Using AI Tools
Arketic's assistants don't just answer questions — they can look things up for you, create files and images, and take real actions in the platform. You describe what you need in plain language, and the assistant does the work while showing you exactly what it is doing.
This page explains what the assistant can do, how you can tell what is happening, and when it will stop and ask you first.
The Two Kinds of Tool Activity
Everything the assistant does falls into one of two groups.
| Kind | What it is | What you see | Do you approve it? |
|---|---|---|---|
| Looking things up and creating content | Searching documents, checking tasks, reading the org chart, searching the web, writing a document, drawing an image | A live status line in the chat | No — nothing in your data is changed |
| Making a change | Creating a task, updating a status, starting a process, sending something to a connected app | An Action Requires Approval card | Yes — it waits for you |
No action that creates or changes data is ever taken without your explicit approval. If you don't press Approve, nothing happens.
Status Lines: Watching the Assistant Work
While the assistant works on a step, a small status line appears in the chat with an animated symbol and a short label. When the step finishes, the symbol turns into a green check and the label changes to a completed message.
Some examples of what you'll see:
| While it runs | When it finishes |
|---|---|
| Searching documents... | Documents found |
| Reading document... | Document loaded |
| Summarizing document... | Summary ready |
| Searching the web... | Web results ready |
| Loading your tasks... | Tasks loaded |
| Analyzing deadline risks... | Risk analysis complete |
| Loading org chart... | Org chart loaded |
| Creating task... | Task created |
| Writing document... | Document ready |
| Generating image... | Image ready |
If a step doesn't have its own label, you'll simply see Processing... followed by Done.
More than one status line can appear for a single answer. A question like "Find the travel policy and check whether my expense task is overdue" may run a document search and a task lookup, one after the other.
The Tools Menu
The Tools button (the sliders icon) next to the message box opens a menu with two groups: actions that apply to your next message only, and search switches that stay the way you set them.
Actions for One Message
| Action | What the assistant does | Hint shown in the message box |
|---|---|---|
| Create Image | Draws a picture from your description | "What should I draw? Describe the scene…" |
| Create Document | Writes a document and delivers it as a file | "What kind of document? Describe the content and who it is for…" |
| Create Presentation | Builds a slide deck and delivers it as a file | "What should the presentation cover, and who is the audience?…" |
| Summarize File | Reads the whole attached file, then summarizes it | "What should I focus on? (I will read the whole file)" |
To use one:
- Click Tools and choose the action.
- A chip with the action's name appears at the top of the message box, and the placeholder changes to the hint.
- Type what you want and send.
The action applies to that one message. After you send, the chip disappears and the next message is an ordinary one again.
To cancel before sending, click the × on the chip. You can also open Tools again — the chosen action is marked with a check — and click it a second time.
These buttons are shortcuts. You can also ask in words — "draw a…", "write this up as a Word document", "turn this into a presentation" — as long as the assistant has the capability.
When Each Action Is Offered
The menu shows only what the assistant you are talking to is allowed to do, so it can look different from one assistant to another.
| Action | Offered when |
|---|---|
| Create Image | The assistant is allowed to create images |
| Create Document, Create Presentation | The assistant is allowed to create documents |
| Summarize File | The assistant is allowed to read documents and at least one file is attached and waiting under the message box |
In a project chat the actions are available without a per-assistant setting; Summarize File still needs an attached file.
If an action you expect is missing, the assistant was set up without that capability. An admin can change which tools an assistant has — see AI Assistant Configuration.
Search Switches
| Switch | What it does |
|---|---|
| Web Search | Lets the assistant search the internet and cite the pages it used |
| Document Search | Lets the assistant look inside your organization's documents and knowledge |
Each row has a sliding switch that turns sky-blue when it's on. Unlike the actions above, a switch stays the way you left it for the following messages.
A switch only appears if the assistant you're using is allowed to use it. If your assistant was set up without web access, you won't see the Web Search row. In a project chat, both are available. If an assistant has neither switch and none of the actions, the Tools button is not shown.
Knowledge and Document Search
Ask a question about your company's material and the assistant searches your documents and knowledge, then answers using what it found.
"What does the travel policy say about international flights?" "Summarize the employee handbook's section on remote work." "Find the document that describes our onboarding checklist."
Sources under the answer
When an answer is based on documents or web pages, a sources strip appears underneath it.
- Closed, it shows the name of the first source, followed by +N more when there are others.
- Open (click it), the header reads N sources and every source is listed.
| Source type | What the row shows |
|---|---|
| Document | The document name and a relevance percentage. Each document appears once, with the most relevant first |
| Web page | A globe icon and the page title — click to open it in a new tab |
Relevance is shown as a plain percentage. Only a low value — below 60% — is highlighted with an amber badge, as a warning that the document matched your question weakly.
Open the sources before you act on an answer. If a document carries an amber badge or the documents listed aren't the ones you expected, rephrase your question with the exact document or policy name.
When an answer is well supported by its sources, a small green Source-grounded answer badge appears next to the message time when you hover over the answer.
Web Search
With Web Search on, the assistant can look something up on the internet and show you where the information came from.
While the search runs, a sky-blue block appears with Searching the web and animated dots. When it's done, the block header shows Web search: "your query" and the body contains:
- A short summary of what was found
- A Sources list with the number of pages — each entry is the page title (with a snippet where available) and opens in a new tab when clicked
The block is collapsible, so you can fold it away once you've read it.
Links from the internet are shown only when they are safe, standard web addresses. Anything else is listed but not clickable. Web results come from outside your organization — check the linