project — every status dropdown, priority list, and type list comes from here. The issue, RFI and asset sets are filled in by the starter template you picked at project creation and can be edited any time. The two document sets are not part of a template: Document groups are the columns of the document tracker and are created the first time something is dropped in one, and Document slots holds the documents your project added on top of the shared document library. Access: project owner or projects.settings.manage. ## Editing a configuration set (statuses, types, priorities) Opening a set from the hub shows its editor. What you can do: - Rename a member: edit the name in place — it saves when you leave the field. - Set flags: mark which member is the initial one (where new records start) and which is the default. - Add members, or retire a member you no longer want offered (retiring keeps history intact). - Apply a preset: replace the set with a curated preset list. - Edit the transition policy: define which status can follow which, controlling the allowed next statuses users see on assets, issues, and RFIs. - Reorder by drag and drop — reordering is STAGED: the list goes dirty and a save bar appears showing the real consequence of your change (for example how completion percentages shift for existing records) before you commit. Navigating away with unsaved changes is intercepted. These changes affect how everyone creates and edits data, so review the impact preview before saving. ## Custom fields manager The Custom fields page is a tabbed manager for custom attribute definitions, organised per entity (for example assets). For each field you define its type, options, whether it is required, and a default value. How to open it: the page has no sidebar entry and no button on the project details page. Use the search bar instead. 1. Click Search at the top of the app, or press Ctrl+K (Cmd+K on a Mac). 2. Type "custom fields". 3. Pick Custom fields under Pages. The Custom fields result only appears if you are allowed to manage the project's settings. What you can do: create, edit, and delete field definitions; soft-delete a field and restore it later; or permanently delete it. Access needs projects.settings.manage (or the project owner). Once defined, the fields appear on the matching records — for assets, in the Technical section of the asset dialog (filling values there is gated by assets.edit.technical). ## Project branding and team memories Two more cards on the project details page, both for the owner or settings managers: - Project branding: set the project's visual identity, such as the logo used in exports and project surfaces. - Team memories: project-wide memories for the AI assistant — facts and preferences the assistant should remember for everyone working in this project (personal assistant memories live separately in your own Settings). Editing team memories needs projects.memories.edit. ## Projects troubleshooting - Cannot edit project fields or configuration: you need to be the project owner or hold projects.settings.manage (there is no separate "project edit" permission). - Cannot see billing or the billing portal: billing is owner-only; no permission can grant it. - Invites blocked: the seat limit may be reached — the owner needs to upgrade the plan. - A company is missing from the client list: create it from the create-company option in the project form, or ask an admin. - Status or type options look wrong across the app: check the eleven configuration sets and their transition policies — open them from the Configuration card on the project details page. - Map or Layouts is missing from the sidebar: the module may be switched off for this project — the owner or a settings manager can switch it on in the Modules card on the project details page. - Cannot find the Custom fields page: it has no menu entry — press Ctrl+K and type "custom fields". - Lost your in-progress project setup: it is saved as a draft — open Project drafts to resume. --- # Reviews Cx Assistant help · platform: web · module: reviews · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/reviews ## What are reviews A review is a formal approval process for project files: you pick a workflow (an ordered chain of approval steps), add items — documents, folders, scripts, or templates — and the designated approvers approve or reject each item step by step. Open Reviews from the sidebar. Viewing requires the reviews.read permission (all built-in roles have it). Reviews update live, so decisions from teammates appear as they happen. ## The review queue and the sidebar badge The number badge on Reviews in the sidebar counts items that are AWAITING YOUR DECISION, and it updates live. On the Reviews page, click the "Awaiting me" chip to filter the list to reviews that need you; those rows also show a "Your decision" marker in the Awaiting column. The list is a table with sortable columns and filters that are kept in the page URL — so a filtered view survives a refresh and can be shared as a link. The list opens showing Open reviews only. Change or clear the Status filter to see Closed and Cancelled reviews. ## How to create a review 1. On the Reviews page, click New review (requires the reviews.create permission). 2. Enter a title (required) and, if you want, a description. 3. Pick a WORKFLOW — once picked, the dialog shows its chain of approval steps. If the project has only one workflow it is already selected. 4. Add items with Add document, Add script, or Add template. Picking a folder adds every document inside it as its own item (up to 200 documents per folder; a review holds up to 500 items). Only completed scripts and published templates can be added. (Tracker cells can also seed a review via their Send for review action, and the Documentation bulk bar has Send to review too.) 5. Click Start review. Approvers of the first step are notified that items await their decision. Each document is pinned at its current version, and an item can be in only one active review at a time. If your project has no workflows yet, the dialog says so. Users with workflows.manage get a Create a workflow button that opens the project's Workflows page; everyone else is told to ask a project admin. A workflow must exist before you can create a review. ## How to approve or reject items Open a review to decide on its items (requires the reviews.decide permission, and you must be an APPROVER on the item's current step — see below): 1. Select an item in the list on the left. Its pinned version is previewed on the right, with Approve and Reject buttons under the preview. Approving takes an optional comment; rejecting requires a reason. 2. For many items at once: tick their checkboxes (or click "Select all awaiting me") and use the Approve selected / Reject selected buttons at the top of the list. Items where it isn't your turn are skipped. You can only decide on steps where YOU are listed as an approver (directly or through a group). Project Admins holding reviews.decide.override can decide on ANY step. A step set to "All approvers" completes only when every listed user and at least one member of every listed group has approved; on an "Any approver" step one approval is enough. Approving the last step approves the item; a rejection on any step ends the item's round. Each item in the list carries a step progress pill showing how far it has advanced through the chain. ## Item status and timeline Each item in a review shows a status chip (In review, Approved, Rejected, or Withdrawn) and has its own timeline: who decided what, on which step, when, and with what comment. Select an item and expand History under its preview to read every round. A warning icon next to the chip means the content changed after it was submitted: a newer version exists than the one under review, or the content changed after the decision. While an item is in review, its step progress pill in the item list shows the current step and its position in the workflow chain. ## How to add items to an existing review Open the review and click Add items (requires the reviews.create permission; the review must still be open). Pick documents, folders, scripts, or templates as when creating the review — the new items start at the first step and appear in the item list. ## How to resubmit a rejected or changed item A rejected item is not the end: fix the document, script, or template, then open the review, select the item, and click Resubmit (requires the reviews.create permission; the review must still be open). Resubmitting pins the item's current content and starts a new round from step 1, so every approver sees it again. Earlier rounds stay in the item's History. Resubmit is also offered while an item is still in review if a newer version appeared after it was submitted. For a document, approvers can keep deciding on the pinned version, or you can resubmit to put the latest version under review. A script that was reopened has to be completed again and resubmitted before it can be decided. ## How to close, cancel, withdraw, or delete a review From the review detail page: - Close review: finish the review. Close is blocked while items are still in review, and a closed review cannot be reopened. - Cancel review: stop the review without completing it. Items still in review are withdrawn. - Withdraw: pull a single ITEM out of the review, using the withdraw icon next to the selected item's name. The rest of the review carries on. - Delete: remove the review entirely. Only a closed or cancelled review can be deleted (requires the reviews.delete permission — Project Admins only by default). You'll be asked to confirm; items that this review approved or rejected lose that review status and go back to pending. Close, Cancel, and Withdraw require the reviews.update permission (Project Admins and Project Members by default). Withdrawing an item or cancelling the review releases the items that were still in review, so they can be sent to another review. Items already approved or rejected keep their outcome. ## Review stamps on documents and the in-review lock Documents carry their review outcome with them: in the Documentation module, files show review status chips (with tooltips) reflecting the reviews they went through, and you can filter the file list by approval or review status. A document's status is not set by hand — it follows its review. While a document is IN an active review it is held by that review and cannot be added to another one. Once a review has approved or rejected it, the status only changes through a new review round: resubmit it in the same review, or send it through a new review. ## How to see all files of a review On a review's page, click "View files in Documentation" to jump to the Documentation module filtered to exactly the documents in that review (the button appears when the review contains documents). From there you can preview, download, or open each file as usual. You can also get there from Documentation directly: the filter menu has a specific-review picker (reviews are labelled R-1, R-2, ...). ## Workflows — defining the approval chains A workflow is an ordered chain of approval steps; each step names its approvers — individual members or groups — and a rule: Any approver (one approval is enough) or All approvers. Every review runs on one workflow, and keeps the steps it started with even if the workflow is edited later. Find them on the project's Workflows page (open the project details page and click Manage workflows on the Review workflows card). Viewing needs workflows.read (Project Admins and Members). Creating, editing, archiving/unarchiving, and deleting workflow definitions needs the workflows.manage permission (Project Admins by default). A show-archived switch reveals archived workflows. Tip: create at least one workflow before anyone needs to start a review — the New review dialog requires one. ## How to create or edit a workflow On the project's Workflows page (requires the workflows.manage permission): 1. Click New workflow, or click the edit (pencil) icon on an existing workflow. 2. Name the workflow, then define the ordered steps with Add step: give each step a name, choose its rule (Any approver or All approvers), and pick its approvers — project members or groups. Every step needs at least one approver. Use the arrows to move a step up or down. 3. Save. The workflow is now available in the New review dialog. Editing a workflow does not change reviews that are already running — they keep their original steps. You can archive a workflow to retire it without deleting history, restore it later, or delete it. A workflow that an existing review has used cannot be deleted — archive it instead. Use the show-archived switch to see archived ones. ## Review notifications Reviews notify you through the bell menu (and by email or phone push, depending on your settings): - review.awaiting (Awaiting your decision): items reached a step where you are an approver. - review.decided (Decisions on your submissions): items you submitted were approved or rejected. - review.closed (Review closed): a review you created was closed or cancelled. This one comes by bell and email, not by push. You are not notified about your own actions. Clicking a notification takes you to the review. Tune channels per type in Settings > Notifications. The sidebar Reviews badge also live-counts items awaiting you. ## Who can do what in reviews (permissions) - reviews.read — see the Reviews page and open reviews. Default: Project Admin, Project Member, Technician. - reviews.create — create reviews, add items, and resubmit items. Default: Project Admin, Project Member. - reviews.update — withdraw items, close or cancel reviews. Default: Project Admin, Project Member. - reviews.delete — delete closed or cancelled reviews. Default: Project Admin only. - reviews.decide — approve/reject, but ONLY on steps where you are an approver. Default: all built-in roles. - reviews.decide.override — decide on any step regardless of approver lists. Default: Project Admin only. - workflows.read (Admin, Member) to view workflows; workflows.manage (Admin) to create/edit/archive them. The project owner can always do everything. ## Reviews troubleshooting - Can't approve or reject an item: you can only decide on steps where you are an approver (directly or via a group). If it's not your step, wait for the earlier steps — or ask an admin, who can use the override. A script that was reopened after it was submitted must be completed and resubmitted before anyone can decide on it. - New review dialog says there are no workflows: someone with workflows.manage must create a workflow on the project's Workflows page first. - Can't add an item: it is already held by another active review, the script is not completed yet, the template is not published, or the folder holds more than 200 documents (add its subfolders instead). - Can't close a review: closing is blocked while items are still in review — decide on them, withdraw them, or cancel the review instead. - Can't delete a review: only closed or cancelled reviews can be deleted, and you need reviews.delete. - Can't change a document's status: document statuses follow reviews — the change must come from a review's outcome. - Reviews missing from the sidebar: your role lacks reviews.read — ask a project admin. - A review is missing from the list: the list opens filtered to Open reviews — change the Status filter. - The badge count seems off: it counts items awaiting YOUR decision specifically; click the "Awaiting me" chip to see the reviews they are in. --- # RFIs Cx Assistant help · platform: web · module: rfis · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/rfis ## What is an RFI An RFI (Request For Information) is a formal question that needs an official answer — for example a clarification about a drawing, a specification, or a site condition. Unlike an ordinary comment thread, an RFI tracks who must answer, by when (due date), and ends with one designated OFFICIAL response. Open the RFIs page from RFIs in the sidebar. Viewing needs the rfis.read permission, which all built-in roles have by default. ## The RFIs list page The RFIs page lists all RFIs in the current project as a table. Columns include a status colour bar, Id, title, priority, assignee (a user or a group), due date (with an Overdue chip when the date has passed), and status. - Click a column header to sort. - Use the filter row under the headers to narrow results. - Click a row to open the RFI for editing. - The delete column appears only if you can delete RFIs. - Pagination controls are at the bottom. ## Filter RFIs and share a filtered view Use the filter row under the column headers to filter by id, title, priority, assignee, status, and more. Filters are stored in the page URL, so: - Your filtered view survives a page refresh. - You can copy the URL and send it to a teammate — they open exactly the same filtered list. Combine filters with column sorting to find the right RFI quickly. ## Export the RFIs list to Excel You can download the RFIs table as an Excel file (.xlsx) — for example an RFI log to share with a client. 1. On the RFIs page, set the filters and sorting you want. The export matches what the table shows. 2. Click the three-dot Page actions button next to the RFIs title and choose Export…. 3. The Export table dialog opens. If you have filters on, it reminds you that the active filters and sorting apply to the export. 4. Optional: switch on Only visible to me to keep the file private. 5. Click Export. The button shows that the file is being generated. When it is ready, the file opens in a new browser tab and a message confirms the export. What is in the file: one row per RFI with its Id, title, priority, assignee, type, status, due date, who created it and when, and the description. All matching RFIs are exported, not just the current page, up to 5,000 rows. Where the file goes: without the switch, the message reads "Export ready — saved to the project's documents". With Only visible to me on, it reads "Export ready — saved privately for you" and only you can see the saved file. Anyone who can see the RFIs page (`rfis.read`) can export — no extra permission is needed. ## How to create an RFI 1. On the RFIs page, click the create button. 2. Give the RFI a clear title phrased as the question you need answered. 3. Add a description with the context: what you looked at, what is unclear, what decision depends on the answer. 4. Set priority, type, assignee (the person or group who should answer), and a due date. 5. Save. Creating RFIs needs the rfis.create permission — all built-in roles have it by default. ## Edit an RFI: fields you can change Click an RFI row to open its edit dialog. You can update: - Title and description (inline). - Priority and type (defined by your project). - Assignee: a single user or a whole group. - Due date. - Watchers: people who follow the RFI. - Status (follows your project's status flow). - Linked assets: connect the RFI to the equipment it concerns. - Attachments: upload files or pick existing documents. You can edit if you created the RFI, are its assignee, belong to the assigned group, or hold the rfis.update permission. ## Due dates and the Overdue chip Every RFI can have a due date — the date by which the official answer is needed. Set or change it in the RFI's edit dialog. When the due date passes and the RFI is still open, the list shows an Overdue chip next to the date so overdue questions stand out. Sort or filter the list to chase overdue RFIs first. ## Watchers: follow an RFI The watchers list on an RFI holds the people who want to follow it besides the creator and assignee. Add teammates as watchers from the RFI's edit dialog so the right people can keep an eye on the question and its answer. Use watchers for stakeholders who are affected by the answer but are not the ones answering. ## Comments vs the official response An RFI has two levels of conversation: - Comments: the open discussion — clarifying questions, partial answers, back-and-forth. Anyone with rfis.comment (all built-in roles) can comment. - The official response: ONE answer shown in its own card, which is the formal, authoritative reply to the RFI. The official response is created by promoting a comment: once the discussion produces the definitive answer, that comment is promoted into the official response card. It can also be cleared again if it was promoted by mistake. Promoting or clearing needs the rfis.respond permission. ## Who can set the official response Promoting a comment to the official response, or clearing it, needs the rfis.respond permission — held by Project Admins and Project Members by default. Important: unlike editing or status changes, there is NO creator or assignee shortcut for responding. Even the RFI's creator or assignee cannot set the official response without rfis.respond. This keeps the official answer authoritative. If you should be able to respond but can't, ask a project admin for the permission. ## Change an RFI's status Change status from the RFI's edit dialog. The available options follow the status flow defined by your project, and some statuses are terminal — once the RFI reaches them, it is considered closed. You can change status if you created the RFI, are its assignee, belong to the assigned group, or hold the rfis.status.update permission (Project Admin and Project Member by default). If the status you expect is unavailable, the flow may only allow certain next steps — ask a project admin about the configured transitions. ## Who can do what with RFIs Default permissions (the project owner can always do everything): - View: rfis.read — Project Admin, Project Member, Technician. - Create: rfis.create — Project Admin, Project Member, Technician. - Edit: rfis.update — Project Admin, Project Member. Also allowed without the permission for the RFI's creator, its assignee, and members of the assigned group. - Change status: rfis.status.update — Project Admin, Project Member. Same creator/assignee/group bypass applies. - Comment: rfis.comment — Project Admin, Project Member, Technician. - Set/clear the official response: rfis.respond — Project Admin, Project Member. NO creator or assignee bypass. - Delete: rfis.delete — Project Admin only. If an action is hidden or disabled for you, ask a project admin to adjust your role. ## RFI problems — troubleshooting - Can't edit an RFI: you can only edit if you created it, are assigned to it (directly or via a group), or have rfis.update. - Can't promote a comment to the official response: this always needs rfis.respond — there is no creator/assignee shortcut. - Can't change status: needs rfis.status.update or the creator/assignee/group bypass; also check that the target status is allowed by the project's flow, and note that some statuses are terminal. - Delete column missing: deleting needs rfis.delete (Project Admin by default). - Filters seem stuck after sharing a link: filters live in the URL — clear them from the filter row or remove the URL parameters. - An RFI shows Overdue: its due date passed while it was still open — answer it or move the due date. --- # Scripts & Templates Cx Assistant help · platform: web · module: scripts · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/scripts ## What are scripts and script templates A script is an executable checklist — a structured procedure (for example a test or commissioning protocol) where you record Pass/Fail results, measured data, notes, evidence, and signatures. A script TEMPLATE is the reusable definition a script is created from. Scripts and templates live inside the Documentation module as documents in the tree — there is no separate Scripts page anymore; old script links simply redirect into Documentation and open the right script. Note: by default, scripts are visible and usable by PROJECT ADMINS ONLY (see the permissions section). ## How to create a script from a template 1. In Documentation, open the New menu and choose New script (requires the scripts.create permission). 2. Pick the template to run — only PUBLISHED templates can be used (drafts must be published first). 3. The new script is created as a document in the tree and opens ready to fill in. Scripts can also live in Asset Docs tracker cells as script slots, tying a procedure to a specific asset. ## Recording results: Pass, Fail, N/A Each checklist item has result toggles: click Pass, Fail, or N/A to record the outcome — click the same result again to clear it (requires the scripts.execute permission). Items marked as required show a required marker, and each completed item shows the avatar of who completed it. Your entries save automatically; a save-status indicator at the top shows when everything is stored. ## Data fields, validation, and notes Items can include typed data fields for measurements and readings. Enter the value in the field; fields with a defined range are validated, and out-of-range values are flagged. A flagged value does not stop you from finishing. When you complete the script, required fields left empty and out-of-range values are listed as warnings. You can go back and fix them, or accept them with Complete anyway (see the completing section). Always record the value you actually measured — validation exists to surface problems, not to force a "good" number. Each item also has a notes area for observations and context. ## Attaching evidence to a script item Checklist items accept evidence attachments — photos or files that prove the step was done. Use the attachment control on the item to upload or pick evidence; attached files are visible to everyone working the script. ## Navigating a script: sections and outline Scripts are organized into sections. While a script is open, the Documentation sidebar swaps to the script's section OUTLINE — click a section to jump straight to it. As you scroll, the outline highlights where you are. At the top you have breadcrumbs and a back button to return to the folder, plus the save-status indicator. An inspector pane offers Details and History tabs for the script's metadata and change log. ## Signatures — how signing works The Signatures panel lists the script's signature slots. To sign: 1. Open your slot and draw your signature on the signature pad. 2. Optionally add a comment, then confirm. You can also REJECT a slot with a comment instead of signing. Only the expected signer can sign a slot: you can sign slots assigned to you or unassigned ones (requires the scripts.sign permission). Admins holding scripts.sign.override can sign any slot. A required slot that is not signed blocks completion — it cannot be accepted as a warning. ## Completing a script — warnings you can accept vs blockers Once all the steps are done, a Complete script button appears in the bottom bar. While a required signature is still missing, the button reads Sign off to complete instead. Clicking it takes you to the signatures and shows "Sign off all required signatures to complete this script." When you click Complete script, one of three things happens: 1. Nothing is open: the script completes and you see "Script completed". 2. There are WARNINGS: an amber dialog titled "Complete this script?" lists them. A warning is a required field marked "Left empty", or a value outside its expected range (the row shows the value you entered and the range). Click a row to go to that step. Choose "Go back and fill them" to fix the values, or "Complete anyway" to accept them as they are. Warnings you accept are recorded in the script's History. 3. There are BLOCKERS: a red dialog titled "This script isn't finished" lists them. A blocker is a required step marked "No result recorded", or a required signature marked "Not signed". There is no Complete anyway button here. Close the dialog, resolve each one, and try again. Completing locks the script. The warnings dialog reminds you: "Completing locks the script. You'll have to reopen it to change anything." Need to change something after completion? Use Reopen in the bottom bar to put the script back in progress, make the correction, and complete it again. ## Editing a script's structure With the scripts.update permission you can switch a script into structure editor mode to adjust its sections and items — separate from filling in results. Structure changes are for fixing the procedure itself; day-to-day execution (results, data, notes, evidence) happens in the normal runner and needs only scripts.execute. ## Templates: draft, published, archived Templates live in the Templates scope of the Documentation sidebar, with filter chips for All / Drafts / Published / Archived. Lifecycle: a new template starts as a DRAFT; publish it (requires the scriptTemplates.publish permission) to make it available for creating scripts; archive it when it should no longer be used. Only PUBLISHED templates appear in the New script picker. Use New template to create one, and delete from the same panel. ## Editing a template Open a template to edit its definition: - Sections and checklist items. - Typed data-field definitions (the measurements scripts created from it will collect, including validation ranges). - Signature slots (who must sign). The editor offers grid and list views and a bottom save bar. Remember to PUBLISH the template when it's ready — scripts can only be created from published templates. ## Sending a script or template to review Scripts and templates can go through the same formal review process as documents. Open the script's metadata panel (or select it in Documentation) and choose Send to review, pick a workflow, and create the review (requires the reviews.create permission). Approvers then decide on it from the Reviews page, and the outcome is stamped on the script like any reviewed document. ## Working together: live presence and field locks Scripts support live collaboration. You can see who else has the script open, and while someone is editing a specific field it is locked for others, so two people can't overwrite each other's entries. Changes from teammates appear in real time. ## Who can use scripts (permissions) — admin-only by default IMPORTANT: by default, ONLY Project Admins hold script permissions. Project Members and Technicians cannot even see scripts unless a custom role grant gives them access — ask a project admin if your team needs wider access. The keys: - scripts.read — see scripts. - scripts.create / scripts.update / scripts.delete — create, edit structure, delete. - scripts.execute — fill in results, data, notes, and evidence. - scripts.sign — sign slots assigned to you or unassigned; scripts.sign.override — sign any slot. - scriptTemplates.read / create / update / publish / delete — manage templates. The project owner can always do everything. ## Scripts troubleshooting - Can't see any scripts or the New script option: script permissions are Project Admin-only by default — other roles need a custom grant. - A template doesn't appear when creating a script: it's still a draft — it must be PUBLISHED first. - Can't complete the script: only two things block completion — a required step with no result, and a required signature that is not signed. The "This script isn't finished" dialog lists them; click a row to go to the step. Empty required fields and out-of-range values are only warnings — you can accept them with Complete anyway. - Can't sign a slot: only the expected signer can sign; ask that person, or an admin with the sign override. - Script is read-only: it's completed and locked — use Reopen to edit again. - A field won't accept my edit: a teammate may be editing it right now (field lock) — wait a moment. - An old /scripts link: it now redirects into Documentation and opens the script there — that's expected. --- # Profile & Settings Cx Assistant help · platform: web · module: settings · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/settings ## How to edit your profile — name, email, avatar You edit your personal details on the Account tab of Settings: 1. Click your avatar at the bottom of the sidebar and choose Account. 2. Under Profile details, edit your Name, Surname, Email or Phone, then click Save. 3. To change your picture, click Upload and pick an image (JPEG, PNG or WebP, up to 5 MB). A progress bar shows while it uploads, and the new picture applies right away. 4. To go back to your initials, click Remove. Your avatar and name appear across the app: in member lists, comments, assignee pickers, and presence indicators. ## Settings overview — the tabs and how to reach them The Settings page groups your personal preferences into tabs: - Account: profile details, avatar, language, timezone and job title. - Notifications: which notifications you receive, and on which channel. - Memories: the assistant's saved memories about you. - Security: two-factor authentication, backup codes, sessions, and password. - Activity: your account activity feed. - Connections: link the assistant to services you use, such as Outlook, Gmail and Notion. - Privacy & Legal: terms and privacy documents. To get there, click your avatar at the bottom of the sidebar — the account menu opens the Account, Notifications, Security, Activity and Privacy & Legal tabs directly. For Memories and Connections, open Settings and pick the tab. You can also type a tab's name in the search bar in the header (Ctrl+K or ⌘K) — for example "memories" or "connectors" — and open it from the Pages results. Settings are personal and need no project permission; they apply to your account across all projects. ## Account tab — language, timezone and job title The Account tab holds your basic account preferences: - Your avatar, and your Profile details: Name, Surname, Email and Phone. - Language: choose the language the app uses for you. It applies to the app, the assistant's replies and your emails. Content written by your team (issue titles, document names, statuses defined by your project) stays exactly as it was written. - Timezone: used for local times in the assistant and in reminders. - Job title: tells the assistant who it is talking to, so answers fit your role. Click Save to apply your changes. They are personal — they affect only your account, not anyone else. At the bottom, the Danger zone has Delete account. It is permanent, and asks you to type your email address to confirm. ## How to switch between light and dark mode The theme toggle lives in the header, available on every page: 1. Click the theme mode button in the header. 2. Choose Light, Dark, or System. System follows your operating system's appearance automatically. Your choice is remembered on this device. There is also a colour-mode selector on the sign-in screen, so you can pick your theme before signing in. ## Notifications tab — choose what you get notified about The Notifications tab lists every notification type you can receive — for example review decisions, planner reminders, issue assignments, tracker alerts, and export results. Each type has two switches: - In-app: shows the notification under the bell icon in the header. - Email: also sends it to your account email address. Toggle each channel on or off per type; changes apply immediately and affect only your own notifications, in every project. You can jump here quickly via the settings shortcut inside the bell menu. ## Memories tab — what assistant memories are The assistant can remember facts and preferences to give you better answers — for example how you like reports formatted, or context about your work. The Memories tab lets you see and manage everything it has remembered about you. Memories come in two scopes: - Global: applies whenever you talk to the assistant, in any project. - Project: applies only when you are working in that specific project. You are always in control: every memory is visible here, and you can edit or delete any of them. ## How to add, edit, or delete assistant memories On the Memories tab in Settings: 1. Pick the scope — Global (all projects) or a specific Project. 2. Add a new memory by writing what the assistant should remember. 3. Edit an existing memory to correct or refine it. 4. Delete a memory to make the assistant forget it. These are your personal memories. Team-wide memories — shared context every member's assistant should know about the project — are managed separately in Project settings (Team memories card) by people with the `projects.memories.edit` permission or the project owner. ## How to set up two-factor authentication with an authenticator app (TOTP) Two-factor authentication adds a second check at sign-in, protecting your account even if your password leaks. To enable the authenticator-app method: 1. Go to Settings, Security tab. 2. Start the authenticator (TOTP) setup — a QR code appears. 3. Scan the QR code with your authenticator app (Google Authenticator, Authy, 1Password, and similar apps all work). 4. Enter the 6-digit code from the app to confirm. Once enabled, the Security tab shows since when it has been active, and sign-in asks for a code from your app. Save your backup codes when offered — they are your way in if you lose the phone. If you enter 5 wrong codes, verification is locked for 15 minutes and you see "Too many failed attempts". Wait for the time shown, then try again with a fresh code. ## Email codes as a two-factor method (Email OTP) Besides an authenticator app, you can use one-time codes sent to your email as a two-factor method: 1. Go to Settings, Security tab. 2. Enable the Email OTP method. At sign-in you can then choose to receive a code by email and enter it to finish signing in. You can disable the method again from the same tab. If you have both methods enabled, the sign-in screen lets you pick which one to use. The same safety limit applies here: 5 wrong codes lock verification for 15 minutes. ## Backup codes — save them, they are shown only once Backup codes are single-use codes that let you sign in when you cannot use your usual two-factor method (lost phone, no email access). On the Security tab you can see how many backup codes you have left and regenerate a fresh set. Important: - Codes are shown ONCE, right when generated — copy them and store them somewhere safe (a password manager is ideal). You cannot view them again later. - Each code works one time only. - Regenerating replaces all previous codes — old ones stop working immediately. ## How to disable two-factor authentication 1. Go to Settings, Security tab. 2. Find the two-factor method you want to turn off — authenticator app (TOTP) or Email OTP. 3. Use its disable action and confirm. After disabling, sign-in goes back to email and password only (or your remaining method, if you had two). For account safety, consider keeping at least one two-factor method enabled. ## Sessions — see where you are signed in and sign devices out The Sessions list on the Security tab shows every device and browser where your account is currently signed in. To sign out a device remotely, click Revoke next to its session — that device is signed out immediately. Use this if you forgot to sign out on a shared computer or notice a session you do not recognise. If you see anything suspicious, revoke the session and change your password right away. ## How to change your password 1. Click your avatar at the bottom of the sidebar and choose Security. 2. Scroll to the Change password card. 3. Type your New password, then type it again under Confirm new password. It needs at least 8 characters, with upper and lower case letters and a number. 4. Click Update password. Use the new one next time you sign in. Pick a strong, unique password you do not use elsewhere. If you cannot sign in because you forgot your password, use "Forgot your password?" on the sign-in screen instead — that sends a reset link to your email. ## Activity tab — your account activity feed The Activity tab shows a feed of recent activity on your account, so you can review what has been happening. Check it if you want to verify recent actions or spot anything you do not recognise. If something looks wrong, review your Sessions on the Security tab, revoke anything unfamiliar, and change your password. ## Connections tab — link Outlook, Gmail, Notion and your own servers The Connections tab is where you connect the assistant to services you use: Outlook mail, Outlook Calendar, Gmail, Notion, and your own servers. Click Connect on a service, sign in on the service's own page, and you come back with it connected. Connections are yours only — they are tied to your account, not to a project, and nobody else can use them. Sending an email or a meeting invitation always asks for your approval first. See the Connections help topics for step-by-step guides: connecting each service, what the assistant can do with it, approvals, removing or reconnecting, and troubleshooting. ## Privacy & Legal tab — terms and privacy The Privacy & Legal tab gives you access to the legal documents that apply to your account: the Terms of Service and the Privacy Policy. They are also available without signing in at the public legal pages linked from the sign-up form. --- # Sign up Cx Assistant help · platform: web · module: sign-up · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/sign-up ## How to create an account Step-by-step: 1. Enter your Name (at least 2 characters). Surname is optional. 2. Enter your Email. 3. Create a Password and confirm it. 4. Tick both boxes: one to agree to the Terms of Service and one to accept the Privacy Policy. 5. Click Create account. You will then see a "check your email" panel — open the confirmation email we send you and click the link to activate your account. ## Password requirements Your password must: - Be at least 8 characters long - Include at least one uppercase letter - Include at least one lowercase letter - Include at least one number A warning appears if Caps Lock is on. Pick something strong and unique — a password manager helps. ## Terms of Service and Privacy Policy You must accept the Terms of Service and the Privacy Policy to create an account. Each has its own checkbox, and both must be ticked. Click their links in the form to read each document in an inline dialog without leaving the page. Both documents are also available as full pages at any time — the public legal pages for terms and privacy — and later from Settings, on the Privacy & Legal tab, once you are signed in. ## Email confirmation and resending it After signing up you see a "check your email" panel. Open the confirmation email and click the link to activate your account — you cannot sign in until your email is confirmed. If the email does not arrive: - Check your spam or junk folder. - Use the resend button on the panel to send a fresh confirmation email. ## Confirm email page The confirmation link opens a page that verifies your email automatically. It shows whether your address was confirmed, was already confirmed earlier, or whether the link is expired or invalid — in which case you can request a new confirmation email right there. Once confirmed, click "Go to sign in" to log in. ## After your first sign-in A new account does not belong to any project yet. After you confirm your email and sign in, you land on a welcome page with two choices: - Create new project — set one up from scratch or from a template. You can also ask the assistant in chat to create the project for you; it asks you to confirm first. - Join existing project — enter the 8-character code from your invite email. You do not need a project to get started: chat and My Workspace, your personal files, work without one. If you signed up from an invite link, the invite is accepted automatically when you sign in in the same browser, and you land in that project. ## Already have an account Use the Sign in link to go back to the login page if you already have an account or have already confirmed your email. ## Common sign-up errors - Email already exists: sign in instead, or use "Forgot your password?" on the sign-in screen to reset it. - Validation errors: review the required fields and the password rules; the form highlights what is missing. - Server unavailable: check your network connection and try again. ## Account security tips - Use a strong, unique password you do not reuse elsewhere. - Store passwords in a trusted password manager. - Keep your email account secure — it is used for verification and account recovery. - After signing in, consider enabling two-factor authentication in Settings, on the Security tab. --- # Support, Feedback & About Cx Assistant help · platform: web · module: support · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/support ## How to submit a support ticket 1. Click your avatar at the bottom of the sidebar and choose Support. You can also type "support" in the search bar in the header and open it from the Pages results. 2. Choose a reason: Billing & payments, Technical issue, Account & access, Feature request, or Other. 3. Describe your problem or question in the details field — the more specific, the faster we can help. 4. Click Submit request. You get a ticket number on screen as confirmation, and a note that you will be contacted by email. Keep the ticket number handy if you follow up. ## The support centre The Support page includes a link to the support centre, where you can find help articles and further assistance beyond submitting a ticket. Use the support centre for self-service answers; use the ticket form when you need a person to look at your specific case. ## How to send feedback — ratings, categories, and ideas The Feedback page is for telling us what you think of the app — bugs, ideas, or general impressions: 1. Open Feedback at the bottom of the sidebar. 2. Pick a star rating from 1 to 5. 3. Choose a category chip: Bug, Feature, Idea, or Other. 4. Write your comment (a counter shows how many characters are left). 5. Optionally leave "Include technical context (browser, screen, timezone)" on — it helps us reproduce bugs. 6. Click Submit feedback, or Clear to start over. Anyone signed in can send feedback — it needs no project permission. ## Feedback or support — which one should I use Use Support when you need help or an answer: something is broken for you, a billing or account question, or you are stuck. Support creates a ticket and you will be contacted by email. Use Feedback when you want to tell us something: rate the app, report a bug you worked around, suggest a feature, or share an idea. Feedback does not open a ticket, so if you need a reply, choose Support. ## The About page The About page presents what the app is and the mission behind it. To open it, click your avatar at the bottom of the sidebar and choose About. It is informational — a good place to point new teammates at for a quick idea of what the product does. ## Where to find help inside the app Help is never far away: - The Help page: click Help at the bottom of the sidebar. It has guides for every module, a search box, and a button to watch the intro tour again. - The search bar in the header: press Ctrl+K (⌘K on a Mac) and type your question. Matching guides appear under the Help group, and clicking one opens it on the Help page. - The assistant: click the round Ask Cx Assistant button at the right end of the header and ask your question in plain language. The assistant knows the app and can often answer how-to questions instantly. - The (i) icon beside many page titles explains what that page is for. - Feedback: also at the bottom of the sidebar, in every project and in My Workspace. - Account menu: click your avatar at the bottom of the sidebar — Support and About are there, together with Welcome tour and Get the apps. - Support centre: linked from the Support page for help articles. None of these need any special permission. --- # Trackers Cx Assistant help · platform: web · module: trackers · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/web/trackers ## What are trackers Trackers are status grids: rows of items crossed with document placeholders, where each cell shows the state of a linked document. Teams use them to follow deliverables at a glance — which documents exist, which are approved, which were rejected, and what is still missing. Open Trackers from the sidebar. Viewing requires the trackers.read permission (all built-in roles have it). Trackers update live, so you see teammates' changes as they happen. ## The tracker library and mini previews The Trackers page shows all trackers as cards in a grid. Each card has a live mini preview of the grid and a status segment bar summarizing how its cells are doing, so you can spot progress without opening it. The built-in Asset Docs card is always first — it opens the project-wide Asset Docs tracker (assets crossed with document requirements). Click any other card to open that tracker's full page. Use the show-archived switch to also list archived trackers. ## How to create a tracker 1. On the Trackers page, click New tracker (requires the trackers.create permission). 2. Enter a tracker name (required) and, if you want, a description. 3. Pick a tracking MODE: Review mode (cells mirror each linked document's review status) or Status mode (cells carry their own status from a list you manage). 4. Under Start from, pick a template or keep the blank tracker. A template may select the mode it suits best; you can still change it. 5. Click Create tracker — the new tracker opens and you can start adding rows and linking documents. By default, Project Admins and Project Members can create trackers. ## Review mode vs Status mode — what's the difference Every tracker works in one of two modes (you can switch without losing data): - REVIEW mode: each cell chip mirrors the review-derived status of the linked document — approved, rejected, in review, and so on. You don't set cell statuses by hand; the only action verb is Send for review. Statuses change as reviews are decided. - STATUS mode: each cell chip carries its own status key, chosen from the tracker's status list. Use the Manage statuses dialog to define the vocabulary, then set statuses directly on cells that have a linked document. To switch, open the three-dot menu at the top right of the tracker page and choose Switch to status mode or Switch to review mode (requires trackers.update). Nothing is deleted: cell statuses are kept and come back when you switch back. Choose Review mode when a formal review workflow drives your document states; choose Status mode for a simpler, manually-updated board. ## The Asset docs tracking switch (project setting) Each tracker you create has its own mode. The built-in Asset Docs tracker instead follows a project setting called ASSET DOCS TRACKING — Review mode or Status mode — that decides what its document placeholder chips show. In Review mode the chips mirror each document's review status; in Status mode each placeholder holds its own status, set in the tracker, and the documents themselves are not touched. This switch does not change the trackers in your library. It is the Asset docs tracking row on the Review workflows card of the project details page. Changing it needs the projects.settings.manage permission (Project Admins) or the project owner. If chips in the Asset Docs tracker suddenly look different, this switch is usually why. ## Reading the tracker grid A tracker page shows a grid: row labels down the left (your tracked items), one column per group across the top (placeholders without a group sit under General), and inside each column a chip for every document placeholder that row has, showing that document's state. A row only shows the placeholders it was given. Script cells also show their completion percentage. Above the grid you have a row search, a status filter, a group filter, and status count chips — click a count chip to filter by that status. The grid updates live as teammates link documents or change statuses. ## How to link or unlink a document in a cell 1. Hover a cell chip and click the three-dot button that appears to open its menu. 2. Choose Link document and pick the item from the picker — documents, folders, and scripts can be linked. The cell chip now reflects it. Relink points the cell at a different item. 3. To remove the link, open the cell menu and choose Unlink. 4. Open jumps straight to the linked document in Documentation; clicking a linked chip does the same. Linking and unlinking require the trackers.update permission (Project Admins and Project Members by default). ## Cell notes and setting cell statuses Open a cell's menu and choose Add notes… (or Edit notes…) to keep a note on that cell — useful for context like "waiting on vendor" or "resubmitted 3rd version". A cell with a note shows a small note icon; hover it to read the note. Notes require trackers.update. In STATUS mode you also set the cell's status from the tracker's status list (defined in the Manage statuses dialog), or remove it with Clear status. The cell needs a linked document first. In REVIEW mode statuses are not set by hand — they mirror the linked document's review outcome, and the cell's action is Send for review instead (requires reviews.create). When a document is tied to a review, the cell menu also offers Open review. ## How to manage a tracker's statuses (Status mode) Every tracker starts with three statuses: Approved, Pending, and Rejected. To change the list: 1. Switch the tracker into edit mode and click Manage statuses (requires trackers.update). 2. Add a status with a name, a color, and a meaning: Done, Open, or Blocked. You can rename, recolor, or change the meaning of an existing status in the same dialog. 3. To delete a status that cells still use, pick the status that replaces it first. The meaning drives completion: a row counts as fully complete when every one of its cells is linked and in a Done status. The status list is used when the tracker is in Status mode; it is kept while the tracker is in Review mode. ## Edit mode — rows, groups, placeholders, and the palette Switch the tracker into edit mode with the pencil button at the top right (requires trackers.update) to change its structure: - Add rows (type or paste one label per line, up to 1000 at a time), Add group, and Add placeholder (a name plus a short code of up to 6 characters shown on the chip). - Drag a placeholder from the Placeholders palette onto a row to give that row the cell. Dropping onto a selected row adds it to every selected row. - Drag a row by its handle to reorder it (handles are hidden while a filter is active). - Rename a row by double-clicking its label. - Click rows to select them (Shift+click selects a range, Ctrl/Cmd+A selects all loaded rows, Esc clears), or click chips to select individual cells. - Delete rows removes the selected rows; Remove cells removes the selected cells. - Remove a placeholder with the x on its palette entry, or a group with the x on its column header. If rows still use it you are asked to confirm; linked documents are not touched. - Manage statuses edits the status list used in Status mode. Switching between view and edit mode never loses data. ## Watching a tracker — the bell toggle and notifications Click the bell icon on a tracker to WATCH it — anyone who can view the tracker can. Watchers receive this tracker's notifications: - tracker.docRejected (Tracked document rejected): a document linked in the tracker was rejected in a review. - tracker.rowGreen (Tracker row complete): a row became fully complete — every cell is linked and in a done status. These notifications arrive in the bell menu only; there is no email for them. You can switch each type off in Settings > Notifications. You are not notified about changes you made yourself. Click the bell again to stop watching. ## How to export a tracker to PDF or Excel 1. Open the tracker and click the Export (download) button at the top right. Anyone who can view the tracker can export it — trackers.read is enough. 2. Choose PDF or Excel (xlsx). 3. Pick options: Include cell notes, Show project logos and Grayscale (both PDF only), and Only visible to me — a private export is saved to your private exports instead of the project exports folder. 4. Click Export. The file opens for download and is also saved as a document. It is generated with your CURRENT filters applied, so filter first if you want a subset. An export holds at most 5000 rows. If the tracker has more, the file says how many are shown — narrow the filters to export the rest. ## How to archive or delete a tracker From the three-dot menu on a tracker's card in the library you can: - Archive a tracker to tidy the library without losing it (requires trackers.delete). Turn on the show-archived switch to see archived trackers, and Unarchive to bring one back (requires trackers.update). - Delete permanently (requires the trackers.delete permission — Project Admins only by default). You must type DELETE to confirm. The tracker and its rows are removed and cannot be recovered; the linked documents are not touched. ## The Asset Docs tracker — what it is Asset Docs is the built-in, project-wide tracker: a matrix of your ASSETS crossed with document placeholders and groups. It answers "which documents does each asset have, and in what state?". Open it from the first card in the Trackers library. Viewing needs both assets.read and documents.read (all built-in roles have both). Its chips follow the project's Asset docs tracking setting (Review mode or Status mode), not a mode of its own. ## Using the Asset Docs grid (view mode) In view mode, each cell shows a status chip for that asset/placeholder pair. You can: - Link or unlink documents on a cell, and preview image documents in place. - Use script slots: cells can hold scripts, with a preview and a switch-script-version dialog to point the slot at a different version. - Filter and search, collapse or expand groups, turn on Compact chips in Table settings (with a width slider), and read the stats bar for overall progress. - When the project's Asset docs tracking is Status mode, set a linked cell to Approved, Pending, or Rejected from its menu, or clear it (requires assets.update or documents.update). In Review mode the chips mirror each document's review status and are not set by hand. To send cells for review, switch to edit mode, click the chips to select them, and choose Send to review (requires reviews.create). ## Editing the Asset Docs tracker (edit mode) Switch Asset Docs to edit mode (requires assets.update or documents.update) to change its structure: - The palette on the right is one searchable list of everything you can place: the documents this project already uses, a universal catalog of standard commissioning documents, and your published script templates. It is not grouped — search it and drag. - Drag an item onto a GROUP CELL (an asset row under a document-group column). The column you drop on decides the group, so the same document can be placed in more than one group. Dropping onto a row that is part of a selection applies to the whole selection; 'select all matching' asks for confirmation first. - Dropping a script template creates a script for each asset in that group. - Placing a document the column doesn't offer yet adds it to the project's document structure, so it requires projects.settings.manage. Placing one the column already has is just a tracker edit. - Add assets inline without leaving the page (requires assets.create). - Click chips to select cells, then Copy them and Paste onto other selected rows, Delete them, or Send to review (requires reviews.create). Before a destructive change is applied, a set-impact dialog summarizes what will be affected so you can confirm safely. ## Who can do what in trackers (permissions) Tracker access is controlled by project role permissions: - trackers.read — view the library and tracker pages. Default: Project Admin, Project Member, Technician. - trackers.create — create trackers. Default: Project Admin, Project Member. - trackers.update — link/unlink documents, set statuses, notes, edit structure, switch the tracker's mode, and unarchive. Default: Project Admin, Project Member. - trackers.delete — archive or delete trackers. Default: Project Admin only. Exporting a tracker and watching it need only trackers.read. Related: Send for review needs reviews.create; the Asset Docs tracker needs assets.read + documents.read to view, assets.update or documents.update to edit, and projects.settings.manage to change its vocabulary. The project owner can always do everything. ## Trackers troubleshooting - Trackers missing from the sidebar: your role lacks trackers.read — ask a project admin. - Can't set a status on a cell: the tracker is in REVIEW mode, where statuses mirror document reviews — send the document for review instead, or switch the tracker to Status mode if that fits better. In Status mode, a cell without a linked document cannot take a status — link one first. - Chips in the Asset Docs tracker look different than before: the project's Asset docs tracking switch (review vs status) was changed on the Review workflows card of the project details page. For a tracker from the library, its own mode was switched. - Can't edit structure or link documents: you need trackers.update (or, in Asset Docs, assets.update / documents.update). - Can't reorder rows: row handles only appear in edit mode with no search or filter active. - A tracker disappeared from the library: it may be archived — turn on the show-archived switch. - The export is missing rows: an export holds at most 5000 rows and follows your current filters — narrow the filters and export in parts. - Not receiving tracker notifications: make sure the bell (watch) toggle is on for that tracker and check Settings > Notifications. Tracker notifications appear in the bell menu only, never by email, and you are not notified about your own changes. --- # My Workspace Cx Assistant help · platform: web · module: workspace · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/web/workspace ## What is My Workspace (personal scope) My Workspace is your personal file area — a private space that belongs to you, not to any project. It holds files you upload through the assistant chat when no project is active, plus anything you store there yourself. When you switch to My Workspace, the whole app runs in "personal scope": project pages are unavailable and the sidebar shows only personal items. Files in My Workspace are visible only to you — no project member or admin can see them. ## How to switch to My Workspace 1. Click the project picker at the top of the sidebar (where your current project name is shown). 2. Choose "Personal" / My Workspace from the list. 3. The app switches to personal scope and you land on your workspace files. Your choice persists — if you close the app while in personal scope, you come back to personal scope next time. No permission is needed; everyone has a personal workspace. ## What is available in personal scope In personal scope the sidebar offers: Home (a welcome page with Create-a-project and Join-a-project shortcuts), My Workspace (your files), Projects, Project drafts, and the Assistant chat. You can also open your Profile, Settings, Feedback, Support, and About pages, join or create projects, and resume project drafts. Project pages — Assets, Issues, RFIs, Documentation, Planner, Trackers, Dashboards, Reviews, and so on — are not available in personal scope. If you try to open one, you are redirected to My Workspace. Switch back to a project to use them. ## Working with files in My Workspace My Workspace uses the same file manager as project Documentation, so everything works the way you already know: - Create folders, upload files or whole folders, and drag & drop to organise. - Search, sort, switch between grid and list views, star favourites, and preview files. - Rename, move, download, and delete items; deleted items go to a trash you can restore from. The only difference is scope: everything here is yours alone. ## Where chat uploads go Files you attach in the assistant chat while no project is active (for example when chatting from personal scope) are stored in a chat folder inside My Workspace. Inside the file manager, the "Chat files" view in the left sidebar lists everything uploaded through the assistant, so you can find, download, or clean up those files at any time. Chat-uploaded attachments are private to you. ## Storage limit for My Workspace My Workspace has a storage limit. A slim Storage meter at the top of the My Workspace page shows the space you have used next to your total, in GB. Hover it to read: "Space used by your personal files and chat uploads." - The bar turns amber once you have used 80% of the space. - The bar turns red when you are over the limit. - The size of the limit is set by the service, not in your settings — the meter always shows your current total. If no limit applies, the meter is not shown. What happens when the space is full: - New uploads are refused with a storage-quota message. Nothing already stored is removed. - Restoring an item from the Trash view can also fail with a storage-quota message, because a restored file counts towards your space again. To free up space: 1. Open My Workspace and find files you no longer need — the Chat files view is a good place to start, and sorting by size helps. 2. Delete them. Deleting frees the space straight away, even while the files are still in the trash. 3. Try your upload or restore again. ## Who can see my workspace files Only you. My Workspace is strictly personal: - Files there never appear to project members, project admins, or anyone else. - They are not part of any project's Documentation. - Files you upload through chat land in your workspace and stay private to you. If you want to share a file with a project team, switch to that project and upload it into the project's Documentation instead. ## How to switch back to a project 1. Click the project picker at the top of the sidebar. 2. Choose the project you want to work in. 3. The app switches back to project scope and all project pages become available again. You can move between projects and your personal workspace as often as you like — nothing is lost when you switch. --- # Assets Cx Assistant help · platform: mobile · module: assets · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/assets ## What is an asset An asset is any equipment, system, or item you track in a project. Assets are the physical or digital objects you manage, inspect, and link to documentation and issues. Examples include UPS units, inverters, sensors, racks, servers, fire panels, or any component that needs tracking, auditing, or maintenance records. ## Opening the Assets screen To reach the Assets screen: 1. Tap the hamburger menu icon (☰) to open the side drawer. 2. Tap Assets in the module list. The header shows the Assets title with a badge showing the total number of assets in the current project. Viewing the asset list requires the assets.read permission — if your project role does not include it, the screen shows a no-access state instead. ## Assets list layout The Assets screen shows: - A floating glass header with the Assets title, the total asset count, the notification bell, and a + button to create an asset (shown when your role has `assets.create`). - A search bar and a Filters button, with removable chips for any active filters. - A scrollable list of asset cards, each with a coloured status bar, the Asset ID, type, category, and current status. When you scroll down, the search and filter row tucks away to give the list more room — scroll up to bring it back. A loading indicator appears at the bottom while more assets load. ## Search assets Tap the search bar and type to search assets. Results update automatically after a short pause (about a third of a second) — there is no separate search button. Clear the search by tapping the X in the search bar or deleting all text. Search and filters can be combined. ## Filter assets by status, type, or category To apply filters: 1. Tap the Filters button next to the search bar. 2. A filter sheet slides up from the bottom. 3. Select one or more values for Status, Type, or Category — all are multi-select. 4. Apply to update the list. Active filters appear as chips below the search bar; tap the × on a chip to remove that filter individually. Filters and search work together. ## Pull to refresh and infinite scroll Drag down from the top of the asset list and release to refresh — this reloads the list from the server to pick up changes made by teammates. The list loads 25 assets per page. When you scroll near the bottom, the next page loads automatically with a small activity indicator. ## Asset card information Each asset card in the list shows: - A coloured left border — the colour reflects the asset's current status. Status colours are defined by your project. - Asset ID — the unique identifier such as UPS-001. - Type and Category — as configured by your project. - The current status label. Tap any card to open the asset detail sheet. ## How to create an asset from the phone You can create an asset from the phone when your role has the `assets.create` permission (Project Admins and Members have it by default). Without it, the + button is not shown. 1. Open Assets and tap the + button at the top right of the header. The Create Asset sheet opens. 2. Type the Asset ID, for example UPS-001 (required). 3. Tap a Type chip (required) and a Category chip (required when the project has categories). The choices are the ones configured for your project. 4. Optionally fill in Model and Description. 5. Optionally tap Location and pick a place from the project's location tree. 6. Optionally choose a Parent asset (see "Parent asset and sub-assets"). 7. Optionally set a Map position: tap Use my position to store where you are standing. For an asset that spans distance, such as a cable route, use Walk this span under Line route. Both are explained in the Map help. 8. Tap Create. You do not choose a status. The "Starts as" tile shows the first status of your project's flow, and every new asset begins there. Vendor and attachments are not part of the create sheet. Open the new asset afterwards to set its vendor or add photos and files. You can also create an asset from the Map with its Add button. The pin you place fills in the Map position for you. ## Parent asset and sub-assets An asset can be a component of another asset — a converter inside a turbine, for example. The outer one is the parent asset, and the ones inside it are its sub-assets. On the phone you choose the parent while creating the asset: 1. In the Create Asset sheet, tap Parent asset. A search panel opens under the field. 2. Type part of the parent's asset ID in the "Search by asset ID…" box. The list shows up to 12 matches, so keep typing to narrow it down. 3. Tap the asset to select it. Tap the × on the field to clear it again. Leaving Parent asset empty is fine — the asset then stands on its own. The asset's detail sheet on the phone does not show the parent, does not list sub-assets, and cannot change the parent. For that, open the asset on the web app: it has a Parent asset field and a Sub-assets card where you can add a sub-asset. One place the parent does matter on the phone: Show on map. A sub-asset with no map position of its own lands on its parent's pin when the parent has one. ## Open and view asset details Tap any asset card to open the asset detail sheet, which slides up from the bottom. It opens in read-only mode first, showing: - Asset ID, type, category, model, and description. - Vendor/company and location (shown as its full location path). - The current status. - A Map position card — the asset's own coordinates, with Use my position, Clear position and Show on map. It appears when you can edit the asset or when there is a position or pin to show. See the Map help for details. - Custom fields, grouped by field group. - An attachments strip. - A linked documents card. - A history feed of changes. Scroll within the sheet to see everything; swipe it down to close. ## Edit asset fields In the asset detail sheet you can edit fields directly (with the right permissions): - Select fields — status, type, category, vendor/company, and location — open a compact picker that slides up inside the sheet. The location picker resolves your choice to its full path. - Text fields — Asset ID, description, and model — use inline editors. Editing requires the assets.update permission. If you created the asset yourself, you can always edit it even without that permission. Changing the status is governed separately (see the status section). ## Change asset status In the asset detail sheet, tap the status field to open the status picker inside the sheet. Important: status transitions follow your project's status flow — only the statuses allowed as next steps from the current status are offered. If a status is not available, the flow does not permit jumping to it directly. Changing status requires the assets.status.update permission (not granted to any role by default — it is assigned via custom roles). If you created the asset yourself, you can change its status without the permission. Every status change is recorded in the asset's history feed. ## Custom fields on assets Projects can define custom technical fields for assets — for example IP address, serial number, or firmware version. In the asset detail sheet these appear grouped by their field group. Values are read-only unless you can edit the asset: editing custom/technical fields follows the same rule as the other fields (assets.update, which Project Admins and Members hold, or being the creator of the asset). ## Asset attachments The asset detail sheet includes an attachments strip where you can: - Add attachments to the asset. - Tap an attachment to preview it. - Remove an attachment. Use attachments for photos of the installed equipment, nameplates, or other supporting files. Adding or removing attachments follows the same edit access as the asset itself. ## Documents linked to an asset Assets can have documents linked to them. In the asset detail sheet, the linked documents card lists the documents associated with this asset. Tap a linked document to view it in the document viewer. Managing document links is done from the web app — on mobile you can view them. ## Asset history feed The asset detail sheet includes a history feed — a timeline of changes made to the asset, such as status changes and field edits, with who made each change and when. Use it to audit how an asset reached its current state. ## Who can view and edit assets Asset access is controlled per project by your role: - View the asset list and details: assets.read (all built-in roles have it by default). - Create assets: assets.create (Project Admins and Members by default). - Edit asset fields: assets.update (Project Admins and Members by default). - Change status: assets.update or assets.status.update (Project Admins and Members by default). - Edit custom/technical fields: same as other fields (assets.update, or being the creator of the asset) Exception: if you created an asset, you can edit it and change its status even without the update permissions. The project owner can always do everything. If you lack access, ask a project admin to adjust your role. ## No permission to view assets If the Assets screen shows a no-access state, your project role does not include the assets.read permission. Contact a project admin to request access. ## No project — empty state If you have not joined a project yet, the Assets screen shows a "No project joined yet" state with a "Join with invite code" button. Tap it to enter an 8-character invite code and gain access to a project. If you switched to My Workspace, the screen says "You're in My Workspace" instead, with a Select project button that opens the drawer so you can switch back to a project. ## Assets not loading — troubleshooting If the asset list shows an error or stays empty: 1. Pull down to refresh the list. 2. Check your internet connection. 3. Switch between Wi-Fi and mobile data if one is unavailable. 4. Close and reopen the app. 5. If the problem persists, contact support from Profile → Support. --- # Chat — AI assistant Cx Assistant help · platform: mobile · module: chat · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/mobile/chat ## The assistant is your home screen The AI assistant chat is the first screen you see after signing in. Ask it anything about your active project — issues, assets, documents, the planner, RFIs — in plain language, and it looks the data up for you and answers with sources. You can return to chat at any time from the drawer (hamburger icon or swipe right from the left edge), and your past conversations are always available in the drawer's chat history. ## The chat header — project chip, new chat, and badge The chat header has four controls: - Left: the menu chip opens the drawer. - Centre: the project chip shows your active project's name. Tap it to open the project picker and switch projects, or to join one with an invite code. It reads "My Workspace" while you are in your personal workspace. - Right: the bell opens your notifications; it carries a badge with your unseen notification count. - Far right: the compose icon starts a new chat. Until you join your first project, an onboarding banner guides you to join one. ## How to choose which assistant answers Cx Assistant has several assistants, each focused on one kind of work. You pick one when you start a chat. 1. Start a new chat with the compose icon in the header. 2. In the toolbar under the message box, tap the chip that shows the current assistant's name (next to the + button). 3. The "Choose assistant" sheet opens. Each row shows the assistant's name, a short description, and a "Default" or "Beta" chip where it applies. 4. Tap the ⓘ icon on a row ("About this assistant") to see its card: "What it can do", "What it can't do", "Try asking" examples, and "Available on". Tap back to return to the list. 5. Tap a row to select it, then send your first message. The assistant is fixed for the whole conversation. The chip only shows on a new, empty chat — to switch assistants, start a new chat. If you see no chip, only one assistant is available to you there. A warning icon next to a name means that assistant can make changes that cannot be undone, such as removing members or locations. ## The assistants you can choose from Inside a project, the "Choose assistant" sheet lists: - Commissioning Assistant (Default) — works with this project's issues, assets, documents and scripts, draws and edits 3D layouts, reads CAD drawings and administers the project (sets and statuses, members, locations, workflows and settings) — each of those as far as your role allows. - General Assistant — engineering knowledge, web search and your own files; no project workflows. In My Workspace the sheet lists the My Workspace Assistant (Default) — your personal files, engineering knowledge and web search, no project data — and the General Assistant. Before you join a project it lists Getting Started (Default), which creates your first project and guides you through the platform, and the General Assistant. Building dashboards in chat is only available in the web app. Every assistant works with your own permissions: the Commissioning Assistant only draws layouts or administers the project for people whose role grants it (the layouts and project administration permissions, granted to project admins by default), and every change it makes is checked like a change you would make yourself. ## Asking a question — streaming replies and stopping Type your question in the composer and send it. The reply streams in live, word by word, with a status chip and typing indicator showing what the assistant is doing. While the assistant is answering, the Send button becomes a Stop button — tap it to stop generation immediately if you already have what you need or want to rephrase. ## Tool chips, thoughts, and sources — seeing how the answer was built While answering, the assistant may use tools to look things up in your project. Each tool call appears as a chip with a live label describing what it's doing, and you can see its result. You can also expand the thoughts panel to read the assistant's reasoning, and a sources list under the answer shows where the information came from, with inline citation chips in the text itself. ## Opening citations — documents, issues, and assets in place Answers cite their sources. Tap a citation chip to open the source without leaving the chat: - Document citations open the document viewer. - Issue citations open the issue's detail sheet right there. - Asset citations open the asset's detail sheet right there. This lets you verify any claim the assistant makes in one tap. ## Approvals: control what the assistant may change You decide how much the assistant can do on its own. The approval mode chip is in the toolbar under the message box, with a shield icon and the current mode's name. Tap it to choose: - Auto — the assistant runs all actions without asking. This is the default. - Ask for critical — only critical actions (permanent deletions, member removal) ask first. - Ask for edits — every action that changes project data asks first. The mode is remembered per chat. Reading data never requires approval — only changes do. A few actions ask in every mode, Auto included: creating a project, adding a company to the company directory, deleting a planner activity, and anything a connected service sends on your behalf, such as an email or a meeting invitation. For those, the card shows the full details — recipients, subject and message — so you can read exactly what will be sent. Connected services are set up in the web app, in Settings → Connections. Deleting a planner activity: the assistant can remove an activity from the planner when you ask, in the Commissioning Assistant. It always asks first — the card names the activity and warns that everything under it goes too — and it needs the planner.delete permission, like deleting it yourself. ## How to answer an approval card When the assistant needs your go-ahead, it pauses and an "Approval required" card appears in the conversation. You answer it right on the phone. It lists each action the assistant wants to run, with a checkbox per row. 1. Read each row. The title says what will happen; the lines below show the details. Long text, such as an email body, folds — tap "Show more" to read all of it. 2. Untick any action you do not want. 3. Tap Approve to run the ticked actions (the button reads "Approve 2" when only some are ticked), or Decline all to run none. 4. Optional: before approving, tick "Don't ask again for … in this chat" so that kind of action stops asking for the rest of the conversation. Critical actions never offer this. Declined actions show as "Declined" and the assistant carries on without them. If you send a new message instead of answering the card, the waiting actions are dropped and do not run. If you are not looking at the chat when the assistant stops for approval, you get a notification: "The assistant is waiting for your approval". Tap it to open the chat. ## The Tasks list: follow a long job step by step For a job with several steps, the assistant writes itself a task list and shows it to you. A card titled "Tasks" appears just above the message box. - The header shows progress as done/total, for example 2/5. - A pulsing dot marks the task the assistant is working on right now (In progress). - An empty circle is a task still to do (Pending). - A green tick is a finished task (Completed). Tap the header arrow to collapse or expand the list. The card disappears by itself once every task is completed. The list is the assistant's own plan — you do not edit it; to change course, send a new message. ## Research agents: helpers that read in the background When a question needs a lot of reading — many documents, long reports, several topics at once — the assistant can hand parts of that reading to research agents and write its answer from their reports. A research agent only reads; it never changes anything. (This needs an up-to-date version of the app.) The agents work in the background: the assistant keeps working on the rest of your request while they read, and it can start several for one message. If it has nothing left to do but wait, it may send a short first message and then continue the answer once the reports are in. Each agent is one compact row in the conversation: - The row reads "Agent (Researcher)" and a short description of the job, with its state on the line below. - While the agent works in the background, its icon pulses and the row says "background task". - When the assistant is waiting for the agent, the row says "running" with the time so far. - When the agent ends, the row shows the steps it took, the time and the tokens it used, for example "5 steps · 41s · 2.4k tokens". A warning icon with Stopped, Timed out, Ran out of steps or Failed means it could not finish. Tap a row to open its card underneath, with the steps the agent took. On the card, tap "Open thread" to open the "Research thread" sheet with the Briefing the assistant gave, the Steps taken and the final Report. Limits: the assistant can start up to 9 research agents for one message, and three of them work at a time — the others wait their turn. Once the limit is reached, the assistant does the rest of the reading itself. Stopping the answer also stops the agents that are still running. You do not need to do anything — the rows are there so you can see where the answer came from. ## Documents the assistant writes: Word, PDF and exact-layout sheets Ask the assistant to write a document and it saves a real file in your files, with a preview and versions like any other document. There are two kinds: - Reports, minutes, memos and other flowing text. The assistant writes the text and saves it as a Word document (the default, editable), a PDF or a Markdown file. Say which format you want. - Exact-layout sheets, for when the layout itself is the point: a client's form or checklist reproduced from its original, a one-page test sheet, a certificate or cover with a logo in a corner, tables with merged cells and shaded bands. The assistant lays the page out itself (it writes it as an HTML page) and saves it as a PDF. Nothing is added to such a page — no cover, no logo, no footer — unless you ask for it. Getting a good exact-layout sheet: - Attach the original form, or name the document to copy. The page is A4 unless you say otherwise. - Logos and pictures must be images in your files or attached to your message — the assistant cannot take a picture from a web address. It can cut a logo or a figure out of a page of one of your documents, save it as an image, and place it on the sheet. - The assistant looks at the finished pages and the page count itself. Ask for corrections in plain words ("move the logo to the top right", "keep it on one page"): each correction saves a new version of the same file, not another file. Where it goes: the folder you name, or your own Chat files when you name none. Creating a document is a change, so it follows your approval mode, and it needs the documents.create permission in a project. The Commissioning, Project Management and My Workspace assistants can write documents. ## Leaving a chat while the assistant works — background work and notifications You do not have to wait on the chat screen. If you open another chat, go to another screen, or put the phone away while the assistant is working, it keeps going and the finished answer is waiting when you come back. (This needs an up-to-date version of the app.) You can have the assistant working in up to 3 chats at the same time — start a long task in one chat, then start a new chat and ask something else. Each chat works on one request at a time. In the drawer's chat history, a dot next to a chat shows its state: - Pulsing dot — the assistant is working in that chat. - Green dot — finished, with an answer you have not seen yet. - Amber dot — waiting for your approval. - Red dot — stopped with a problem. Opening the chat clears its dot. When an answer finishes in a chat you are not looking at, you get a notification: "The assistant finished answering". With the app closed or in the background it arrives as a push notification; tap it to open that chat. The first time you walk away from a working chat, the app asks "Get notified when it's ready?". Tap "Turn on" and then allow notifications in the system prompt. "Not now" is fine too — the offer is made only once, and you can turn notifications on later from the notification settings in the app. ## Long conversations — the context ring and summaries Every chat has a limit on how much the assistant can keep in its working memory at once. The small ring next to the message box shows how much of that memory the conversation is using; it fills as the conversation grows. When a conversation gets close to the limit, the assistant summarizes the older part of it and continues from that summary, so you can keep working in the same chat (needs an up-to-date version of the app). This can take a minute or two — the status line says "Summarizing earlier conversation…" while it happens. A thin line saying "Earlier conversation summarized" then appears in the transcript, and the ring drops. Nothing you wrote is removed: every message stays above the line for you to read; only what the assistant keeps in memory changes. Tap "View summary" on the line to read what the assistant continues from. Summaries keep record ids, decisions, open tasks and the exact next step, but fine detail from early in the conversation may be condensed. For a new topic, a new chat is still the cleanest start. ## Sending a message with a weak connection — "Your message was not sent" If the connection drops for a moment while you write, you can still tap Send. The app holds your message and sends it by itself as soon as the connection is back — you do not need to retype it. There is one exception. If, while you were offline, you moved to a different chat, the app does not post the held message into the wrong conversation. It removes the message from the screen and shows an alert: "Your message was not sent. The connection dropped while you were writing it and that chat is no longer the one open. Open the chat and send it again." When you see that alert, open the chat you were writing in from the drawer's chat history and send the message again. ## How to create a project from the chat You can set up a new project by asking for it — also before you have joined any project. 1. Open the chat and ask, for example: "Create a project called Riverside Data Center for Acme". 2. Give the two things the assistant needs: the project name and the client company. The project code is optional — a short one is made from the name if you do not give one. You can also ask which project templates exist and pick one. 3. An "Approval required" card appears with the project name, code and client. Creating a project always asks, whatever your approval mode. Tap Approve. 4. A "Project created" card appears. Tap Open to switch to the new project. You become the owner of the new project. If the client company is not in the company directory yet, the assistant tells you and asks before adding it. This works with the Getting Started, Commissioning, Full, Project Management, My Workspace and General assistants. ## Attaching photos and files to your message Tap the + button in the composer to attach context to your question: - Take photo — use the camera. - Photo library — pick images from your phone. - Document — pick a file from your phone. - Project documents (or My Files in My Workspace) — browse the documents already in the app and attach files, or a whole folder, without uploading them again. - Paste image — shown when you have copied an image. You can attach images (JPG, PNG, GIF, WEBP, HEIC), PDFs, and Office or text documents (Word, Excel, PowerPoint, TXT, CSV). Limits: up to 10 files per message, 60 MB per file. Videos cannot be attached from the phone — use the web app for those. Attachments appear as a thumbnail strip above the input with upload progress. If an upload fails you get an error with a retry option, and each chip has a remove control. If a file is refused, a message tells you why. Send your message and the assistant can read the attachments. ## Voice dictation — talk instead of typing When the input is empty, a microphone button appears in the composer. Tap it to dictate: - The button pulses red while the app is listening. - Your words appear as a live transcript merged into the input, so you can keep editing by hand. - Dictation follows the app's language, set in Profile. Tap again to stop listening, review the text, and send. ## Thinking mode — deeper answers for harder questions The composer has a thinking-mode selector with four settings: - Non-thinking — fast, direct answers for everyday questions. - Thinking · Low — brief reasoning; quick answers with a sanity check. This is the default and the recommended setting. - Thinking · Medium — balanced reasoning for complex tasks. - Thinking · High — the deepest reasoning; thorough analysis for hard, multi-step problems, at the cost of a slower reply. The setting applies per message, so you can raise it for one hard question and drop back down afterwards. A context-usage donut next to the composer shows how much of the conversation's capacity is used — start a new chat if it fills up. ## Mentioning members with @ and assets with # While typing, two shortcuts bring project context into your message: - Type @ to get an autocomplete of project members and mention one. - Type # to get an autocomplete of assets and reference one directly. Pick from the suggestion list that appears above the input. References give the assistant an exact anchor, so answers about that person or asset are precise. ## Copy, feedback, and regenerate Under each assistant message you'll find: - Copy — copies the message text (a brief "Copied" confirmation appears). - Thumbs up / thumbs down — rate the answer to help improve the assistant. - Regenerate — available on eligible messages; asks the assistant to produce a fresh answer to the same question. ## Chat history — finding past conversations Open the drawer (hamburger icon or swipe right from the left edge) to see your chat history below the module list. The active chat is highlighted; tap any conversation to reopen it, and scroll down to load older ones. The New chat button at the top of the history starts a fresh conversation. Inside a long conversation, scroll up to load older messages; a floating "Jump to latest" chip returns you to the newest message. ## Quick prompts on a new chat When a conversation is empty, suggestion chips with quick prompts appear above the composer. Tap one to send it as your question — a fast way to see what the assistant can do or to kick off common requests without typing. ## The assistant respects your permissions The assistant works with the same access you have. It answers from the active project shown in the header's project chip, and it can only read and change what your own project role allows — it never bypasses permissions to reach data you couldn't open yourself. Chat itself needs no special permission; anyone signed in can use it. ## Chat not responding — troubleshooting If the assistant misbehaves: - Reply stalls or errors — tap Stop if it's still running, then resend, or tap Regenerate under the failed answer. Check your internet connection. - Answers reference the wrong project — check the project chip in the header and switch to the right project. - Attachment stuck — use the retry control on the failed chip, or remove and re-attach it. A file is refused when it is over 60 MB, is a type the chat cannot read, or is the 11th file in one message. - The assistant seems to be waiting and nothing happens — look for an "Approval required" card in the conversation (an amber dot in the chat history marks it). It is waiting for your answer. - Actions keep asking for approval — the approval mode chip under the message box may be on "Ask for edits". Switch it to Auto or "Ask for critical". A few actions (creating a project, sending an email through a connected service) always ask. - An alert says "Your message was not sent" — the connection dropped and you had moved to another chat. Open the chat you were writing in and send it again. - You cannot find the assistant chip — it only shows on a new, empty chat, and only when more than one assistant is available to you. Start a new chat to switch. - No notification when an answer is ready — turn notifications on in the app's notification settings, and check that your phone's system settings allow notifications for Cx Assistant. - Dictation not working — make sure the app has microphone permission in your phone's system settings, and note the mic button only appears while the input is empty. - Long conversation getting slow or the context donut is full — start a new chat with the compose icon. - Still stuck — close and reopen the app, and contact support from Profile → Support if the problem persists. --- # Documents Cx Assistant help · platform: mobile · module: documents · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/documents ## What are documents The Documents section stores files and folders for your project. It is organized as a folder tree where you can upload files, group them into folders, and keep a version history of each document. Documents can be linked to assets as supporting evidence. This is the central file repository for your project — think of it as a structured drive shared across your team. ## Opening the Documents screen To reach the Documents screen: 1. Tap the hamburger menu icon (☰) to open the side drawer. 2. Tap Documents in the module list. The screen opens at the root level of the project's document tree. Viewing documents requires the documents.read permission. In My Workspace (pick it in the project switcher at the top of the drawer), Documents opens your personal files instead — the same files you see under My Files on the web app. ## Documents screen layout The Documents screen shows: - A header with the Documents title and controls. - A breadcrumb trail showing your current folder path. - A search bar for searching across the whole project. - A sort control (opens a sort sheet) and a list ⇄ grid view toggle. - The folders and files of the current folder. - Actions to create a folder and upload a file. Each item also has an actions menu (⋯, or long-press the item) with Open, Version history, Rename, and Delete — depending on your permissions. ## Navigating folders — breadcrumbs and the back button The document tree works like a file system: - Tap a folder to enter it. The breadcrumb trail at the top updates to show your current path. - Tap any breadcrumb segment to jump back up to that folder level; tap the leftmost segment for the root. On Android, the hardware back button first walks UP the folder tree one level at a time — it only leaves the Documents screen once you are at the root. ## Search documents Tap the search bar and type to search across the whole project's documents — all folders, not just the current one. Results update automatically after a short pause and show up to 50 matches. While searching, folder navigation is replaced by the results list. Clear the search (tap the X or delete the text) to return to normal folder browsing. If you expect a file that is not in the results, refine your search terms — only the first 50 matches are shown. ## Sort documents Tap the sort control to open the sort sheet. You can sort by: - Name - Kind - Last updated Each in ascending or descending order. Folders always group first, before files, regardless of the sort you pick. ## List view and grid view Toggle between List and Grid view with the view mode button. - List view shows one item per row with details at a glance. - Grid view shows items as tiles — useful for visual browsing. The number of grid columns adapts to your screen width, so tablets show more tiles per row. Your choice is remembered — the app reopens Documents in the view you last used. ## Create a new folder To create a folder in the current location: 1. Tap the create-folder action. 2. A dialog asks for a folder name. 3. Type the name and confirm. Folders help organise documents by phase, discipline, or asset type. Creating folders requires the documents.create permission. ## Upload a document To upload a file to the current folder: 1. Tap the upload action. 2. The device file picker opens — select a file (one file per upload). 3. The upload starts immediately and shows a live progress percentage. 4. When it finishes, a completion alert confirms the upload and the file appears in the folder. You can pick files from Files, iCloud, Google Drive, or other document providers on your device. Uploading requires the documents.create permission. ## Document and folder actions (rename, delete, versions) Every document and folder has an actions sheet. Open it by tapping the ⋯ button on the item, or by long-pressing the item. Depending on your permissions, the sheet offers: - Open / Preview — view the file. - Version history — see and open previous versions. - Rename — change the item's name (requires documents.update). - Delete — remove the item, with a confirmation prompt (requires documents.delete). Rows you do not have permission for are simply not shown. ## Document versions Documents keep a version history: each new upload to the same document becomes the latest version, and previous versions are retained. To view versions: 1. Open the item's actions sheet (⋯ or long-press) and choose Version history. 2. The versions sheet lists versions with their file size and timestamp, loading 20 at a time as you scroll. 3. Tap a version to open it in the viewer. Versioning gives you an audit trail of what was submitted and when. ## Open and view a document Tap any document (not a folder) to open it full-screen: - Images open in the built-in viewer with pinch-to-zoom. - PDFs open in an in-app viewer on iOS; on Android they open in your device's system viewer. If the document has no uploaded file yet, you will see a message that there are no versions to view. ## Item moved to Trash by someone else Documents are shared, so a teammate may move an item to the Trash while you are looking at the same folder. If you try to open something that was just trashed elsewhere, the app shows a message that the item was moved to Trash and refreshes the list. This is normal — pull down to refresh if you want to re-sync the folder at any time. Restoring items from the Trash is done on the web app. ## Pull to refresh Drag down from the top of the document list and release to refresh. This reloads the current folder from the server to pick up changes made by other team members. ## Who can do what in Documents Document access is controlled per project by your role: - View and open documents: documents.read (all built-in roles by default). - Create folders and upload files: documents.create (Project Admins and Members by default). - Rename or move items: documents.update (Project Admins and Members by default). - Delete items: documents.delete (Project Admins by default). Actions you lack permission for are hidden from the actions sheet. The project owner can always do everything. If you need more access, ask a project admin to adjust your role. ## No project — empty state Until you join a project you are in My Workspace, and Documents shows your personal files. To work with a team's documents, join their project: open the drawer and tap Join project, then enter the 8-character invite code. If the screen shows "No project joined yet" instead, tap "Join with invite code". ## Documents not loading — troubleshooting If the document list shows an error or fails to load: 1. Pull down to refresh. 2. Check your internet connection. 3. Try switching from Wi-Fi to mobile data or vice versa. 4. Close and reopen the app. 5. If the issue persists, contact support from Profile → Support. --- # Home — project insights Cx Assistant help · platform: mobile · module: home · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/home ## What is the Home insights screen Home gives you a read-only overview of the active project's health at a glance. Open the drawer (hamburger icon or swipe right from the left edge) and tap Home. The screen shows four KPI tiles — Total assets, Completion rate (%), Open issues, and Total issues — followed by three charts: - Issue velocity — a cumulative weekly chart of issues created vs closed. - Issues by priority — horizontal bars. - Asset status distribution — a bar showing how assets split across statuses. Everything on Home is view-only; you cannot edit data from this screen. ## Choosing the chart colours — app palette vs project status colours Tap the ⋯ button in the Home header to choose where chart colours come from: - App palette (default) — the app's own consistent colour set. - Project status colours — the colours your project defines for its statuses. Your choice is remembered between sessions. ## Refreshing the insights Drag down from the top of the Home screen and release to refresh. This reloads the KPI tiles and all three charts with the latest project data. ## No project yet — empty state If you have not joined a project, Home shows a "No project joined yet" state with a "Join with invite code" button. Tap it to enter an 8-character invite code and join. Once you are in a project, the tiles and charts fill with its data. Home belongs to a project. In My Workspace, and until you join your first project, the drawer has no Home row. If Home is open when you switch to My Workspace, it says "You're in My Workspace" with a Select project button that opens the drawer so you can switch back to a project. ## Drilling into the numbers — use the web app The mobile Home screen is a summary. Drill-downs — clicking into a KPI or chart segment to see the underlying items — are available on the web app's Home page. On the phone, use the Issues and Assets screens with their search and filters to inspect specific items. ## Who can see Home insights — permissions Viewing Home requires home.view, which all built-in roles (Project Admin, Project Member, Technician) have by default. Everyone who can open Home sees the same statistics; there is no separate permission for them. The project owner can always see everything. If Home is missing for you, ask a project admin to check that your role has `home.view`. --- # Issues Cx Assistant help · platform: mobile · module: issues · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/issues ## What is an issue An issue is a trackable problem, task, or question related to your project assets or work. Each issue has a title, description, status, priority, type, and optional assignee. Issues help your team capture what needs attention, route it to the right person, and track progress until it is resolved. Think of an issue as a single, well-scoped item you can discuss, update, and close when done. ## Opening the Issues screen To reach the Issues screen: 1. Tap the hamburger menu icon (☰) to open the side drawer. 2. Tap Issues in the module list. The screen shows all issues for your active project, with a badge in the header showing the total count. ## Issues list layout The Issues screen shows: - A floating glass header with the Issues title, the total issue count, and a + button to create a new issue. - A search bar and a Filters button, with removable chips for any active filters. - A scrollable list of issue cards, each showing the status colour, title, status label, priority, type, and assignee. When you scroll down, the search and filter row tucks away automatically to give the list more room — scroll back up to bring it back. A loading indicator appears at the bottom while more issues load. ## Search issues Tap the search bar at the top of the Issues screen and start typing. Results update automatically after a short pause (about a third of a second) — there is no separate search button. To clear the search, tap the X inside the search bar or delete all text. Search and filters can be combined. ## Filter and sort issues To narrow or reorder the issue list: 1. Tap the Filters button next to the search bar. 2. A filter sheet slides up from the bottom. 3. Select values for Status, Priority, Type, Assigned to, or Created by — all are multi-select. 4. Choose a sort option in the same sheet to change the list order. 5. Apply to see the results. Active filters appear as chips below the search bar. Tap the × on a chip to remove that filter individually. ## Pull to refresh and infinite scroll Drag down from the top of the issue list and release to refresh — this reloads issues from the server to pick up changes made by teammates. The list loads 25 issues at a time. As you scroll near the bottom, the next page loads automatically with a small loading indicator. ## Create a new issue Step-by-step: 1. Tap the + button in the Issues screen header. 2. A Create Issue sheet slides up. 3. Fill in the Title (required) — keep it short and specific, for example 'UPS inverter overtemperature'. 4. Add a Description with context, symptoms, or expected behaviour. 5. Select a Priority and a Type from your project's configured options. 6. Optionally assign the issue using the assignee picker. 7. Optionally tap the Location row and pick where the problem is from your project's location tree. 8. Tap Create. The issue appears in the list immediately after creation. ## Create issue field guidance Title: Required. Keep it brief and specific. Avoid vague names like 'Problem' — use 'Cooling fan failure in Rack B3' instead. Description: Optional but strongly recommended. Add symptoms, steps to reproduce, or background context. Priority: Choose based on urgency or risk. Use a higher priority for safety or production-blocking issues. Type: Pick the category that best fits. Types are configured per project. Assignee: Select the team member responsible. Unassigned issues can be harder to track. Location: Optional. Pick the site, building, room or other place from the project's location tree, so the team knows where to go. It reads "Select location (optional)" until you choose one. ## Open and view an issue Tap any issue card in the list to open the issue detail sheet. It slides up from the bottom and opens in read-only mode first, showing all fields, the attachments, the comments, and the history feed. Scroll within the sheet to see everything; swipe it down to close. You can also land directly on an issue by tapping an issue notification (in the app's Notifications inbox or a push notification) — the app opens the Issues screen with that issue's sheet already open. ## Edit issue title and description In the issue detail sheet, tap the Title or Description to open its inline editor. You can edit both fields and then confirm them together with a single Save — changes are not sent until you save. Saved changes are recorded in the issue history feed so your team can see what was updated and when. ## Change status, priority, type, or assignee In the issue detail sheet, tap the Status, Priority, Type, or Assignee field. A compact picker slides up inside the sheet — choose a value and it is applied. Statuses, priorities, and types are defined by your project (a typical status flow might look like Open → In Progress → Resolved → Closed, but your project may use different names). Every change is recorded in the issue history feed. Assigning ensures someone is accountable; to reassign, simply tap the Assignee field again and pick a different member. ## Set a due date Every issue can carry a due date — the date it should be fixed by. When creating an issue, tap the Due date row to open the calendar and pick a day; leave it empty for no deadline. In the issue detail sheet, tap the Due date field to change it, or use Clear in the calendar to remove it. When the date passes and the issue is still open, the field turns red with an Overdue marker, and the issue row in the list shows a small clock icon. Use the "Due date — soonest first" sort to see what is due next. Closed issues are never shown as overdue. The assignee (or the creator, when unassigned) gets an Issue overdue notification the day it slips; tapping it opens the issue. Tune the channels in Settings → Notifications. ## How to set an issue's location and show it on the map Every issue can carry a location — a place from your project's location tree, such as a site, building, floor or room. How to set or change it: 1. When creating an issue, tap the Location row. In an existing issue, open it and tap the Location field. 2. The Select location picker slides up inside the sheet. Browse the tree, or type in the search box to find a place by name, code or path. 3. Tap a location. In an existing issue the change is saved straight away. Tap "— No location" to clear it. The field shows the full path, for example Site A > Building 2 > Room 104. If the picker says "No locations configured for this project.", a project admin has to set up the locations on the web app first. Show on map: when the Map module is on for the project, an open issue can show a Show on map row under its fields. It appears when the issue's location, or a place above it in the tree, has a pin on the map. If not, it uses the first linked asset that has a pin. Tap the row to open the Map on that pin. When there is no pin to land on, the row is not shown. See the Map help for what you can do from there. ## Add attachments to an issue The issue detail sheet has an attachments area where you can attach evidence to the issue: 1. Tap the add-attachment control. 2. Choose the source: take a photo with the camera, pick from your photo library, or pick a file. 3. The attachment uploads and appears in the strip. Tap an attachment to preview it, or use its remove control to delete it from the issue. ## Add a comment to an issue Comments live in the issue detail sheet: 1. Scroll to the comment area. 2. Tap the comment input and type your message. 3. Send it. Comments appear in the issue's history feed alongside other changes, and relevant team members are notified. Commenting is covered by the issues.comment permission, which all built-in roles have by default. ## Issue history feed The history feed in the issue detail sheet shows a timeline of everything that happened on the issue: status changes, field edits, assignee changes, and comments — each with who did it and when. Use the history filters to focus on one kind of entry: All, Comments, Status, Assignee, or Fields. ## Delete an issue To delete an issue: 1. Open the issue detail sheet. 2. Tap the Delete action. 3. Confirm in the prompt — deletion cannot be undone. Deleting issues requires the issues.delete permission, held by Project Admins by default. If the server rejects the deletion, your role does not include it — ask a project admin. ## Opening an issue from a notification When you are notified about an issue — for example when it is assigned to you or someone comments on it — tapping the notification takes you straight to it: - Tapping a row in the Notifications inbox opens the Issues screen with that issue's detail sheet already open. - Tapping a push notification does the same, even when the app was fully closed. If the issue belongs to a different project than your active one, the app switches projects first, then opens the issue. ## Who can edit issues — how permissions work On mobile, the issue editing controls are always shown — the server checks your permissions when you save. If a change is rejected, your project role does not allow it. How issue permissions work: - Viewing, creating, updating, and commenting (issues.read, issues.create, issues.update, issues.comment) are granted to all built-in roles by default. - Changing status (issues.status.update) is granted to Project Admins and Members by default. - Deleting (issues.delete) is Project Admin only by default. Regardless of role, the issue's creator, its assignee, and members of an assigned group can always edit the issue and change its status. The project owner can always do everything. If an action keeps failing, ask a project admin to adjust your role. ## No project — empty state If you have not joined any project yet, the Issues screen shows a "No project joined yet" state with a "Join with invite code" button. Tap it to enter an 8-character invite code and join a project. Until you join one, the drawer shows only Chat and Documents. If you switched to My Workspace, the screen says "You're in My Workspace" instead, with a Select project button that opens the drawer so you can switch back to a project. If you are waiting to be added, ask a project admin to send you an invite code. --- # Layouts Cx Assistant help · platform: mobile · module: layouts · updated 2026-09-10 Canonical: https://cx-assistant.com/en/help/mobile/layouts ## What are layouts on mobile A layout is an interactive 3D plan of your site: the walls and rooms, the equipment placed on it, the cable trays, pipes and conductors that connect it, and the issues pinned exactly where they are in the field. On the phone you open the same 3D scene the web editor shows, walk around it with your fingers, see the live status of every linked asset, and pin issues from where you stand. Drawing walls, placing equipment and routing services by hand stay on the web app; on the phone you view the plan and work with issue pins — or pick the Layout Builder assistant in chat, describe the plan (or photograph a drawing) and watch it appear in the viewer. Open Layouts from the drawer. It appears only when the Layouts module is on for the project, and viewing requires the layouts.read permission. Every layout has a number (LY-1, LY-2, …) shown on its card and in the viewer header. ## The layouts list and creating a layout from the phone The Layouts screen lists every layout of the project as a card: its LY-number, name and description, chips with what it contains (walls, objects, rooms, issue pins and routes) and when it was last updated. Pull down to refresh. Tap a card to open it in 3D. The + button in the header (requires layouts.create) creates an empty layout with a name and an optional description. The phone cannot draw walls or place equipment by hand — create it here, then draw it on the web or ask the Layout Builder assistant in chat to build it ("build a layout of the switchroom with two transformers and a busbar"). The new layout opens in the viewer right away and fills in live as the assistant works; the "Layout created — Open" card in chat takes you straight to it. ## Moving around the 3D plan The viewer fills the screen. Drag with one finger to orbit around the plan, pinch to zoom, and drag with two fingers to pan. The buttons on the right switch views: Top view looks straight down like a drawing, 3D view returns to the angled overview, and Fit re-frames the whole plan from wherever you are looking. Lower walls cuts every wall to about a metre so you can see inside a building from any angle; tap it again to restore full height. The back chip in the header returns to the list. The plan keeps drawing only while the screen is in front of you — it pauses when you switch screens or background the app, so it costs no battery in your pocket. ## Status markers, issue pins and layers Equipment linked to an asset carries a floating gem above it in the asset's status colour, so a glance at the plan tells you what is commissioned, in progress or blocked. Issues pinned on the plan show as map pins with a pulsing ring, coloured by the issue's status. Colours come from the project's own status sets. The Layers button in the header opens switches for what is drawn: asset status markers, asset ID labels under them, issue pins, room areas, routes (trays, pipes, conductors) and X-ray walls, which makes every wall see-through. Layers are a display choice — they change nothing in the layout. ## Tapping equipment, pins, rooms and routes Tap any element to select it — a card slides up from the bottom. For linked equipment the card shows the asset tag, its status and Open asset, which opens the same asset sheet as the Assets screen. For an issue pin it shows the issue number, title, status and priority, with Open issue for the full issue (comments, attachments, status changes). Rooms show their name and linked location; routes show their label and system. Tap empty ground, or the ✕ on the card, to deselect. A tap only counts when your finger stays put — letting go after orbiting the camera over an object does not open it. ## Pinning an issue from the field (add, move, remove) With layouts.update you can place issue pins from the phone. Tap Pin issue at the bottom left, pick the issue from the list (search by title) or tap New issue to create one on the spot, then tap the place on the plan where it is. The pin is saved immediately — there is no separate Save step on the phone. From a piece of equipment's card, Pin an issue here does the same but drops the pin at that equipment. From a pin's card, Move pin lets you tap the new spot, and Remove pin takes the marker off the plan — the issue itself is untouched. Pins created on the phone appear on the web editor within a second, and vice versa. ## Live updates and working alongside the assistant The viewer listens for changes while it is open: when the assistant adds equipment from a chat, when someone edits the plan on the web, or when an issue or asset changes status, the scene and its colours refresh on their own — no need to leave and come back. Opening a freshly created layout and asking the assistant to build it is a good way to watch a plan appear on your phone. ## Layouts troubleshooting on mobile "Layouts are off for this project": a project admin can switch the Layouts module on from the project settings on the web. "You don't have permission": you need layouts.read; pinning needs layouts.update. Ask a project admin. "This device can't show 3D layouts": the phone's browser engine has no WebGL, which is very rare on supported devices. Restart the app, and if it persists open the layout on the web. The plan looks empty: the layout may be new — the cards on the list show what each contains. Layers can also hide things: open Layers and make sure issue pins and routes are on. PDF underlays (a drawing traced under the plan on the web) are not shown on the phone. --- # Sign in & Authentication Cx Assistant help · platform: mobile · module: login · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/login ## How to sign in Step-by-step: 1. Open the CX Assistant app. 2. Enter your email address in the Email field. 3. Enter your password in the Password field. 4. Tap Sign in. If your credentials are correct you will be taken directly to the app (the Chat screen). If two-factor authentication is enabled on your account, you will first see a verification screen where you enter a code. If your email is not yet confirmed, you will be redirected to a Confirm Email screen instead. ## Remember email Below the password field you will find a Remember email toggle. When enabled, the app stores your email address locally so it is pre-filled the next time you open the sign-in screen — you only need to type your password. To turn it off, simply disable the toggle on the sign-in screen. Your stored email will be removed from the device. Only enable Remember email on devices that only you use. ## Show or hide password Tap the eye icon on the right side of the Password field to reveal your password as plain text. Tap it again to hide it. This helps you verify what you typed before submitting, especially on a small mobile keyboard. ## Caps Lock warning If Caps Lock is active while you type in the password field (for example when using a hardware keyboard on a tablet), the app shows a warning so you know your input is in capital letters. Passwords are case-sensitive, so if you see the Caps Lock warning and your sign-in fails, turn Caps Lock off and try again. ## Forgot password — reset your password If you cannot remember your password: 1. Tap Forgot your password? on the sign-in screen. 2. You will be taken to the Reset password screen. 3. Enter the email address linked to your account. 4. Tap Send reset link. 5. Check your email inbox (and spam/junk folder) for a message from CX Assistant. 6. Open the link in the email and follow the instructions to set a new password. After resetting, return to the app and sign in with your new password. ## Email not confirmed — verify your email If you registered but have not yet confirmed your email address, the app will redirect you to a Confirm Email screen after you try to sign in. From that screen: - You will see an explanation and the address we sent the confirmation to. - Tap Resend confirmation email if you did not receive it (a short cooldown applies between resends). - Check your spam or junk folder. - Once you open the confirmation link in the email, return to the app and sign in normally — there is also a back-to-sign-in link on the screen. You cannot sign in until your email is confirmed. ## Common sign-in errors - Invalid email or password: Check for typos. Passwords are case-sensitive (watch for the Caps Lock warning). Use Forgot your password? to reset if needed. - Unable to reach the server: Check your internet connection. Try switching between Wi-Fi and mobile data. - Email not confirmed: Complete email verification before signing in. - Account not found: Make sure you are using the email address you registered with. - Too many attempts: Wait a few minutes before trying again. ## Security tips for sign-in - Never share your password with anyone, including support staff. - Use a strong, unique password for your CX Assistant account. - Enable two-factor authentication (Profile → Security) for extra protection. - Only use Remember email on personal devices. - Sign out when using a shared or borrowed device. ## Two-factor authentication (2FA) verification at sign-in If two-factor authentication is enabled on your account, you will see the verification screen after entering your email and password. The screen shows tabs for the methods available on your account: - Email OTP: A 6-digit code is sent to your registered email address. Enter it in the field. - Authenticator (TOTP): Open your authenticator app (such as Google Authenticator, Microsoft Authenticator, or Authy) and enter the 6-digit code it shows. - Backup code: Use one of your single-use backup codes if you cannot access your authenticator app or email. Tap the tabs at the top to switch between methods. Once you enter a valid code, you are signed into the app. ## Resend 2FA email code If you chose the Email OTP method and did not receive the email: 1. Wait up to one minute for the email to arrive. 2. Check your spam or junk folder. 3. Tap Resend code to request a new one. The button re-activates after a 30-second cooldown between sends. If you ask again too soon you may see "Wait …s before requesting another code.", and after several requests in an hour "Too many code requests. Try again later." Each code expires after a few minutes. If it expires, simply tap Resend code again. ## Too many wrong 2FA codes — the 15-minute lock To protect your account, the verification screen limits wrong codes. After five wrong codes in a row, that verification method is locked for 15 minutes. This applies to email codes and to authenticator app codes. While it is locked, even a correct code is refused and the screen shows: "Too many failed attempts. Try again in 15 minutes." — the number counts down as the lock runs out. What to do: 1. Wait until the time has passed, then enter a fresh code. 2. For email codes, you can tap Resend code instead. The new code comes with a fresh set of attempts. 3. The lock is per method. If your account has another method, switch tabs and use it — for example the Backup code tab with one of your saved backup codes. Tip: authenticator codes change every 30 seconds. Wait for a new code rather than retyping one that is about to expire. ## Using a backup code at sign-in Backup codes are single-use codes you received when you set up two-factor authentication. Each code can only be used once. To use a backup code: 1. On the verification screen, tap the Backup code tab. 2. Enter one of your saved backup codes exactly as it appears in your list. 3. Confirm to sign in. After use, the code is permanently invalidated. If you run low on backup codes, regenerate a new set from Profile → Security once you are signed in. ## Reset password screen The Reset password screen is reached by tapping Forgot your password? on the sign-in screen. 1. Enter your registered email address. 2. Tap Send reset link. 3. A success message confirms we sent the email — this message always appears even if the email is not registered, to protect privacy. 4. Check your inbox (and spam) for a CX Assistant email with a Reset Password link. 5. Tap the link — it opens a page where you can set a new password. 6. After resetting, return to the app and sign in with the new password. If you never receive the email, double-check the address and try again, or contact support. --- # Map Cx Assistant help · platform: mobile · module: maps · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/maps ## What is the Map on mobile and how to open it The Map shows your project on your phone's map: every site and building that has an address or coordinates, and every asset that has its own position or route. Pins take the colour of the asset status. Tap a pin to see its details, get directions to it, or create an issue right there. Open the drawer and tap Map. The entry only appears when the Map module is switched on for the project. The header shows the title Map with the number of pins currently shown, a search button and a filters button. When the screen opens it frames all your pins. If you arrive from a Show on map link in an asset or an issue, it goes straight to that pin. The Map belongs to a project. It is not available in your personal workspace. ## What the pins, lines and colours mean - A rounded square pin is a site or a building. Its colour is the most common status among the assets inside it. - A round pin is an asset with its own position, such as a turbine, a pole or a tower. Its colour is the asset's status and the icon comes from the asset type. - A coloured line is an asset with a route, such as an overhead line, a cable route or a pipeline. It has a round pin at its midpoint so it is easy to tap. - A donut with a number is a group of nearby pins. Tap it to zoom in. - The blue dot is you. It appears once you allow location access. Equipment inside a building does not need its own pin. It is counted in the building's pin. To change what the colours mean, open the filters and pick Status, Asset type or Open issues under Colour by. With Open issues, pins with open issues are red and the rest are green. ## The map buttons: grouping, basemap, fit all pins and my location The round buttons sit in a column at the bottom right. From top to bottom: - Move pins (four arrows): only shown when your role has `assets.update`. See the section on moving a pin. - Group pins (three circles): when it is on, nearby pins merge into a donut until you zoom in. When it is off, every pin is drawn on its own. - Basemap: switches between the street map and satellite. - Fit all pins (frame icon): zooms out to show every pin that matches your filters. - My location (target icon): centres the map on you. The first time, your phone asks for location access. The icon turns blue while your location is on. Your basemap and grouping choices are remembered on this phone. If you see "Location access is off for Cx Assistant", tap Open Settings and allow location for the app. ## How to search and see what is nearby 1. Tap the search button in the header. 2. Type a site or building name, an asset ID, an address or a location in the box labelled "Search sites, buildings & assets…". 3. Tap a result. The map moves to that pin and opens its card. Nearby: leave the search box empty. When your location is known, the list is headed "Nearby · Closest to you first" and shows the closest pins with the distance to each one (up to 60). A red dot marks pins with open issues. If your location is not shared yet, tap Use my location at the top of the list. Search looks only at pins that match your current filters. ## How to filter the map 1. Tap the filters button in the header. 2. Under Layers, show or hide Sites & buildings and Assets, or turn on With open issues to see only pins that have open issues. 3. Under Colour by, choose what the colours mean: Status, Asset type or Open issues. 4. Under Status and Type, pick one status or one asset type. A site or building stays visible when at least one asset inside it matches. 5. Tap Apply. The filters button turns blue with a small dot while filters are on, and the number next to the title shows how many pins match. To reset, open the filters again, tap Clear all and then Apply. ## The pin card: details, issues and directions Tap a pin and a card slides up from the bottom. The map stays live behind it: tap another pin to switch, or tap the map or the ✕ to close the card. The chips at the top show the number of open issues, the number of assets (or sub-assets), the length of a line, and how far the pin is from you when your location is on. For a site or building the card shows its Address, Assets by status and Asset types. For an asset it shows its Status, Part of (the parent asset, which you can tap), Location and its Sub-assets. Tap the Coordinates to copy them. When there are open issues, the card lists the three most recently updated ones under Open issues. Tap one to open it. Buttons: - Open asset: opens the full asset sheet. - Create issue: starts a new issue. From an asset pin, the asset is already linked. From a site or building pin, the location is filled in. - Add asset and Add building: see the section on adding things. - Use my position: see the section on moving a pin. - Directions: opens your phone's maps app with a route to the pin. ## Lines and routes on the phone An asset with a route is drawn as a line with a round pin at its midpoint. Tap the line or its pin to open the card. For a line, the card shows its Length and number of points, and under Route its Start and End coordinates with Copy route. The directions button reads Directions to start and takes you to where the line begins, not to its middle. Lines cannot be dragged. To record or replace a route on site, use Walk this span from the asset (see that section). Kilometre points (KP) and the chainage reference line are shown on the web app only. ## How to add a site, a building or an asset from the phone The Add button sits at the bottom left. It is shown when you may create something: sites and buildings need the project owner, `projects.locations.edit` or `projects.settings.manage`; assets need `assets.create`. 1. Tap Add. The Add to the map sheet opens. 2. Choose Site, Building or Asset. 3. A pin is fixed in the middle of the screen. Move the map under it until the pin sits on the right spot. The card at the bottom shows the address found there. 4. Tap Place here. 5. For a site or building: fill in Name (required), Code, Address and, for a building, Inside site. Tap Create. 6. For an asset: the create asset sheet opens with the coordinates filled in. Give it an asset ID, pick a type and a category, and save. The new pin appears and its card opens. From a pin card you can also tap Add building on a site, or Add asset on a site or building. The map zooms to that pin, you place the new item the same way, and it is created inside that site or building. On the web you can also pick an asset that already exists and give it a spot on the map. On the phone, use Use my position or Move pins for that. ## How to move a pin or use your own position Both ways need `assets.update`. Only asset pins can be moved. Lines cannot. Use my position (you are standing at the asset): 1. Tap the asset's pin. 2. Tap Use my position on the card. 3. A message titled "Use my position?" shows the coordinates and the GPS accuracy. Tap Confirm. 4. The pin moves to where you are. Move pins (drag): 1. Tap the Move pins button (four arrows) at the bottom right. 2. Press and hold an asset pin, then drag it to its new spot. 3. The position is saved when you let go. If the save fails, the pin goes back. 4. Tap the button again when you are done. You can also set a position from the asset itself: open the asset and, in the Map position card, tap Use my position. Clear position removes the asset's own spot on the map; the asset keeps its location. Show on map takes you to its pin. ## How to record a route by walking it (Walk this span) Use this for an asset that spans a distance, such as a cable route, a fence line or a pipeline. You need to be able to edit the asset. 1. Open the asset (from its pin with Open asset, or from the Assets screen). 2. In the Map position card, tap Walk this span. 3. Tap Start walking. Allow location access if your phone asks. 4. Walk the line from one end to the other with the phone on you. A point is recorded every 5 m. The chip on the map shows the points, the length so far and the GPS accuracy. 5. Keep the app open while you walk. Recording pauses in the background. 6. Tap Stop at the end. 7. Check the trace on the map. Tap Save route to keep it, Walk again to start over, or Discard. Good to know: - The map follows you while you record. If you pan away, tap Follow me to come back. - When the GPS accuracy is poor (worse than about ±50 m), points are skipped until it improves. - A route needs at least two points. - If the asset already has a route, it is shown in grey. Saving replaces it. - Clear route in the Map position card removes the route. The asset keeps its position. You can also walk a route while creating a new asset: the same button is in the create asset sheet. ## What is only on the web These Map features are on the web app and not on the phone: - Import KML or KMZ files. - Chainage: kilometre points (KP) and choosing the reference line. - Placing an asset that already exists by picking it from a list, and adding an existing asset to a site or building. - The Legend and the hover summary. - View all issues, which opens the issues list filtered to a pin. - Floor plans linked to a building. - Sharing a filtered view as a link. - Switching the Map module on or off for the project. ## Permissions and Map troubleshooting on mobile Permissions: - `maps.read`: see the map. - `assets.update`: Move pins and Use my position. - `assets.create`: add an asset from the map. - Project owner, `projects.locations.edit` or `projects.settings.manage`: add a site or a building. Troubleshooting: - Map is not in the drawer, or the screen says "The map is off for this project": the Map module is off. A project admin can switch it on from the project settings on the web (the Modules card on the project details page). - "Access restricted — You don't have permission to see the map in this project": your role lacks `maps.read`. Ask a project admin. - "Nothing on the map yet": no site, building or asset has a position. Give your sites and buildings an address, give assets their own position, or tap Add on the map. - An asset is missing: it may have no position of its own. Equipment inside a building is counted in the building's pin. Also check your filters. - No blue dot, or Nearby is empty: location access is off. Tap the My location button, or allow location for Cx Assistant in your phone's settings. - "Your position is not available right now": the phone has no GPS fix. Move outdoors and try again. - "Could not load the map": check your connection and tap Retry. - No Add button or no Move pins button: your role lacks the permission. - Walk this span skips points: the GPS accuracy is poor. Wait for a better signal, away from buildings and steel roofs. --- # Navigation & App Basics Cx Assistant help · platform: mobile · module: navigation · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/mobile/navigation ## How to open and close the navigation drawer The main navigation in CX Assistant mobile is a sliding side drawer. To open the drawer: - Tap the hamburger icon (☰) in the header of any main screen. - Or swipe right from the very left edge of the screen. To close the drawer: - Tap anywhere outside the drawer panel. - Or swipe the drawer back to the left. While open, the drawer pushes the screen content to the right. The drawer is available from every main screen, and its width adapts on tablets and in split-screen modes. ## What is in the navigation drawer From top to bottom, the drawer contains: 1. The project card — the name and code of the project you are in, or My Workspace. Tap it to switch project or to join one. 2. The module list — up to ten rows: Chat, Home, Issues, RFIs, Planner, Scripts, Assets, Map, Layouts, and Documents. Map and Layouts appear only when that module is turned on for the project. The section you are currently on is highlighted. 3. Your chat history — previous conversations with the AI assistant, plus a New chat button. 4. Your profile card — avatar, name, and email, at the very bottom. Tap it to open your Profile screen. Sign out is on the Profile screen, not in the drawer. Notifications has no row in the drawer. Tap the bell in the header of any main screen instead. In My Workspace, and until you join your first project, the module list shows only Chat and Documents. While you have no projects it also shows a Join project row. The drawer rows themselves are not hidden by your role — individual screens may still require project permissions. ## The Sync row in the drawer Below the module rows, the drawer has a Sync row (needs an up-to-date version of the app). It is always there, in every project and in My Workspace. Tap it to open the Sync screen, which lists the script work your phone has not sent yet — for example steps you filled in with no signal — and anything that needs your decision before it can be sent. The row shows a number when something is waiting or needs your attention, counted across all your projects. When an item needs your attention, the row's icon changes to a warning. No number means everything has been sent. The Sync screen opens on top of the screen you are on; use the back button to return. See the Scripts help for what the Sync screen shows and how to work offline. ## The main sections of the app The app has up to ten main sections, switched from the drawer: - Chat: The AI assistant — this is also the landing screen after you sign in. - Home: Read-only project insights — KPI tiles and charts for issues and assets. - Issues: View, create, and manage project issues. - RFIs: Requests for information, with official responses and due dates. - Planner: A calendar of planner activities (month, week, and day views). - Scripts: Find and execute commissioning scripts. - Assets: Browse, create, and update project assets. - Map: Your sites, buildings and assets on a map. Shown only when the Map module is on for the project. - Layouts: Interactive 3D plans of your site. Shown only when the Layouts module is on for the project. - Documents: Browse, upload, and manage project files and folders. The Notifications inbox is not in the drawer. Tap the bell in the header of any main screen to open it. Tap any item in the drawer to switch to it. Sections switch with a quick fade — there is no back button between main sections; use the drawer to move around. Detail screens (like Profile or a script runner) slide in on top and support swipe-back. ## Where are Profile, Security, Support and Legal? Profile, Security, Support, and Legal are no longer separate rows in the drawer. They all live inside your Profile: 1. Open the drawer (☰). 2. Tap your profile card at the bottom of the drawer (your avatar, name, and email). 3. On the Profile screen you will find: Profile details, Change password, Appearance (dark mode), Desktop control, Security, Privacy & Legal (Terms of Service and Privacy Policy), Support, Sign out, and the Danger zone (account deletion). So the path for support is: drawer → profile card → Support. The path for two-factor authentication and sessions is: drawer → profile card → Security. ## The notification bell and its badge Every main screen has a bell in its header, on the right. It carries a badge with the number of notifications you have not yet seen (it shows 9+ above nine). The same count is mirrored on the app icon. There is no Notifications row in the drawer. How to open your notifications: 1. Tap the bell. A Notifications sheet slides up over the screen you are on, so you do not lose your place. 2. Tap a notification to go to it, or tap See all to open the full Notifications screen. Opening the sheet or the Notifications screen acknowledges the badge: everything is marked as seen, the badge clears, and stacked system notifications are dismissed. Individual notifications stay bold until you read them. ## Chat history in the drawer All previous chat conversations are listed in the drawer, most recent first, and are available from every screen. - Tap the New chat button at the top of the history list to start a fresh conversation. - The active chat is highlighted. - Tap any conversation to reopen it. - Scroll down to load older chats — the list loads 20 at a time as you scroll. ## The chat header — menu, project chip, bell, and new chat The Chat screen header has four floating glass chips: - Left: the hamburger chip (☰) opens the drawer. - Centre: the project chip shows your active project's name, or My Workspace when you are in your personal workspace. Tap it to open the project picker, where you can switch projects, go to My Workspace, or join a project with an invite code. - Right: the bell opens your notifications and carries a badge with your unseen notification count. - Far right: the compose icon starts a new chat. Until you join your first project, the Chat screen also shows an onboarding banner guiding you to join one. ## Switching projects To switch between projects: 1. Open the drawer (☰) and tap the project card at the top. On the Chat screen you can also tap the project chip in the centre of the header. 2. The Select project sheet opens with My Workspace first, then your project list (name, code, and a check on the active one). 3. Tap a project to switch to it, or tap My Workspace for your personal workspace. At the bottom of the sheet, the Join project row opens the invite-code screen for joining another project. When you switch, the app clears cached data and re-fetches your permissions for the new project, so all screens (Issues, Assets, Documents, Planner, etc.) show the newly selected project's data. Creating projects is only possible on the web app. ## Contact support — submit a ticket You can contact the CX Assistant support team directly from the app. How to submit a support ticket: 1. Open the drawer (☰) and tap your profile card at the bottom. 2. On the Profile screen, tap Support. 3. Select a reason for your request: Subscription, Technical, Account, Feature request, or Other. 4. Describe your issue or request in the details field. 5. Tap Submit. 6. You will see a confirmation with your ticket ID — tap it to copy it to the clipboard. Keep the ticket ID in case you need to follow up. ## Support website and email In addition to in-app tickets, you can also reach support through: - The support website (linked from the Support screen). - Email: support@cx-assistant.com For the fastest response, use the in-app ticket form — it automatically includes your account information. ## Reading the Terms of Service and Privacy Policy To read the Terms of Service or Privacy Policy: 1. Open the drawer (☰) and tap your profile card at the bottom. 2. On the Profile screen, find the Privacy & Legal section. 3. Tap Terms of Service or Privacy Policy — the document opens in an in-app viewer. You accepted both documents when you created your account, and you can review them at any time. ## Sign out To sign out: 1. Open the drawer by tapping ☰. 2. Tap your profile card at the bottom of the drawer. 3. On the Profile screen, scroll down and tap Sign out. There is no Sign out button in the drawer itself. You will be returned to the sign-in screen and your locally cached data is cleared. If your phone still holds script changes that have not been sent, an "Unsent changes" message appears first. Choose Sign out and keep them — they stay on the phone and are sent after you sign in again — or Discard and sign out, or Cancel. To sign back in, enter your credentials on the sign-in screen. ## Floating glass headers and collapsing search bars Screens in CX Assistant use a floating "liquid glass" header — lists scroll behind a translucent header bar rather than stopping under it. On list screens (Issues, RFIs, Assets, and others), the search and filter rows tuck away automatically when you scroll down, giving the content more room. Scroll back up and they return. This is normal behaviour, not a missing search bar — just scroll up a little to bring it back. ## Bottom sheets — how detail and picker panels work Most detail views and forms in the app open as bottom sheets — panels that slide up from the bottom of the screen with a drag handle at the top. - Swipe the sheet down (or tap outside it) to dismiss it. - When you edit a select field inside a sheet (for example an issue's status), a compact picker slides up inside the same sheet instead of opening a new screen. Choose a value and the picker slides back down. - Scroll within a sheet to see all of its content. You will meet this pattern when viewing issues, RFIs, assets, planner activities, document actions, and more. ## Pull to refresh and infinite scroll Two gestures work on virtually every list in the app: - Pull to refresh: drag down from the top of a list and release to reload it from the server. Use this to pick up changes made by teammates. - Infinite scroll: long lists (Issues, RFIs, Assets, Scripts, Notifications, chat history, document versions) load a page at a time. When you scroll near the bottom, the next page loads automatically and a small loading indicator appears. Search fields across the app update results automatically after a short pause while you type — there is no separate search button. ## Dark mode and language The app follows your device's light or dark appearance automatically. To override it, open your Profile (drawer → profile card) and use the dark mode switch in the Appearance section — the change applies immediately. The app's interface language can be changed from the language picker in your Profile details. Content authored by your project — project names, status labels, announcements — is always shown exactly as it was written and is never translated. ## Using the app on a tablet CX Assistant adapts to larger screens. On tablets and in split-screen or Slide Over modes: - Content is capped to a comfortable column width so lines stay readable. - The navigation drawer adapts its width to the available space. - Grid views (such as Documents in grid mode) show more columns. All features work the same as on a phone. ## App not responding or showing an error If the app freezes, shows an unexpected error, or seems to be missing data: 1. Check your internet connection. 2. Pull down to refresh on any list screen. 3. Close and reopen the app. 4. If the problem persists, submit a support ticket: drawer → profile card → Support. For critical issues, email support@cx-assistant.com and include your ticket ID or a description of the problem. --- # Notifications Cx Assistant help · platform: mobile · module: notifications · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/notifications ## The notifications inbox — what it shows The notifications inbox collects everything addressed to you: assignments, comments, planner reminders, review and tracker updates, export results, assistant answers that finished while you were away, assistant runs paused for your approval, and system announcements. How to open it: 1. Tap the bell in the header of any main screen. It carries a badge with your unseen count. There is no Notifications row in the drawer. 2. A Notifications sheet slides up over the screen you are on. Tap a notification to go to it. 3. Tap See all to open the full Notifications screen, with the All / Unread filter, Mark all as read, and the Notification settings button. The inbox groups rows by project, with a "General" group for system messages and announcements pinned first. It updates live, loads more as you scroll, and supports pull-to-refresh. ## Badge vs unread — what clears what There are two separate states: - Unseen (the badge) — the count on the bell in every main screen's header and on your app icon. Simply opening the notifications sheet or the full inbox clears it: everything is marked seen, the app-icon badge resets, and stacked notifications are dismissed from your phone's notification shade. - Unread (bold rows) — a row stays bold until you actually read it. Opening the inbox does NOT mark rows read; tapping a row does. So the badge disappearing doesn't mean you've read everything — bold rows are still waiting for you. ## Filtering unread and marking all read On the full Notifications screen (bell → See all), use the All / Unread segmented control at the top to show everything or only unread rows. When unread rows exist, a "Mark all as read" action appears — tap it to mark every notification read at once. Individual rows are marked read the moment you tap them. ## Tapping a notification — project switch and deep links Tapping a row does three things in order: 1. Marks the row read. 2. If the notification belongs to a different project than your active one, the app switches to that project automatically. 3. Navigates to the target: issue notifications open the issue sheet, planner notifications (assignment, reminder, activity due) open the activity in the planner calendar, assistant notifications ("answer ready", "needs your approval") open that chat — a waiting approval shows its card there, ready to approve or decline — and announcements open the announcement sheet. You land directly on the thing the notification is about — no manual searching needed. ## Announcements System announcements appear in the pinned "General" group at the top of the inbox. Tap one to open it in a sheet with its full formatted message. Announcements are shown in the language they were written in — the app does not translate authored content. ## Notifications for web-only features — continue on web Some notifications point at features that live only in the web app — for example review, tracker, and export notifications. These rows still appear in your mobile inbox so nothing gets lost. Tapping one marks it read and shows a "continue on web" hint chip instead of navigating: open the web app to act on it. ## Notification settings — choosing what you receive and where Open the full Notifications screen (bell → See all) and tap the tune button in its header to open Notification settings. You get a switch matrix: one row per notification type (grouped into categories such as reviews, issues, planner, trackers, exports, and system), with a toggle per channel: - In-app — rows in the notifications inbox. - Push — notifications on your phone (mobile only). - Email. Each toggle saves instantly — there is no Save button. Flip a switch and you're done. ## How to enable push notifications Push notifications are enabled from Notification settings (bell → See all → tune button). There is no prompt at first launch. 1. Open Notification settings. 2. In the "Turn on push notifications" card, tap Turn on; the system permission dialog appears. 3. Allow notifications. The app also offers once, in chat: the first time you walk away from a chat that is still working, or an answer finishes while you were away, it asks "Get notified when it's ready?". Tap Turn on and allow notifications, or tap Not now and use Notification settings later (needs an up-to-date version of the app). If you previously denied permission, the screen offers a link that takes you straight to the app's page in your phone's system settings, where you can allow notifications manually. Note that push does not work in simulators — only on real devices. ## How push notifications behave Once push is enabled: - Your app-icon badge mirrors your unseen notification count, and opening the inbox clears it. - Tapping a push notification opens the app and routes you straight to the target (issue, planner activity, announcement) — this works even when the app was fully closed. - Your device is re-registered for push each time the app cold-starts, so delivery keeps working after reinstalls and sign-ins. ## Not receiving push notifications — troubleshooting If pushes aren't arriving: 1. Open Notification settings (bell → See all → tune button) and check that Push is toggled on for the notification types you expect. 2. If the screen shows a "Turn on push notifications" card, notification permission hasn't been granted — tap Turn on and allow. If you denied it earlier, use the link to your phone's system settings and allow notifications there. 3. Check your phone's focus/do-not-disturb modes. 4. Fully close and reopen the app — this re-registers your device for push. 5. Remember pushes never arrive in simulators, only on real devices. In-app rows in the inbox arrive regardless of push, so check there to confirm the notifications themselves are being generated. --- # Planner Cx Assistant help · platform: mobile · module: planner · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/planner ## What is the planner calendar The planner is your project's schedule on a calendar. It shows planned activities — tasks, milestones, and groups — laid out by date so you can see what is happening this month, this week, or today. On mobile you can browse the calendar, create and edit activities, drag them to reschedule, set reminders, and assign work to people or groups. Overdue activities are highlighted in red. The full gantt chart, dependency editing, and bulk operations live on the web app; the phone focuses on the calendar. ## How to open the planner and switch between month, week, and day views Open the drawer (hamburger icon or swipe right from the left edge) and tap Planner. The top bar offers three views — Month, Week, and Day. Tap a view name to switch. Use the back (◀) and forward (▶) arrows to step to the previous or next month, week, or day, and tap Today to jump back to the current date. The header badge shows how many events are in the visible range. Pull down on any view to refresh it. ## Reading the month view The month view shows a Monday-first grid of day cells. Each day displays up to 3 dots — one per activity on that day. Below the grid, an agenda lists the activities for the selected day; tap a day cell to select it. Tapping a greyed leading or trailing cell (a day from the previous or next month) pages the calendar to that month. From the month view you can also: - Long-press a day cell to create an activity on that day. - Drag an activity card from the agenda onto another day cell to reschedule it. ## Reading the week view The week view shows the whole week as an agenda: seven day headers, each followed by that day's activity cards. Overdue activities appear in the error colour. To reschedule, drag an activity card into another day's section and release — the activity moves to that day. Use the arrows or Today in the top bar to change weeks. ## Reading the day view — all-day band, hour rail, and now-line The day view has three parts: 1. A 7-day week strip at the top — dots mark busy days; tap a day to jump to it. 2. An all-day band below the strip, showing multi-day and untimed activities as cards. It shows up to 3 cards; if there are more, tap the "+N more" expander to reveal the rest. 3. A 24-hour rail where timed activities appear as blocks at their scheduled times. Overlapping blocks are packed side by side so nothing is hidden. On today's date a red now-line marks the current time. When you open the day view it automatically scrolls to your first event, or to 08:00 if the day has no timed events. ## How to create an activity There are three ways to create an activity (all require the planner.create permission): - Tap the + button to open the create sheet. - Long-press a day cell in the month view to create an activity on that day. - In the day view, tap an empty hour slot to create a timed activity there — the start and end times are pre-filled, snapped to 30 minutes. The create sheet asks for: - Name (required). - Kind — Task or Milestone, chosen with chips. - Parent group — an optional chip row of existing groups (shown as PL- · name). - Start date, and for tasks an End date, picked in a calendar sheet. The end date can never be before the start date. - All-day switch — turn it off to also pick Start and End times. - Reminders — preset offsets before the start (0, 1, 2, 3, 7, 14, or 30 days), up to 5. - Assignee — a searchable picker for a user or a group. Tap Save to create the activity. ## Tasks, milestones, and groups — what's the difference Planner activities come in three kinds: - Task — work with a start date and an end date (a duration). Tasks can carry progress while In progress. - Milestone — a single-date marker for a key moment; it has a start date but no end date. - Group — a container that summarises its child activities. Group dates and progress are derived from the children. On mobile you can create tasks and milestones, and you can place them inside an existing group using the Parent group chips in the create sheet. Group activities themselves are read-only on mobile — their detail sheet shows a rollup hint and cannot be edited here. Create and restructure groups on the web app. ## How to view and edit an activity Tap any activity card or block to open its detail sheet. The sheet shows the activity's details and lets you edit inline — the Save button only becomes active once you change something. You can edit: - Name. - Status — chips for Planned, In progress, and Done. - Progress — steps of 0/25/50/75/100%, available only for tasks and only while the status is In progress. - Start and end date. - All-day switch and, when off, start/end times. - Reminders and assignee. - Notes. Group activities open read-only: their dates and progress are derived from their children, and the sheet shows a rollup hint instead of editors. To delete an activity, use Delete in the sheet and confirm (requires planner.delete). Editing requires planner.update. ## Drag an activity to reschedule it You can reschedule activities directly on the calendar (requires planner.update): - Month and week views: drag an activity card onto another day and release. This shifts the whole activity by whole days — and it always pushes any dependent (successor) activities along with it, even though dependency lines are not drawn on mobile. You'll feel a haptic tick when the move commits. - Day view: long-press a timed block to grab it, then drag it up or down the hour rail. The block snaps to 15-minute steps; release to commit the new time. If a drag doesn't seem to work, you may not have the planner.update permission — ask a project admin. ## All-day vs timed activities — setting times Every activity is either all-day or timed: - All-day activities occupy whole days. In the day view they appear in the all-day band at the top. - Timed activities have start and end times as well as dates. In the day view they appear as blocks on the 24-hour rail. To switch, open the activity (or the create sheet) and toggle the All-day switch. Turning it off reveals Start time and End time pickers. Tapping an empty hour slot in the day view creates a timed activity directly, with times pre-filled and snapped to 30 minutes. ## How to set reminders on an activity Open an activity (or the create sheet) and find the Reminders row. Tap a chip to add that reminder; tap it again to remove it. You can add up to 5 reminders per activity. The chips depend on the All day switch: - Timed activity (All day off): At the start time, or 15 minutes, 30 minutes, 1 hour, 2 hours, 1 day, 2 days, or 1 week before. These arrive within a few minutes of the time, in your own time zone. - All-day activity: On the start day, or 1, 2, 3, 7, 14, or 30 days before. These are the same choices as on the web app. A reminder set on the web with a different offset shows here as an extra chip. A chip whose reminder was already sent shows a check instead of a bell. The reminder notifies the assignee and whoever added it. Tapping the notification opens the activity. Whether it also arrives as a push or email depends on your choices in Notification settings (bell → See all → tune button). ## Assigning an activity to a person or group In the activity detail sheet or the create sheet, tap the Assignee field. A searchable picker slides up where you can choose either a single project member or a group. Type to filter, then tap to select. The assignee receives a planner assignment notification. To clear the assignee, open the picker again and remove the selection. ## Opening activities from notifications Planner notifications — assignment, reminder, and activity-due — deep-link straight into the planner. Tapping one (from the notifications inbox or a push notification) opens the activity's detail sheet and re-anchors the calendar on the activity's start day, so you land exactly where the work is scheduled. ## Gantt chart, dependencies, and bulk edits are on the web The mobile planner is a calendar. The gantt chart, dependency drawing and editing, and bulk operations (multi-select shifts, bulk status changes, bulk delete) are deliberately web-only — open the Planner page in the web app for those. Dependencies still take effect on mobile: dropping an activity onto a new day always pushes its dependent (successor) activities along, even though the dependency lines themselves are not drawn on the phone. ## Who can use the planner — permissions Planner access is controlled by your project role: - planner.read — see the calendar and activities. Default: Project Admins, Project Members, and Technicians. - planner.create — the + button, long-press create, hour-slot create, and the empty-state create action. Default: Project Admins and Project Members. - planner.update — inline editing and all drag-to-reschedule gestures. Default: Project Admins and Project Members. - planner.delete — delete an activity. Default: Project Admins only. The project owner can always do everything. If an action is missing or disabled for you, ask a project admin to adjust your role. ## Planner not loading or empty — troubleshooting If the calendar looks empty: - There may simply be no activities in the visible range — use ◀ ▶ or Today to check other dates, and note the header badge shows the event count for the range. - If you have not joined a project yet, the planner shows a no-project state — join a project first. Plans themselves are created on the web (the empty state links there). If the planner shows an error or stale data: 1. Pull down to refresh (works in all three views). 2. Check your internet connection. 3. Close and reopen the app. 4. If activities you expect are still missing, confirm with a project admin that you have the planner.read permission. --- # Profile & Account Settings Cx Assistant help · platform: mobile · module: profile · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/profile ## Opening your profile To open your profile: 1. Tap the hamburger menu icon (☰) on any main screen to open the side drawer. 2. Tap your profile card at the bottom of the drawer — the card with your avatar, name, and email. (The card at the top of the drawer is the project switcher.) The Profile screen slides in on top of the current screen; swipe back or use the back control to return. ## Profile screen overview The Profile screen is your hub for account settings. It contains: 1. Avatar — your profile photo (pick or remove). 2. Profile details — first name, last name, email, phone number, and the app language picker, with a Save changes button. 3. Change password. 4. Appearance — a dark mode switch. 5. Desktop control — the "Ask before every desktop task" switch for the Cx Desktop app. 6. Security — two-factor authentication and your active sessions. 7. Privacy & Legal — Terms of Service and Privacy Policy. 8. Support — contact the support team. 9. Sign out. 10. Danger zone — permanently delete your account. ## Update or remove your avatar (profile photo) Your avatar is shown in the drawer and in team member lists. To set a new avatar: 1. Tap your current avatar (or the camera control) in the avatar card. 2. The app asks for access to your photo library the first time — allow it. 3. Pick a photo. The upload starts automatically. To remove your avatar: 1. Tap the Remove option in the avatar card (shown when you have a photo set). 2. Confirm. Your account then shows your initials instead of a photo. ## Photo library permission The app needs access to your photo library to let you pick a profile photo. When you tap the avatar for the first time, iOS or Android shows a permission dialog. - Tap Allow (or Allow Access) to grant permission. - If you previously denied it, enable photo access for CX Assistant in your device Settings. If permission is denied, the photo picker cannot open. ## Update your name, email, and phone number In the Profile details section: 1. Edit the First name field (required). 2. Edit the Last name field. 3. Edit the Email field to change your registered email address. 4. Edit the Phone field to add or update your phone number. 5. Tap Save changes. Changes are reflected across the app and for your teammates. Note that changing your email changes the address used for login and notifications. ## Change the app language To change the language of the app interface: 1. Open your Profile (drawer → profile card). 2. In the Profile details section, tap the Language picker and choose your preferred language. 3. Tap Save changes. The app interface switches to the selected language. Content written by your project team — project names, status labels, comments, announcements — always stays exactly as it was written and is not translated. ## Change your password To change your password from the app: 1. Open your Profile and find the Change password section. 2. Enter your new password. 3. Re-enter it in the confirmation field. 4. Save. Requirements: minimum 8 characters, and both fields must match. Tap the eye icon on a password field to show or hide what you are typing. After a successful change you remain signed in on this device. To sign other devices out, use Security → Active sessions. ## Dark mode — change the app appearance The app follows your device's light or dark appearance by default. To override it: 1. Open your Profile (drawer → profile card). 2. In the Appearance section, use the dark mode switch. The change applies immediately across the entire app — no restart needed. ## Security and sessions — where to manage 2FA and devices Two-factor authentication and signed-in devices are managed from the Security screen: 1. Open your Profile (drawer → profile card). 2. Tap the Security row ("Two-factor authentication and active sessions"). From there you can set up or disable an authenticator app (TOTP) and email codes, manage backup codes, and open the Active sessions screen to see and revoke signed-in devices. ## Legal — Terms of Service and Privacy Policy To read the legal documents: 1. Open your Profile (drawer → profile card). 2. In the Privacy & Legal section, tap Terms of Service or Privacy Policy. The document opens in an in-app viewer. You accepted both when creating your account and can review them at any time. ## Support — contact the support team To contact support: 1. Open your Profile (drawer → profile card). 2. Tap the Support row. 3. Pick a reason (Subscription, Technical, Account, Feature request, or Other), describe your request, and submit. You receive a ticket ID you can copy to the clipboard. The Support screen also links to the web support page and support@cx-assistant.com. ## Sign out To sign out of the app: 1. Open the side drawer by tapping ☰. 2. Tap your profile card at the bottom of the drawer to open your Profile. 3. Scroll down and tap Sign out (below Support). There is no Sign out button in the drawer itself. You will be returned to the sign-in screen and locally stored data is cleared. To sign back in, enter your email and password. ## Delete your account — Danger zone Account deletion is permanent and cannot be undone. To delete your account: 1. Open your Profile and scroll to the Danger zone section at the bottom. 2. Tap Delete account. 3. A warning explains what will be deleted — read it carefully. 4. Confirm the deletion. What happens: - Your personal information is removed from the system. - You are signed out immediately and cannot sign in again with the same account. If you only want to leave a project (not delete your account), contact a project admin instead. ## Profile update errors - Name is required: First name cannot be empty. - Email already in use: The new email is already registered to another account. - Password mismatch: The confirmation must match the new password. - Password too short: Use at least 8 characters. - Update failed: Check your internet connection and try again. --- # Projects — Join & Switch (Mobile) Cx Assistant help · platform: mobile · module: projects · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/projects ## Creating a project — web app required Project creation is not available in the mobile app. You must create a project from the CX Assistant web application. Once a project is created on the web, it appears immediately in your mobile app (in the project picker) and you can work with it normally from there. On mobile, the two project actions available are joining a project with an invite code and switching between the projects you already belong to. ## How to create a project from the web app To create a new project, open the CX Assistant web app in a browser: 1. Open the project picker and click "Create project" (also available from the Projects page). 2. Everything happens on a single screen. Fill in the basics: project name, a short code (used as a prefix throughout the project), and the client company. 3. Pick a starter template — it seeds the project's configuration (statuses, priorities, types, doc groups) with sensible defaults you can change later in Project Settings. 4. Click Create. Your progress is saved automatically as a draft, so you can leave and resume later. The project appears in your mobile app straight away. ## Join a project with an invite code If a project admin gave you an 8-character invite code, you can join their project directly from the app. How to join: 1. Open the invite-code screen. You reach it from the Join project row at the bottom of the project picker, from the Join project row in the drawer (shown while you have no projects), or from the "Join with invite code" button on a no-project empty state. 2. Type the code into the 8 boxes — the cursor advances automatically as you type, and backspace walks back to the previous box. 3. Or simply paste the full code — all 8 boxes fill automatically. 4. Codes use uppercase letters A–Z and digits 0–9; lowercase input is converted for you. 5. The Join button enables once all 8 characters are entered — tap it. 6. On success you see a confirmation overlay and are taken into the project. The screen also has a footer link if you prefer to continue on the web platform. ## Invite code errors - Invalid or expired code: The code does not match or has expired. Ask your admin for a new invite. - Already a member: You are already part of that project. Switch to it from the project picker instead. - Wrong email: The invite was issued for a different email address. Sign in with the correct account or ask your admin to resend. - Too many attempts: Wait a while before trying again. - Archived project: The project is not accepting new members. Contact your admin. ## The project picker — switch or join from the drawer or the chat header The project picker opens from two places: - The project card at the top of the drawer, on any main screen. It shows your active project's name and code. - The project chip in the centre of the Chat screen header. The picker is a sheet titled Select project. It shows: - My Workspace — your personal workspace, with the hint "Your personal files". - A scrollable list of your projects — each with its name and code, and a check mark on the active one. Tap a project to switch to it. - A Join project row ("Use an invite code") that opens the invite-code screen, where you enter an 8-character code to join another project. There is no create-project option on mobile — projects are created on the web app. ## What happens when you switch projects When you switch to a different project, the app clears its cached data and re-fetches your permissions for the newly selected project. All screens — Home, Issues, RFIs, Planner, Scripts, Assets, Map, Layouts, Documents, and Chat — then show that project's data. The Map and Layouts rows in the drawer come and go with the project, because each project turns those modules on or off. Because permissions are per project, what you can see and do may change after switching: your role in one project may allow actions that your role in another does not. ## What you can do with projects on mobile On the mobile app you can: - Join projects with an invite code and switch between your projects. - Use the AI chat assistant on your project data. - View project insights on the Home screen. - Browse and manage issues, RFIs, assets, and documents, and create issues and assets. - Work with the planner calendar and execute scripts. - See your sites, buildings and assets on the Map, when the Map module is on for the project. - Open the project's 3D Layouts and pin issues on them, when the Layouts module is on for the project. - Receive and read notifications. - Keep personal files and chat with the assistant in My Workspace, outside any project. Project creation, project settings, member management, configuration, and billing are only available on the web app. ## Personal workspace on mobile (My Workspace) My Workspace is your own space outside any project. You can chat with the assistant there and keep personal files. It is where you start before you join your first project. How to switch to it: 1. Open the drawer and tap the project card at the top (or tap the project chip in the Chat header). 2. In the Select project sheet, tap My Workspace ("Your personal files"). What changes while you are in My Workspace: - The project card and the Chat header chip read My Workspace. - The drawer shrinks to Chat and Documents. Home, Issues, RFIs, Planner, Scripts, Assets, Map and Layouts belong to a project, so their rows are hidden. - Documents opens your personal files — the same files you see under My Files on the web app — instead of a project's document tree. - If a project-only screen is still open, it shows "You're in My Workspace — This section lives inside a project. Switch to a project from the menu to see it." with a Select project button that opens the drawer. To go back, open the project picker again and tap one of your projects. The full drawer returns. ## No project yet — empty states Until you join your first project you are in My Workspace. The drawer shows only Chat and Documents, plus a Join project row, and the Chat screen shows an onboarding banner. Project screens such as Issues or Assets show a "No project joined yet" state with a "Join with invite code" button. Tap Join project (or "Join with invite code") to open the invite-code screen and enter the 8-character code from your project admin. If you are waiting to be added, ask an admin of the project to send you an invite code. --- # RFIs Cx Assistant help · platform: mobile · module: rfis · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/mobile/rfis ## What is an RFI An RFI (Request for Information) is a formal question raised on a project — for example a clarification about a design, a specification, or site conditions — that needs an official answer. Unlike an issue, an RFI is built around getting one authoritative response: it carries a question, a "response needed by" date, watchers who follow it, and an official response that a team member with the right permission promotes from the discussion. ## Opening the RFIs screen and browsing the list Open the drawer (hamburger icon or swipe right from the left edge) and tap RFIs. The list shows RFI cards with infinite scroll — more load automatically as you approach the bottom. The header shows the total count for the project. Pull down to refresh. The search and filter row tucks away as you scroll down and returns when you scroll up; the header with the title and the + button stays in place. ## Search, filter, and sort RFIs To find an RFI: - Type in the search bar; results update after a short pause. Search looks in the RFI title, description, and number. - Tap the Sort & filter button to open the filter sheet. You can multi-select Status, Priority, Type, Assigned to (people and groups), and Created by, and choose a sort order — including "Response needed (soonest first)". Tap Apply. Clear all resets the filters and the sort order. - Active filters appear as removable chips below the search bar — tap a chip to drop that filter. Search and filters combine. ## How to create an RFI Tap the + button on the RFIs screen (requires the rfis.create permission — Project Admins, Project Members, and Technicians have it by default). A create sheet slides up with these fields: - Title — required, up to 100 characters. Phrase it as the question you need answered. - Description — optional; the context and what you need answered. - Priority — required. Your project's default priority is pre-selected when it has one. - Type — optional; shown only if your project defines RFI types. - Response needed by — optional date, picked in a calendar. - Attachments — optional; take a photo, pick from the photo library, or pick a document. - Assigned to — optional; one person or one group, picked from a list (a search box appears on larger teams). - Watchers — optional; tap the members who should follow the RFI. Tap Create to raise the RFI. If you don't see the + button, your role lacks rfis.create — ask a project admin. ## Viewing an RFI — the detail sheet Tap any RFI card to open its detail sheet. It opens read-only first and shows the question, the official response card (if one has been set), properties like status, priority, type and assignee, the "response needed by" date, watchers, attachments, comments, and history. To edit, tap a field: select fields (status, priority, type, assignee) open a compact picker that slides up inside the sheet, and your choice is saved as soon as you tap it; title and description open an inline editor, one at a time — tap Save to keep the change or Cancel to discard it. Attachments: if you can edit the RFI, use the add tile in the Attachments section to take a photo, pick from the photo library, or pick a document. Tap an attachment to open it. ## The official response — setting and clearing it Each RFI can carry one official response — the authoritative answer to the question. It appears in a dedicated card between the question and the properties. To set it, promote an existing comment to be the official response. You can also clear the official response if it was set in error or superseded. Both actions require the rfis.respond permission (Project Admins and Project Members by default). Unlike other RFI edits, there is no shortcut for the creator or assignee here — only rfis.respond holders (or the project owner) can promote or clear the official response. ## Response needed by — due dates and overdue RFIs Each RFI can have a "Response needed by" date — the deadline for the official answer. Tap the date field in the detail sheet to pick it in a calendar sheet. When the date has passed and the RFI is not closed yet, the date turns red and is marked Overdue in the detail sheet, and the RFI shows a red clock icon in the list, so late RFIs stand out at a glance. An RFI stops counting as overdue once it reaches a closing status — setting the official response alone does not close it. ## Watchers — keeping people in the loop The watchers (CC) panel in the RFI detail sheet lets you add project members who should follow the RFI. Open the panel and multi-select the members to watch it. Use watchers for anyone who needs visibility of the question and its answer without being the assignee. ## Changing an RFI's status Tap the Status field in the detail sheet to open the status picker. It only offers the transitions your project's policy allows from the current status — statuses you cannot move to are not offered. Changing status requires rfis.status.update (Project Admins and Project Members by default). The RFI's creator, its assignee, and members of an assigned group can change status even without the permit. ## Commenting on an RFI Use the comments section in the RFI detail sheet to discuss the question — add context, propose answers, or ask follow-ups. Commenting requires rfis.comment, which all built-in roles (Project Admin, Project Member, Technician) hold by default. A comment can later be promoted to the RFI's official response by someone with the rfis.respond permission. ## Who can do what on RFIs — permissions RFI actions are controlled by your project role: - rfis.read — see the RFI list. Default: all roles (Admin, Member, Technician). - rfis.create — the + (New) button. Default: all roles. - rfis.update — edit RFI fields. Default: Admins and Members. - rfis.status.update — change status. Default: Admins and Members. - rfis.comment — comment. Default: all roles. - rfis.respond — promote or clear the official response. Default: Admins and Members; no creator/assignee shortcut. - rfis.delete — delete an RFI. Default: Admins only. Bypass rule: the RFI's creator, its assignee, or a member of the assigned group can edit and change status even without rfis.update / rfis.status.update. The project owner can always do everything. Actions you lack are hidden or disabled — ask a project admin if you need more access. ## RFIs not loading or missing actions — troubleshooting If the RFI list shows an error or stays empty: 1. Pull down to refresh. 2. Clear active search text and filter chips — a narrow filter can hide everything. 3. Check your internet connection, then close and reopen the app. If a button you expect is missing (New, edit fields, status, official response, delete), your role most likely lacks the matching permission — see "Who can do what on RFIs" and ask a project admin. If you have no project yet, join one first from the empty state. If the screen says "You're in My Workspace", open the menu and switch to a project — RFIs live inside a project. --- # Scripts Cx Assistant help · platform: mobile · module: scripts · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/mobile/scripts ## What are scripts Scripts are structured test and inspection procedures — for example commissioning scripts, checklists, or acceptance tests. A script is organised into sections of items; each item can ask for a result (such as pass/fail), data readings, and notes, and can carry evidence like photos and files. Scripts finish with signatures and a completion sign-off. On mobile you find scripts and execute them in the field: fill results, capture photo evidence with the camera, sign, and complete. ## Opening the Scripts screen and finding a script Open the drawer (hamburger icon or swipe right from the left edge) and tap Scripts. The list shows script cards, each with a progress bar and a status chip. To find a script: - Type in the search bar; results update after a short pause. - Tap a status chip in the horizontal filter row to show only scripts in that status. The list loads more as you scroll (infinite scroll); pull down to refresh. Tap a card to open the script runner. ## Why there is no create button on mobile You cannot create scripts from the phone — this is by design. Scripts are authored on the web app or generated with the assistant, where the full template and editing tools live. The mobile app is for finding scripts and executing them in the field: filling results, attaching evidence, signing, and completing. ## The script runner — layout Tap a script to open the runner. It shows: - Sections with sticky headers; each header shows how many items in the section are done (for example 3/8). - The items of the current section, each with its result control, data fields, notes, and evidence. - A footer signatures panel. - A bottom bar with previous/next section buttons, an overall progress bar with percentage, and a contextual action button (Complete script, Sign off to complete, or Reopen depending on the script's state). ## Filling in results, data fields, and notes For each item in the runner: - Result — tap the outcome that applies (for example pass or fail; the options are defined by the script). - Data fields — enter the readings or values the item asks for. Out-of-range or blank values may raise warnings, but record what you actually measured — never adjust a reading to silence a warning. - Notes — add free-text observations. Everything you enter is saved automatically as you go. ## Attaching evidence — photos and files Each item has an Evidence area where you can attach proof: - Take a photo with the camera. - Pick images from your photo library. - Attach files. Tap an attached photo to view it full-screen in the lightbox. To remove a piece of evidence, use its remove control. Evidence saves automatically with the rest of the item. ## Signatures — draw to sign The signatures panel sits in the runner's footer. Tap your signature slot to open the signature pad and draw your signature with your finger, then confirm. Signing requires the scripts.sign permission and applies to slots assigned to you or unassigned slots; signing any slot regardless of assignment requires scripts.sign.override. Ask a project admin if your slot won't accept a signature. ## Completing, signing off, and reopening a script The action button in the runner's bottom bar changes with the script's state: - No button — some items are still not done. Finish them first. - Sign off to complete — every item is done but a required signature is still missing. Tap it to jump to the signatures panel, then sign. - Complete script — every item is done and all required signatures are in. Tap it to finish the script. - Reopen — unlock a completed script for further editing. When you tap Complete script, the app checks the script first: - Values that need a look: if a data field was left blank or holds a value outside its expected range, a "Complete this script?" message lists them ("Left empty", or "outside" the expected range). Tap Cancel to go back and fix them, or Complete anyway to freeze the script as it is. Completing locks the script. - Steps that are not finished: a "This script isn't finished" message lists steps with no result and missing sign-offs. These cannot be skipped — resolve them, then try again. This needs an up-to-date version of the app. On an older version the phone only shows "Failed to complete script" without listing anything. In that case, fill in or correct the data fields and try again, update the app, or complete the script in the web app, which shows the same list and the same Complete anyway choice. Once completed, the script becomes read-only until reopened. ## Autosave and live updates from teammates The runner saves automatically, so there is no Save button to remember. Each entry is first kept on your phone and then sent to the server — straight away when you have a connection, later when you do not. The indicator in the script's header tells you where your entries are: - Syncing… — entries are being sent. - On this phone · 3 — that many entries have not reached the server yet. Tap it to open the Sync screen. - Sent — everything has just been sent. - Offline — nothing is waiting and you have no connection. When the indicator shows nothing, everything has been sent. Older versions of the app show "Saving… / Saved" instead. The runner is also live — while you are connected, if a teammate edits the same script from another device, their changes appear on your screen in real time. ## Working offline — running a script with no signal You can run a script on your phone with no connection (needs an up-to-date version of the app). There is nothing to switch on: it works the same way in every project. What works with no signal, on a script that is on your phone: - Results, data fields, and notes. - Evidence — photos from the camera or your library, and files. They show on the step with a small cloud badge until they are uploaded. - Signatures. - Completing the script. The app runs the same checks as when you are connected and shows the same messages; the script then shows "Completed — waiting to sync" until the completion is sent. Everything you enter is kept on the phone, also if you close the app, and is sent by itself when the connection returns. The header shows "On this phone" with the number of entries still waiting. When you open a script with no connection, a line under the header says "Showing the copy on this phone". What needs a connection: - Opening a script that is not on your phone yet. With no signal the Scripts list shows only the scripts kept on this phone. - Reopening a script whose completion has already been sent. A completion that is still waiting on your phone can be taken back with Reopen. - Removing evidence that has already been uploaded. Evidence still waiting on the phone can be removed: tap it and choose Remove from this phone. - Seeing teammates' changes — they appear once you are connected again. ## Keeping scripts on your phone before going to a site with no signal A script opens offline only if a copy of it is on your phone (needs an up-to-date version of the app). There are two ways a copy gets there: - Automatically — every script you open while connected stays on the phone for a week. - Keep on this phone — a script you mark this way stays until you unmark it. Before you leave for a site with no signal: 1. While you still have a connection, open the drawer and tap Scripts. 2. Swipe the script's card to the left and tap Keep on this phone. The label changes to Kept on this phone. You can also open the script and tap the phone icon in its header. 3. Check that the card shows "Available offline". Repeat for every script you will need. 4. Open the drawer and tap Sync to confirm nothing is still waiting from earlier work. With no connection, the Scripts list shows "Showing the scripts kept on this phone." and lists only those copies; the search bar and status chips still filter them. To free a copy, swipe its card left and tap Remove from this phone (unmark Kept on this phone first). A script with changes that are not sent yet cannot be removed — it stays on the phone until they are sent. This removes only the copy on your phone; the script itself is not deleted. There is no button to download every script of a project at once — mark the ones you need. ## The Sync screen — what is still waiting to be sent The Sync screen shows what your phone has not sent yet (needs an up-to-date version of the app). How to open it: - Open the drawer and tap Sync. The row shows a number when something is waiting or needs your attention. - Or, in a script, tap "On this phone" in the header. What it shows: - A summary at the top: "Syncing…", the number of changes on this phone, or "Everything is sent"; the time of the last sync; and "Waiting for signal" when you have no connection. - Sync now — sends what is waiting straight away. It is unavailable with no connection or when there is nothing to send. - Needs attention — items that could not be sent as they are and wait for your decision. Shown only when there are any. - On this phone — each script with changes or photos still waiting, and when it last synced. - Scripts on this phone — copies with nothing waiting. Each has a Keep on this phone switch; a copy with the switch off also has Remove from this phone. Tap a script's title to open it. If it belongs to another project, the app switches to that project first. You rarely need Sync now: waiting changes are sent by themselves when the connection returns, when you open the app, and when you come back to it. The list covers all your projects, not only the one you are in. ## Needs attention — conflicts and items that could not be sent Sometimes a change made offline cannot simply be sent — for example because a teammate answered the same step in the meantime (needs an up-to-date version of the app). Nothing is discarded for you: the change stays on your phone and the item appears under Needs attention on the Sync screen. In the script, a line under the header shows how many items need your attention; tap Review to go there. Each card says what happened and offers the choices that apply: - "Someone else answered this step while you were offline." — the card shows your value (Mine) and theirs (Theirs), with who changed it and when. Send mine replaces their value with yours. Keep theirs drops your change. Later leaves it for now. - "This signature was decided by someone else." — Keep theirs or Later. - "This script was completed by someone else. Your changes cannot be sent." or "This script was deleted." — Discard all my changes is the only choice. - A step, field, or signature that no longer exists in the script, or no permission to sign or complete — Discard. - A completion that was refused because steps are unfinished — the card lists them. Finish them in the script, then tap Retry, or Discard the completion. - A completion with blank or out-of-range values — the card lists them. Complete anyway, or Discard and fix the values first. - "Could not send" — the app tried several times and stopped. Retry or Discard. - "This photo could not be uploaded." — Retry or Discard. Discard removes that change from your phone for good, so note the value down first if you still need it. ## Completed scripts are locked Once a script is completed it becomes read-only: results, data, notes, evidence, and signatures can no longer be changed. This protects the integrity of the signed record. If something genuinely needs correcting, use the Reopen action in the runner's bottom bar, make the change, and complete the script again. ## Who can see and execute scripts — permissions Scripts are admin-gated by default — only Project Admins hold the scripts permissions unless your project grants them to other roles: - scripts.read — see the scripts list and open scripts. - scripts.execute — fill in results, data, and evidence. - scripts.sign — sign slots assigned to you or unassigned; scripts.sign.override signs any slot. - scripts.create / scripts.update / scripts.delete — manage scripts (authoring happens on the web). The project owner can always do everything. If you can't see the Scripts screen or can't edit a script, ask a project admin to grant your role the needed permissions. ## Script won't save or complete — troubleshooting If the runner misbehaves: - "On this phone" stays in the header — your entries are safe on the phone but have not been sent yet. Check your internet connection; they are sent by themselves when it returns, or open the Sync screen and tap Sync now. On an older version of the app that shows a stuck "Saving…" instead, check your connection and update the app. - A line under the header says items need your attention — tap Review and decide each one on the Sync screen. - "This phone could not keep your change. Restart the app and try again." — the entry was not saved. Close and reopen the app, then enter it again. - No Complete script button — some items are not done yet, or the button reads Sign off to complete because a required signature is missing. - "Failed to complete script" with no list — you are probably on an older version of the app, and a data field is blank or outside its expected range. Update the app to see the list and the Complete anyway choice, fix the values and try again, or complete the script from the web app. - Can't edit anything — the script is completed and locked; use Reopen. If Reopen is unavailable, you may lack the needed scripts permissions (admin-only by default). - List empty or erroring — pull down to refresh, clear search and status filters, and confirm with a project admin that your role has scripts.read. --- # Security — Two-Factor Authentication & Active Sessions Cx Assistant help · platform: mobile · module: security · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/security ## Opening the Security screen To open the Security settings: 1. Open the side drawer by tapping ☰. 2. Tap your profile card at the bottom of the drawer to open your Profile. 3. On the Profile screen, tap the Security row ("Two-factor authentication and active sessions"). The Security screen shows the status of each two-factor authentication (2FA) method, your backup codes options, and a row that opens the Active sessions screen. ## What is two-factor authentication Two-factor authentication (2FA) adds a second layer of security to your account. After entering your password, you are also asked for a temporary code from a second source — either an authenticator app or your email. This means that even if someone discovers your password, they cannot sign in without also having access to your phone or email. CX Assistant supports two 2FA methods: - Authenticator app (TOTP): A time-based 6-digit code from apps like Google Authenticator, Microsoft Authenticator, or Authy. - Email OTP: A 6-digit code sent to your registered email each time you sign in. ## Set up authenticator app (TOTP) Step-by-step to enable authenticator app 2FA: 1. On the Security screen, tap Set up Authenticator app. 2. A QR code appears. Open your authenticator app (Google Authenticator, Microsoft Authenticator, Authy, etc.) and scan it. 3. If you cannot scan, copy the secret key shown and enter it manually into your authenticator app. 4. Your authenticator app will now show a 6-digit code that refreshes every 30 seconds. 5. Enter the current 6-digit code in the verification field and confirm. 6. On success, your backup codes are shown. Save them securely — you can share them to a safe place using the share option. After setup, you will be asked for an authenticator code every time you sign in. ## Set up email OTP (one-time password) Step-by-step to enable email OTP: 1. On the Security screen, tap Set up Email code. 2. We immediately send a 6-digit code to your registered email address. 3. Open your email and find the code (check spam if needed). 4. Enter the 6-digit code in the verification field and confirm. After setup, you will receive a 6-digit email code every time you sign in. ## Backup codes — save and share them securely Backup codes are shown when you enrol an authenticator app. They are single-use emergency codes that let you sign in if you ever lose access to your phone or authenticator app. What to do with backup codes: - Use the share button to send them to a safe place via your device's share sheet — for example a password manager or a secure note app. - Do NOT store them on the same device as your authenticator app. - Each code can only be used once — it is invalidated immediately after use. If you have used most of your codes or lost them, regenerate a fresh set from the Security screen while signed in. ## Regenerate backup codes If you have used most of your backup codes or want a fresh set: 1. On the Security screen, tap Regenerate backup codes. 2. You will be asked to enter a 6-digit code from your authenticator app to confirm it is you. 3. Enter the code and confirm. 4. A new set of backup codes appears — the old codes are immediately invalidated. 5. Save the new codes securely (you can share them to a safe place via the share sheet). Regenerating requires the authenticator app (TOTP) method to be enabled on your account. ## Disable authenticator app To turn off authenticator app 2FA: 1. On the Security screen, tap Disable Authenticator app. 2. A sheet appears asking for your account password — disabling any 2FA method always requires your password. 3. Enter your password and tap Disable. After disabling, authenticator-based 2FA will no longer be required at sign-in. If you also have email OTP enabled, that still applies. We recommend keeping at least one 2FA method enabled at all times. ## Disable email OTP To turn off email OTP 2FA: 1. On the Security screen, tap Disable Email code. 2. A sheet appears asking for your account password — disabling any 2FA method always requires your password. 3. Enter your password and tap Disable. After disabling, you will no longer receive a code by email at sign-in. ## Two-factor authentication status The Security screen clearly shows the current status of each 2FA method: - Enabled: the method is active and will be offered at sign-in. - Not enabled: the method is inactive. You can have both the authenticator app and email OTP enabled at the same time. At sign-in, the verification screen shows a tab for each enabled method (plus Backup code) and you choose which to use. ## Active sessions — see where you are signed in The Active sessions screen shows every device or session currently signed in to your account — one row per session. Each row shows: - A friendly device name or type (e.g. iPhone, Android device, Mac). - The sign-in location or IP address. - How recently that device was active (relative time). Your current device is highlighted so you can tell it apart. Review this list regularly — if you see a device you do not recognize, revoke it immediately and change your password. ## Opening the Active sessions screen To view your active sessions: 1. Open your Profile (drawer → profile card at the bottom) and tap Security. 2. On the Security screen, tap the Active sessions row. The screen loads the current list of signed-in sessions from the server. Pull down and release to refresh it at any time. ## Sign out a single device (revoke session) To sign out one specific device: 1. Find the session row in the Active sessions list. 2. Tap the sign-out control on that row. 3. Confirm in the dialog — that device will need to sign in again. The session is revoked immediately. The next time that device tries to use the app, it is redirected to the sign-in screen. ## Sign out all other devices To sign out every device except the one you are currently using: 1. On the Active sessions screen, tap Sign out other devices. 2. Confirm in the dialog. Your current device remains signed in; all other sessions are revoked. Use this if you think your account has been accessed without your permission. ## Unrecognized session — what to do If you see a session from a device or location you do not recognize: 1. Revoke that session immediately from the Active sessions screen. 2. Change your password (Profile → Change password). 3. Enable two-factor authentication if you have not already. 4. If you still believe your account is compromised, contact support (Profile → Support). ## Security best practices - Enable at least one 2FA method for your account. - Use a unique, strong password (do not reuse passwords from other services). - Review your active sessions periodically and revoke devices you no longer use. - Save your backup codes somewhere safe, off this device. - If your phone is lost or stolen, sign in from another device and revoke all other sessions. --- # Create an Account Cx Assistant help · platform: mobile · module: sign-up · updated 2026-10-03 Canonical: https://cx-assistant.com/en/help/mobile/sign-up ## How to create an account Step-by-step: 1. On the sign-in screen, tap the sign-up link. 2. Fill in your Name (required, at least 2 characters). 3. Fill in your Surname (optional). 4. Enter your email address. This will be your login and the address we use to contact you. 5. Enter a password, and re-enter it in the Confirm password field. 6. Tick both checkboxes — one to agree to the Terms of Service and one to accept the Privacy Policy (needs an up-to-date version of the app). Tap the links in the labels to read them inside the app first. 7. Tap Create account. After submitting, you will see a "Check your email" success screen. We send a confirmation link to the address you entered, and you must open that link before you can sign in. ## Registration field guidance Name: Your given name, at least 2 characters. Shown to teammates and in notifications. Surname (optional): Helps teammates identify you in lists. Email: Use an address you can access — you'll need to confirm it. It is also used for login and password resets. Password: At least 8 characters, with at least one uppercase letter, one lowercase letter and one number. Avoid simple patterns like '12345678' or 'password'. Confirm password: Must exactly match the Password field. Terms & Privacy: You must tick both acceptance checkboxes to proceed — the Terms of Service and the Privacy Policy each have their own. Tap the links to read the full documents in the in-app viewer before accepting. ## Show or hide password during registration Tap the eye icon on the right side of the Password or Confirm password fields to see what you are typing. This helps avoid mismatches when setting up your password on a mobile keyboard. ## Accepting the Terms of Service and Privacy Policy You must accept the Terms of Service and Privacy Policy to create an account. Each has its own checkbox; if you tap Create account with either one unticked, a message under that checkbox tells you it is required. Tap the Terms of Service or Privacy Policy link in its checkbox label to open and read the full documents in the app's built-in viewer, then return to the form to finish signing up. By accepting, you agree to how CX Assistant stores and uses your data. You can re-read both documents at any time later from Profile → Legal. ## Confirm your email after registration After creating your account, you will see a "Check your email" success screen. We send a confirmation email to the address you registered with. 1. Open your email inbox. 2. Look for a confirmation email from CX Assistant. 3. Tap the confirmation button or link inside the email. 4. Once confirmed, return to the app and sign in. If you cannot find the email, check your spam or junk folder. ## Resend confirmation email If you did not receive the confirmation email or it has expired: 1. On the "Check your email" screen, tap Resend confirmation email. 2. A new link will be sent to your registered address. 3. Check both your inbox and spam folder. If you still do not receive it after a few minutes, make sure the email address you used is correct. If not, register again with the correct address. ## Common registration errors - Email already registered: An account with that email already exists. Try signing in or use Forgot password to recover access. - Passwords do not match: Make sure the Password and Confirm password fields contain exactly the same text. - Password too short or too simple: Use at least 8 characters, with at least one uppercase letter, one lowercase letter and one number. - Terms not accepted: You must tick both acceptance checkboxes — Terms of Service and Privacy Policy — before submitting. - Unable to reach the server: Check your internet connection and try again. ## Already have an account If you already have an account, tap Sign in at the bottom of the registration form to go back to the sign-in screen. You do not need to create a new account. Once signed in, your next step is usually joining a project — ask a project admin for an 8-character invite code and enter it on the Join a Project screen. The code only works for the email address the invite was sent to, so sign in with that address. Until you join a project you are in My Workspace, where you can chat with the assistant and keep your own files (needs an up-to-date version of the app). To create a new project, the Join a Project screen links to the web platform. --- # Support Cx Assistant help · platform: mobile · module: support · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/mobile/support ## How to submit a support ticket To contact support from the app: 1. Open the drawer (hamburger icon or swipe right from the left edge) and tap your profile card at the bottom. 2. Tap the Support row. 3. Pick a reason: Subscription, Technical, Account, Feature request, or Other. 4. Describe your problem or request in the details field. 5. Submit. You receive a ticket id with a copy-to-clipboard button — keep it to reference your request in any follow-up. ## Where to find Support in the app Support lives inside your profile: open the drawer, tap your profile card (avatar, name, and email at the bottom of the drawer), then tap the Support row. Support is account-level — you don't need a project or any special permission to use it. ## Other ways to reach support — email and web Besides the in-app ticket form, the Support screen links to: - The web support centre, for browsing help and managing requests from a browser. - Email: support@cx-assistant.com. Use whichever channel suits you; the in-app form is the quickest from your phone, and quoting your ticket id in emails helps the team find your case. ## Where to find the Terms and Privacy Policy The legal documents are available inside your profile: open the drawer, tap your profile card at the bottom, and find the Privacy & Legal section with Terms of Service and Privacy Policy rows. Each opens the full document in an in-app viewer. --- # Account and security in the Word add-in Cx Assistant help · platform: word · module: account · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/word/account ## How to open the account view Click the account icon in the top bar of the Cx Assistant pane. The account view opens over the chat (your conversation stays open behind it and is right where you left it when you close the view). The account view has five tabs: Profile, Security, Sessions, Activity, and Legal. ## Profile — your name and avatar The Profile tab is where you manage your personal details, such as your name and avatar. Changes here apply to your account everywhere — the same profile is used on the web, mobile, and in the Office add-ins. ## Security — two-factor authentication, backup codes, and password The Security tab protects your account: - Two-factor authentication (2FA): enable a second sign-in step using an authenticator app or email codes. - Backup codes: one-time codes to get in if you lose access to your 2FA method — store them somewhere safe. - Change password: update your account password. Once 2FA is on, signing in to the add-in will show a 2FA challenge after your password. ## Sessions — see and revoke signed-in devices The Sessions tab lists the devices and apps currently signed in to your account. If you see a session you don't recognise, or you left yourself signed in somewhere, revoke it — that device is signed out immediately. ## Activity and Legal tabs - Activity: a log of recent activity on your account, useful for checking what happened and when. - Legal: the terms and privacy documents that apply to your account. ## Colour mode and logging out The colour-mode toggle and sign out are not in the account view — they live in the history panel footer: 1. Click the history toggle (≡) in the top bar of the pane. 2. In the footer at the bottom of the panel, next to your name, use the colour-mode toggle to switch between light and dark mode. 3. To sign out, click the ⋮ button in the same footer and choose "Sign out". The same menu has "Help & support". --- # Using the assistant in Word Cx Assistant help · platform: word · module: assistant · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/word/assistant ## Tour of the chat pane The Cx Assistant pane has three main areas: - Top bar: the history toggle (≡) to open your chat list and project selector, the Cx logo, the account icon, and the new-chat icon. Help & support is in the ⋮ menu in the footer of the history panel. - Middle: the conversation — your messages, the assistant's answers, a thoughts timeline while it works, and status lines showing which actions it is running. At the top of the conversation, a small bar lets you pick how edits reach your document: Direct, Review, or Preview. - Bottom: the composer where you type, with buttons for attachments, voice input, mentions, the approval-mode picker, and the thinking-mode picker. In personal mode (My Workspace), a banner under the top bar says so. ## How to ask the assistant a question Type your question or request in the composer at the bottom of the pane and send it. You can ask about your project (issues, assets, documents, project data) or ask the assistant to work on the open document — for example "Summarise the open issues for asset UPS-001 and insert a table here". While the assistant works, you will see its thoughts timeline and status lines for the actions it takes. To start a fresh conversation, click the new-chat icon in the top bar. ## Chat history — finding your previous chats Click the history toggle (≡) in the top bar to slide open the history panel. It shows: - The selector at the top, where you pick a project or My Workspace. - Your list of Word chats — click one to reopen it, and use its menu to rename or delete it. Scroll down and load more to see older chats. - A footer with your avatar, the light/dark colour-mode toggle, and a ⋮ menu with "Help & support" and "Sign out". The list shows the chats of the project (or My Workspace) that is selected. Switch the selector to see the chats of another project. Only chats you started in Word appear here (see the section on host-locked chats). ## Why some chats are missing — Word chats are host-locked Chats in the add-in belong to the app they were started in. Your history panel in Word lists only Word chats: - Chats you started on the web or mobile app do not appear in Word. - Chats you started in the Excel add-in do not appear either, and trying to open an Excel chat from Word is refused with a message that the chat belongs to the other add-in. This is by design — Word chats can act on your document, so they stay in Word. To continue a web or mobile conversation, open it in that app. ## How to switch projects 1. Click the history toggle (≡) in the top bar. 2. Use the selector at the top of the panel to pick a different project, or pick My Workspace to work without a project (personal mode). The assistant then works in the context of what you selected, and the chat list shows the chats of that project. In My Workspace the assistant cannot see project data such as issues and assets — see "Personal mode — what works and what needs a project" in the getting-started help. ## Approval modes — controlling when the assistant asks before editing Before the assistant changes your document, you decide how much it should ask. Use the approval-mode picker in the composer — the setting applies per chat: - Auto: the assistant runs actions without asking. - Ask for critical: only critical actions, such as permanent deletions, ask first. - Ask for edits: every action that writes to your document or project asks first. Reading never requires approval. All document edits count as writes, so in "Ask for edits" mode nothing changes in your document without your confirmation. Approval modes decide WHETHER the assistant asks before it acts. The review modes (Direct, Review, Preview) decide HOW an edit lands in your document — see "Review modes". Picking Preview in the review bar switches this picker to "Ask for edits" for you. ## Review modes — Direct, Review, and Preview A small bar at the top of the conversation sets how the assistant's edits reach your document. It has three modes. Hover over a mode to read what it does. - Review (the default): edits to existing text become tracked changes in Word. New content, such as a new section or table, becomes a proposal: it is placed in the document inside a blue box titled "Cx Assistant proposal". You then accept or reject the tracked changes, and keep or discard the proposal. - Direct: changes are applied at once. The chat shows an Undo button under the change. - Preview: the assistant asks before every change. The approval card shows what it is about to insert or rewrite. Approved changes are applied directly, with an Undo button. Good to know: - If Track Changes is already on in Word, every change from the assistant is a tracked change, in any mode. New content is then a tracked insertion, not a boxed proposal. - The mode you pick is remembered on this computer and applies to the next change the assistant makes. - The assistant never accepts or rejects its own changes. That decision is always yours. - Comments are not part of the review flow. They are added straight away. - On some older Word builds the changes are tracked, but they can only be accepted or rejected on Word's Review tab. On builds that cannot track changes for the add-in at all, edits are applied directly. - The review bar exists in Word only. ## How to review the assistant's edits — accept, reject, keep, or discard After the assistant changes your document, a review card appears in the chat under that action. The card shows: - How the change was made: "Tracked changes", "Proposal", or "Applied". - A short count, for example "2 paragraphs edited". - The changed text, with added words underlined and removed words struck through. To review a change: 1. Click the target icon ("Show in document") on the card to jump to the change in Word. 2. For tracked changes, click Accept or Reject. 3. For a proposal, click Keep to make the content a normal part of the document, or Discard to remove it. You can also review in Word itself: use Accept and Reject on Word's Review tab, or delete a proposal box. The next time the card checks the document, it shows "Handled in Word". A pending change stays pending until you decide. Proposals and tracked changes are saved with the document, so you can decide later, even after closing and reopening Word. ## How to accept or reject all changes at once When changes from the current chat are waiting for you, a second strip appears under the review bar. It shows the count, for example "3 changes awaiting your decision". 1. Click "Accept all" to accept every pending tracked change and keep every pending proposal from this chat. 2. Or click "Reject all" to reject and discard them all. This only touches changes the assistant made in this chat. Tracked changes from you or other authors are left alone. ## How to undo a change that was applied directly In Direct and Preview mode, changes are applied at once. To take one back: 1. Find the review card under that action in the chat. 2. Click Undo. The card then shows "Undone". Good to know: - If you edited a paragraph yourself after the assistant changed it, Undo leaves that paragraph alone. - Some changes have no Undo button in the chat, such as formatting and table structure changes. Use Word's own Undo (Ctrl+Z) for those. - The Undo button is available while the pane stays open. After you close and reopen the pane, use Word's own Undo or edit the text by hand. ## The approval card — approving or declining pending actions When the assistant needs your approval, the pending actions appear together in one approval card in the chat: - Each row has a checkbox, so you can approve only some of the actions (partial approval). - Use Approve to run the checked actions, or Decline all to reject the batch. - Some rows offer a "don't ask again in this chat" option for that kind of action — tick it to auto-approve it for the rest of the conversation. For document edits, the row also previews the change: the text that will be inserted, or the wording that will be replaced. ## Attachments, voice input, and mentions The composer supports more than text: - Attachments: attach files to your message for the assistant to use. - Voice input: dictate your message instead of typing. - Mentions: reference project items directly in your message so the assistant knows exactly what you mean. ## Citations — opening issues, assets, and documents from a chat When an answer draws on project data, the assistant adds citation chips to its reply. Click a chip to open the source without leaving Word: - Issues open in an Edit Issue dialog inside the pane. - Assets open in an Edit Asset dialog. - Documents open in a document viewer. This lets you check the source, and update issues or assets, right from the conversation. ## The account view Click the account icon in the top bar to open the account view (your chat stays open behind it). It has five tabs: - Profile: your name, avatar, and personal details. - Security: two-factor authentication, backup codes, and password change. - Sessions: the devices signed in to your account, with the option to revoke them. - Activity: recent account activity. - Legal: terms and privacy documents. ## How to contact support from the pane To send a support ticket from the pane: 1. Click the history toggle (≡) in the top bar. 2. In the footer of the panel, click the ⋮ button and choose "Help & support". 3. Pick the reason that best matches your request from the reason chips. 4. Describe the details. 5. Submit the ticket. The dialog also links to the public support centre at cx-assistant.com/en/support/word if you prefer browsing help articles. ## Permissions — the assistant respects your project role Using the assistant in Word requires the agents.word permission, which every project role has by default. Everything the assistant does with project data (issues, assets, documents, and so on) is checked against YOUR permissions in the active project. It can never read or change anything you could not read or change yourself. If the assistant reports it cannot do something in the project, ask a project admin to review your role. Personal mode (My Workspace) needs no project role. My Workspace is yours alone, and the assistant sees no project data there. ## Troubleshooting the assistant in Word Common situations and what they mean: - You were signed out: sessions expire or can be revoked — sign in again from the pane. - You see a "Personal mode" banner, or the assistant says it needs a project: the pane is in My Workspace, where the assistant cannot see issues, assets, or project documents. Open the history panel (≡) and pick a project in the selector. With no project yet, the pane always opens in personal mode. - A chat is missing after you switched project: the chat list shows the chats of the selected project or My Workspace only. Switch back to find it. - A chat is missing or refuses to open: it probably belongs to another app. Word only shows Word chats; Excel, web, and mobile chats live in their own apps. - A write timed out: the assistant is told the edit may still have landed, so it checks your document with a read before retrying. You may notice it verifying — this prevents duplicate edits. - An action seems stuck: an action that cannot finish fails with a clear error after about 4 minutes, and the pane stays usable. This often happens when a dialog box is open in Word. Close the dialog and ask again. The edit may still have landed, so check the document first. - A review card says "Handled in Word": the change was already accepted, rejected, or removed in Word itself, so there is nothing left to decide. - Comments don't work: comment features need a newer Word build (see the getting-started requirements). --- # What the assistant can do in your document Cx Assistant help · platform: word · module: document-tools · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/word/document-tools ## What the assistant can do in your Word document The assistant works directly on the document you have open. It can read it (your selection, the outline, a full map of paragraphs, tables, images and charts), search it, insert rich content including tables and charts, edit or delete text, run find and replace, format text, and manage comments. It also combines document work with your project data — for example, pulling open issues from your project and inserting them as a table in the document. Just describe what you want in plain language. ## Reading your document — selection, outline, full map, search, statistics The assistant can look at your document in several ways: - Your current selection: select some text and ask about it, e.g. "Rewrite this selection more formally". - The outline: it can read the heading structure to understand how the document is organised. - A full document map: every paragraph, table, image, and chart, each with its position, so it can target edits precisely. - Text search: "Find every mention of 'generator'". - Statistics: word counts and similar figures about the document. - Pending changes: "What is still waiting for review?" lists the tracked changes and proposals in the document. Reading never changes your document and never requires approval. ## Inserting rich content — headings, lists, tables, code, and charts Ask the assistant to write content and it inserts properly formatted Word content, not plain text: - Headings, bold and italic text, and nested lists. - Tables — e.g. "Insert a table of the open issues for this asset". - Code blocks. - Charts: column, bar, line and pie, e.g. "Add a bar chart of issue priorities". Each chart is inserted as a picture with a description for screen readers and, if you ask, a numbered caption. Content can be inserted at the end of the document or at a specific position (see the next section). ## Inserting at a specific position You control where new content goes. The assistant can insert at the end of the document or after a specific paragraph. Point it at the spot in plain language: - "Insert the summary after the 'Scope' heading". - "Add this table at the end of section 2". - "Put a new heading right before the conclusion". Because the assistant can map every paragraph with its position, it can place content precisely where you ask. ## Editing text — replace, delete, find and replace, format The assistant can change existing text: - Replace or delete a range of paragraphs: "Replace section 3 with the updated procedure". - Replace or delete your current selection: select text and say "Delete this" or "Rewrite this paragraph". - Document-wide find and replace: "Replace every occurrence of 'Site A' with 'Site B'". - Change wording inside a paragraph: "Fix the voltage in the second paragraph — it should be 400 V". Where possible, only the words that change are marked as changed, not the whole paragraph. - Format the selection: change the font of the text you have selected. In Review mode (the default), edits to existing text arrive as tracked changes that you accept or reject. See "Review modes" in the assistant help. Depending on your approval mode, an edit may also be shown to you for approval before it runs. ## Deleting tables, charts, and images The assistant can remove objects from the document, not just text. Tables, charts, and images are identified by their position in the document map, so you can say things like: - "Delete the second table". - "Remove the chart in section 4". - "Delete the image after the introduction". If you are unsure which object is which, ask for the document map first — the assistant lists every table, image, and chart with its index. ## Tables, footnotes, paragraph styles, and ready-made blocks Beyond plain text, the assistant can work with these parts of a document: - Existing tables: change cell text, add or delete rows and columns, set a table style, repeat the header row, or set column widths — "Add a row for pump P-102 to the second table". - Footnotes and endnotes: "Add a footnote after 'IEC 61439' with the full standard title". This needs a newer Word build. - Paragraph styles and layout: apply a heading or other built-in style, change alignment and spacing, or make text bold, italic, or highlighted — "Make these three lines Heading 2". - Ready-made blocks: a callout, a status table, a row of key figures, a figure with a numbered caption, a signature block, a cover page, or a checklist — "Insert a sign-off block at the end". Blocks use your document's own fonts and styles. In Review mode, a new block arrives as a proposal you keep or discard, and table or footnote edits arrive as tracked changes. ## Working with comments The assistant can manage Word comments for you: - List all comments with their surrounding context. - Add a comment anchored to your current selection, to a specific paragraph, or to text it finds by searching — e.g. "Find every mention of 'generator' and add a comment asking for a spec reference". - Reply to a comment. - Resolve or re-open a comment. - Delete a comment. Comments are added straight away. They are not tracked changes, so they get no review card, whatever review mode you use. Note: comment features need a newer Word build (Word API 1.4+). On older versions of Word, the assistant cannot work with comments while everything else keeps working. ## Approvals — you confirm before the document changes Every action that modifies your document is a write, and writes follow your chat's approval mode: - Auto: edits run without asking. - Ask for critical: only critical actions ask first. - Ask for edits: every document edit shows an approval card first — nothing changes until you approve. The approval card lists each pending action with a checkbox, so you can approve some and decline others. For document edits it also previews the text. Reading your document never asks for approval. Approvals happen BEFORE an edit. Reviewing happens AFTER it: in Review mode the edit lands as tracked changes or as a proposal, and you accept, reject, keep, or discard it. See "Review modes" and "How to review the assistant's edits" in the assistant help. ## Good example prompts for document work Some prompts that show what the assistant does well in Word: - "Summarise the open issues for asset UPS-001 and insert a table here". - "Add a commissioning summary section with a bar chart of issue priorities". - "Find every mention of 'generator' and add a comment asking for a spec reference". - "Replace section 3 with the updated procedure". - "Give me the document outline and statistics". Combine project data with document edits in a single ask — that is where the add-in shines. ## Limits and good to know A few things to keep in mind: - The assistant works on the document currently open next to the pane, and the pane must be open for it to act. - Edits happen in YOUR open copy of the document — you keep normal control over saving. - Charts are pictures, not Word chart objects: they do not open in Word's chart editor. To change one, ask the assistant to replace it. - Comments need a newer Word build (Word API 1.4+). - If a write times out, the assistant checks the document with a read before retrying, so an edit is not applied twice. - An action that cannot finish fails with a clear error after about 4 minutes instead of hanging. An open dialog box in Word is a common cause. - The assistant never accepts or rejects tracked changes for you. You decide, in the chat or on Word's Review tab. - Tracked changes appear under your own name in Word, because Word records the signed-in user as the author. - Footnotes, comments, and tracked changes need a newer Word build. On a Word version that cannot track changes for the add-in, edits are applied directly. - Project actions (creating issues, reading documents, and so on) always respect your project permissions. In personal mode (My Workspace) there are no project actions. --- # Getting started with the Cx Assistant Word add-in Cx Assistant help · platform: word · module: getting-started · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/word/getting-started ## What is the Cx Assistant Word add-in The Cx Assistant Word add-in brings your project assistant into Microsoft Word as a task pane. You chat with the assistant right next to your document: ask about issues, assets, and documentation in your project, and let the assistant read and edit the open document for you — insert sections, tables and charts, find and replace text, add comments, and more. Everything the assistant does respects your project permissions: it can never see or change more than you can. No project yet? The add-in also works without one. In personal mode the assistant works on the open document and on your own My Workspace files (see "How to use the add-in without a project"). ## How to install the add-in from the Office Add-ins store Install Cx Assistant from the Office Add-ins store: 1. In Word, go to Insert and click Add-ins (in Word on the web, Add-ins is on the Home tab). 2. Search for "Cx Assistant". 3. Click Add. After installing, an "Open Cx Assistant" button appears on the Home tab. For a full step-by-step install guide with screenshots, see cx-assistant.com/en/install/word. ## How to open the Cx Assistant pane To open the assistant: 1. In Word, go to the Home tab. 2. In the Cx Assistant group, click Open Cx Assistant. The task pane opens on the side of your document. The first time, a short get-started callout points you to the support page. If you are not signed in yet, you will see the sign-in screen first. ## Signing in and creating an account When the pane opens without an active session, you will see the sign-in screen: 1. Enter your email and password and sign in. 2. If two-factor authentication is enabled on your account, complete the 2FA challenge that appears. Forgot your password? Use the forgot-password link on the sign-in screen. New to Cx Assistant? You can create an account directly in the pane using the sign-up option — no need to leave Word. After you sign up, we send a confirmation link to your email. Open the link to activate your account, then sign in. If the email does not arrive, use the resend option on the same screen. You do not need a project to sign in. If you have no project yet, the pane opens in personal mode. ## How to choose a project or My Workspace After you sign in, the pane picks where the assistant works: - If you belong to one or more projects, it opens in your first project. - If you have no project yet, it opens in My Workspace (personal mode). To change it: 1. Click the history toggle (the ≡ icon) in the top bar of the pane. 2. Open the selector at the top of the panel that slides in. 3. Pick a project, or pick My Workspace ("Your personal files"). The pane remembers your choice the next time you open it. The same selector also has a "Create a project" entry, which opens the Cx Assistant web app in your browser. ## How to use the add-in without a project (personal mode) You can use Cx Assistant in Word without any project. This is personal mode: the assistant works on the open document and on your own My Workspace files only. If you have no project, the pane opens in personal mode by itself. If you have projects, switch to it like this: 1. Click the history toggle (≡) in the top bar of the pane. 2. Open the selector at the top of the panel. 3. Pick My Workspace. You know you are in personal mode when a banner under the top bar says "Personal mode — working with your My Workspace files only." The welcome screen also shows different quick prompts, such as "Improve the selection" and "Summarize a file into this document". To go back to project work, open the same selector and pick a project. Your chats are kept per project and per My Workspace, so the chat list changes when you switch. ## Personal mode — what works and what needs a project What works in personal mode: - Everything the assistant does in the open document: reading, writing, editing, formatting, tables, charts, and comments. The review modes (Direct, Review, Preview) work the same way. - Reading and summarizing files you attach to the chat, and files you uploaded to My Workspace. - Organizing your My Workspace files and folders. - Engineering questions and web search. - Questions about how Cx Assistant works. - Notes and preferences you ask the assistant to remember. What needs a project: - Issues, RFIs, and assets — finding, creating, or updating them. - Inserting live project data into the document, such as a table of open issues. - Reading project documents. In personal mode the assistant cannot see any of your projects. If you ask for something that needs a project, it tells you so and explains how to get one. To create a project, click "Create a project" in the personal mode banner or in the selector. This opens the Cx Assistant web app in your browser — projects are created there, not in the add-in. A colleague can also invite you to an existing project. Afterwards, close and reopen the Cx Assistant pane and pick the project in the selector. If the project is not listed, sign out and sign in again. ## Quick prompts on the welcome screen When you start a new chat, the welcome screen offers quick prompts to get going with one click. In a project: - Create issue - Open issues - Issues summary In personal mode (My Workspace): - Improve the selection - Summarize a file into this document - What can you do here? - How do I create a project? Click one to start a conversation on that topic, or type your own question in the composer at the bottom of the pane. ## Requirements — which versions of Word are supported The add-in works in Word on the web and in Word desktop on Windows and Mac with a Microsoft 365 subscription. Technically, the add-in needs Word API 1.3 or newer, which recent Microsoft 365 builds provide. Working with comments through the assistant needs a slightly newer Word (Word API 1.4+); if your Word build is older, comment features may not be available while everything else keeps working. The same goes for footnotes and for reviewing the assistant's edits as tracked changes: they need a recent Word build, and on older builds edits are applied directly instead. ## Where to get help and support You have several ways to get help: - Ask the assistant. It can answer questions about how Cx Assistant works. - Send a support ticket: click the history toggle (≡), click the ⋮ button in the footer of the panel, and choose "Help & support". Pick a reason, add details, and submit. - Visit the public support centre at cx-assistant.com/en/support/word. The support dialog also links to the support centre if you prefer browsing articles. --- # Account and security in the Excel add-in Cx Assistant help · platform: excel · module: account · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/excel/account ## How to open the account view Click the account icon in the top bar of the Cx Assistant pane. The account view opens over the chat (your conversation stays open behind it and is right where you left it when you close the view). The account view has five tabs: Profile, Security, Sessions, Activity, and Legal. ## Profile — your name and avatar The Profile tab is where you manage your personal details, such as your name and avatar. Changes here apply to your account everywhere — the same profile is used on the web, mobile, and in the Office add-ins. ## Security — two-factor authentication, backup codes, and password The Security tab protects your account: - Two-factor authentication (2FA): enable a second sign-in step using an authenticator app or email codes. - Backup codes: one-time codes to get in if you lose access to your 2FA method — store them somewhere safe. - Change password: update your account password. Once 2FA is on, signing in to the add-in will show a 2FA challenge after your password. ## Sessions — see and revoke signed-in devices The Sessions tab lists the devices and apps currently signed in to your account. If you see a session you don't recognise, or you left yourself signed in somewhere, revoke it — that device is signed out immediately. ## Activity and Legal tabs - Activity: a log of recent activity on your account, useful for checking what happened and when. - Legal: the terms and privacy documents that apply to your account. ## Colour mode and logging out The colour-mode toggle and sign out are not in the account view — they live in the history panel footer: 1. Click the history toggle (≡) in the top bar of the pane. 2. In the footer at the bottom of the panel, next to your name, use the colour-mode toggle to switch between light and dark mode. 3. To sign out, click the ⋮ button in the same footer and choose "Sign out". The same menu has "Help & support". --- # Using the assistant in Excel Cx Assistant help · platform: excel · module: assistant · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/excel/assistant ## Tour of the chat pane The Cx Assistant pane has three main areas: - Top bar: the history toggle (≡) to open your chat list and project selector, the Cx logo, the account icon, and the new-chat icon. Help & support is in the ⋮ menu in the footer of the history panel. - Middle: the conversation — your messages, the assistant's answers, a thoughts timeline while it works, and status lines showing which actions it is running. - Bottom: the composer where you type, with buttons for attachments, voice input, mentions, the approval-mode picker, and the thinking-mode picker. In personal mode (My Workspace), a banner under the top bar says so. ## How to ask the assistant a question Type your question or request in the composer at the bottom of the pane and send it. You can ask about your project (issues, assets, documents, project data) or ask the assistant to work on the open workbook — for example "Read the punch list on Sheet1 and create issues for the open rows". While the assistant works, you will see its thoughts timeline and status lines for the actions it takes. To start a fresh conversation, click the new-chat icon in the top bar. ## Chat history — finding your previous chats Click the history toggle (≡) in the top bar to slide open the history panel. It shows: - The selector at the top, where you pick a project or My Workspace. - Your list of Excel chats — click one to reopen it, and use its menu to rename or delete it. Scroll down and load more to see older chats. - A footer with your avatar, the light/dark colour-mode toggle, and a ⋮ menu with "Help & support" and "Sign out". The list shows the chats of the project (or My Workspace) that is selected. Switch the selector to see the chats of another project. Only chats you started in Excel appear here (see the section on host-locked chats). ## Why some chats are missing — Excel chats are host-locked Chats in the add-in belong to the app they were started in. Your history panel in Excel lists only Excel chats: - Chats you started on the web or mobile app do not appear in Excel. - Chats you started in the Word add-in do not appear either, and trying to open a Word chat from Excel is refused with a message that the chat belongs to the other add-in. This is by design — Excel chats can act on your workbook, so they stay in Excel. To continue a web or mobile conversation, open it in that app. ## How to switch projects 1. Click the history toggle (≡) in the top bar. 2. Use the selector at the top of the panel to pick a different project, or pick My Workspace to work without a project (personal mode). The assistant then works in the context of what you selected, and the chat list shows the chats of that project. In My Workspace the assistant cannot see project data such as issues and assets — see "Personal mode — what works and what needs a project" in the getting-started help. ## Approval modes — controlling when the assistant asks before editing Before the assistant changes your workbook, you decide how much it should ask. Use the approval-mode picker in the composer — the setting applies per chat: - Auto: the assistant runs actions without asking. - Ask for critical: only critical actions, such as permanent deletions, ask first. - Ask for edits: every action that writes to your workbook or project asks first. Reading never requires approval. All workbook edits count as writes, so in "Ask for edits" mode nothing changes in your workbook without your confirmation. In Excel, edits are applied straight to the workbook. There is no tracked-changes review as in the Word add-in, so use "Ask for edits" when you want to check each change before it happens. ## The approval card — approving or declining pending actions When the assistant needs your approval, the pending actions appear together in one approval card in the chat: - Each row has a checkbox, so you can approve only some of the actions (partial approval). - Use Approve to run the checked actions, or Decline all to reject the batch. - Some rows offer a "don't ask again in this chat" option for that kind of action — tick it to auto-approve it for the rest of the conversation. ## Attachments, voice input, and mentions The composer supports more than text: - Attachments: attach files to your message for the assistant to use. - Voice input: dictate your message instead of typing. - Mentions: reference project items directly in your message so the assistant knows exactly what you mean. ## Citations — opening issues, assets, and documents from a chat When an answer draws on project data, the assistant adds citation chips to its reply. Click a chip to open the source without leaving Excel: - Issues open in an Edit Issue dialog inside the pane. - Assets open in an Edit Asset dialog. - Documents open in a document viewer. This lets you check the source, and update issues or assets, right from the conversation. ## The account view Click the account icon in the top bar to open the account view (your chat stays open behind it). It has five tabs: - Profile: your name, avatar, and personal details. - Security: two-factor authentication, backup codes, and password change. - Sessions: the devices signed in to your account, with the option to revoke them. - Activity: recent account activity. - Legal: terms and privacy documents. ## How to contact support from the pane To send a support ticket from the pane: 1. Click the history toggle (≡) in the top bar. 2. In the footer of the panel, click the ⋮ button and choose "Help & support". 3. Pick the reason that best matches your request from the reason chips. 4. Describe the details. 5. Submit the ticket. The dialog also links to the public support centre at cx-assistant.com/en/support/excel if you prefer browsing help articles. ## Permissions — the assistant respects your project role Using the assistant in Excel requires the agents.excel permission, which every project role has by default. Everything the assistant does with project data (issues, assets, documents, and so on) is checked against YOUR permissions in the active project. It can never read or change anything you could not read or change yourself. If the assistant reports it cannot do something in the project, ask a project admin to review your role. Personal mode (My Workspace) needs no project role. My Workspace is yours alone, and the assistant sees no project data there. ## Troubleshooting the assistant in Excel Common situations and what they mean: - You were signed out: sessions expire or can be revoked — sign in again from the pane. - You see a "Personal mode" banner, or the assistant says it needs a project: the pane is in My Workspace, where the assistant cannot see issues, assets, or project documents. Open the history panel (≡) and pick a project in the selector. With no project yet, the pane always opens in personal mode. - A chat is missing after you switched project: the chat list shows the chats of the selected project or My Workspace only. Switch back to find it. - A chat is missing or refuses to open: it probably belongs to another app. Excel only shows Excel chats; Word, web, and mobile chats live in their own apps. - A write timed out: the assistant is told the edit may still have landed, so it checks your workbook with a read before retrying. You may notice it verifying — this prevents duplicate edits. - An action seems stuck: an action that cannot finish fails with a clear error after about 4 minutes, and the pane stays usable. This often happens when a cell is still being edited or a dialog box is open in Excel. Press Enter or Esc to leave the cell, close the dialog, and ask again. The edit may still have landed, so check the workbook first. --- # Getting started with the Cx Assistant Excel add-in Cx Assistant help · platform: excel · module: getting-started · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/excel/getting-started ## What is the Cx Assistant Excel add-in The Cx Assistant Excel add-in brings your project assistant into Microsoft Excel as a task pane. You chat with the assistant right next to your workbook: ask about issues, assets, and documentation in your project, and let the assistant read and edit the open workbook for you — write values and formulas, build sheets and tables, format ranges, insert charts, and more. Everything the assistant does respects your project permissions: it can never see or change more than you can. No project yet? The add-in also works without one. In personal mode the assistant works on the open workbook and on your own My Workspace files (see "How to use the add-in without a project"). ## How to install the add-in from the Office Add-ins store Install Cx Assistant from the Office Add-ins store: 1. In Excel, go to Insert and click Add-ins (in Excel on the web, Add-ins is on the Home tab). 2. Search for "Cx Assistant". 3. Click Add. After installing, an "Open Cx Assistant" button appears on the Home tab. For a full step-by-step install guide with screenshots, see cx-assistant.com/en/install/excel. ## How to open the Cx Assistant pane To open the assistant: 1. In Excel, go to the Home tab. 2. In the Cx Assistant group, click Open Cx Assistant. The task pane opens on the side of your workbook. The first time, a short get-started callout points you to the support page. If you are not signed in yet, you will see the sign-in screen first. ## Signing in and creating an account When the pane opens without an active session, you will see the sign-in screen: 1. Enter your email and password and sign in. 2. If two-factor authentication is enabled on your account, complete the 2FA challenge that appears. Forgot your password? Use the forgot-password link on the sign-in screen. New to Cx Assistant? You can create an account directly in the pane using the sign-up option — no need to leave Excel. After you sign up, we send a confirmation link to your email. Open the link to activate your account, then sign in. If the email does not arrive, use the resend option on the same screen. You do not need a project to sign in. If you have no project yet, the pane opens in personal mode. ## How to choose a project or My Workspace After you sign in, the pane picks where the assistant works: - If you belong to one or more projects, it opens in your first project. - If you have no project yet, it opens in My Workspace (personal mode). To change it: 1. Click the history toggle (the ≡ icon) in the top bar of the pane. 2. Open the selector at the top of the panel that slides in. 3. Pick a project, or pick My Workspace ("Your personal files"). The pane remembers your choice the next time you open it. The same selector also has a "Create a project" entry, which opens the Cx Assistant web app in your browser. ## How to use the add-in without a project (personal mode) You can use Cx Assistant in Excel without any project. This is personal mode: the assistant works on the open workbook and on your own My Workspace files only. If you have no project, the pane opens in personal mode by itself. If you have projects, switch to it like this: 1. Click the history toggle (≡) in the top bar of the pane. 2. Open the selector at the top of the panel. 3. Pick My Workspace. You know you are in personal mode when a banner under the top bar says "Personal mode — working with your My Workspace files only." The welcome screen also shows different quick prompts, such as "Improve the selection" and "What can you do here?". To go back to project work, open the same selector and pick a project. Your chats are kept per project and per My Workspace, so the chat list changes when you switch. ## Personal mode — what works and what needs a project What works in personal mode: - Everything the assistant does in the open workbook: reading, writing values and formulas, formatting, sheets, tables, and charts. - Reading and summarizing files you attach to the chat, and files you uploaded to My Workspace — for example "Build a table from the datasheet I attached". - Organizing your My Workspace files and folders. - Engineering questions and web search. - Questions about how Cx Assistant works. - Notes and preferences you ask the assistant to remember. What needs a project: - Issues, RFIs, and assets — finding, creating, or updating them. - Filling ranges with live project data, such as a sheet of open issues. - Creating issues from rows in your workbook. - Reading project documents. In personal mode the assistant cannot see any of your projects. If you ask for something that needs a project, it tells you so and explains how to get one. To create a project, click "Create a project" in the personal mode banner or in the selector. This opens the Cx Assistant web app in your browser — projects are created there, not in the add-in. A colleague can also invite you to an existing project. Afterwards, close and reopen the Cx Assistant pane and pick the project in the selector. If the project is not listed, sign out and sign in again. ## Quick prompts on the welcome screen When you start a new chat, the welcome screen offers quick prompts to get going with one click. In a project: - Create issue - Open issues - Issues summary In personal mode (My Workspace): - Improve the selection - Summarize a file into this document - What can you do here? - How do I create a project? Click one to start a conversation on that topic, or type your own question in the composer at the bottom of the pane. ## Requirements — which versions of Excel are supported The add-in works in Excel on the web and in Excel desktop on Windows and Mac with a Microsoft 365 subscription. Technically, the add-in needs Excel API 1.4 or newer, which recent Microsoft 365 builds provide. A few newer features — like merged-cell awareness when reading ranges — need newer Office builds; on older builds they degrade gracefully while everything else keeps working. ## Where to get help and support You have several ways to get help: - Ask the assistant. It can answer questions about how Cx Assistant works. - Send a support ticket: click the history toggle (≡), click the ⋮ button in the footer of the panel, and choose "Help & support". Pick a reason, add details, and submit. - Visit the public support centre at cx-assistant.com/en/support/excel. The support dialog also links to the support centre if you prefer browsing articles. --- # What the assistant can do in your workbook Cx Assistant help · platform: excel · module: workbook-tools · updated 2026-09-19 Canonical: https://cx-assistant.com/en/help/excel/workbook-tools ## What the assistant can do in your Excel workbook The assistant works directly on the workbook you have open. It can read it (a full map of sheets, ranges, tables and charts, plus values, formulas and your selection), search cells, write values and formulas, restructure sheets, format ranges, run find and replace, and insert, update or delete charts. It also combines workbook work with your project data — for example, reading a punch list from a sheet and creating issues in your project from the open rows. Just describe what you want in plain language. ## Reading your workbook — the workbook map Ask the assistant what is in your workbook and it builds a full map: every sheet, its used range, and the tables and charts on it. This is how it finds its way around before reading or editing anything. Example asks: - "What's in this workbook?" - "List the sheets and the tables on each". Reading never changes your workbook and never requires approval. ## Reading ranges, formulas, and your selection The assistant can read exactly what your cells contain: - Values and formulas from any range — it sees the formulas, not just the results. - Your current selection: select some cells and ask about them, e.g. "Explain this selection". The read is merge-aware, so merged cells are reported correctly. - A chart's details: ask about any chart in the workbook. Example: "Read A1:F30 on Sheet2 and tell me which formulas look wrong". ## Searching cells and taking a picture of a range — it can see your sheet Two more ways the assistant understands your data: - Cell search: "Find all cells containing 'TBD' and list them" — it searches across cells and reports where each match is. - Range snapshot: the assistant can take a picture of a range, with row and column coordinates included, so it can literally SEE your sheet — layout, formatting, and all. Useful when the visual arrangement matters, e.g. "Look at the header area and tell me how this report is laid out". ## Writing values and formulas The assistant can fill your sheets for you: - Write values or formulas to any range — "Put a SUM of column D in D31", "Fill B2:B13 with the month names". - Clear ranges you no longer need. Like every workbook edit, writes follow your chat's approval mode, so you can require confirmation before anything lands in the sheet. ## Restructuring — rows, columns, sheets, and tables The assistant can change the structure of your workbook: - Insert or delete rows and columns. - Add, delete, or rename sheets — "Create a new sheet called Summary". - Create or delete tables. Example: "Build a commissioning progress summary on a new sheet with a chart" — the assistant creates the sheet, writes the data, and adds the chart in one go (asking for approval per your approval mode). ## Formatting and auto-fit Ask the assistant to make your sheet presentable: - Format ranges — e.g. "Format the header row", "Make the totals bold". - Auto-fit columns and rows so content is fully visible — "Auto-fit the columns on Sheet1". A popular combined ask: "Format the header row and auto-fit the columns". ## Find and replace across a sheet The assistant can run find and replace across a sheet for you: "Replace every 'Site A' with 'Site B' on the Overview sheet". If you only want to know where something is without changing it, ask it to search instead — "Find all cells containing 'TBD'" — which never modifies the workbook. ## Charts — insert, update, and delete The assistant can manage charts in your workbook: - Insert a chart from your data — around 25 chart types are supported, including the column, bar, line, pie, doughnut, area, and scatter families. - Update an existing chart. - Delete a chart. - Read a chart's details when you ask about one. Example: "Insert a doughnut chart of issues by priority next to the table". ## Merged cells — merging, unmerging, and how they are read The assistant handles merged cells carefully: - It can merge cells (including "merge across", which merges row by row) and unmerge them. - Safety first: if a merge would discard non-empty cells, it refuses by default and lists exactly which cells would lose their content. If that's what you want, tell it to go ahead and it will. - When reading, merged regions are reported as merged spans with their anchor value — the assistant won't mistake a merged heading for repeated data. Note: merged-cell awareness when reading needs a newer Office build; on older builds it degrades gracefully. ## Approvals — you confirm before the workbook changes Every action that modifies your workbook is a write, and writes follow your chat's approval mode: - Auto: edits run without asking. - Ask for critical: only critical actions ask first. - Ask for edits: every workbook edit shows an approval card first — nothing changes until you approve. The approval card lists each pending action with a checkbox, so you can approve some and decline others. Reading your workbook never asks for approval. Approved edits are applied straight to the workbook. The tracked-changes review of the Word add-in does not exist in Excel. ## Good example prompts for workbook work Some prompts that show what the assistant does well in Excel: - "Build a commissioning progress summary on a new sheet with a chart". - "Read the punch list on Sheet1 and create issues for the open rows". - "Find all cells containing 'TBD' and list them". - "Format the header row and auto-fit the columns". - "Read A1:F30 and explain the formulas". Combine project data with workbook edits in a single ask — that is where the add-in shines. ## Limits and good to know A few things to keep in mind: - The assistant works on the workbook currently open next to the pane, and the pane must be open for it to act. - Edits happen in YOUR open copy of the workbook — you keep normal control over saving. - Some newer features, like merged-cell awareness when reading, need newer Office builds and degrade gracefully on older ones. - If a write times out, the assistant checks the workbook with a read before retrying, so an edit is not applied twice. - An action that cannot finish fails with a clear error after about 4 minutes instead of hanging. A cell left in edit mode or an open dialog box in Excel is a common cause. - Project actions (creating issues, reading documents, and so on) always respect your project permissions. In personal mode (My Workspace) there are no project actions, so prompts like "create issues for the open rows" need a project first.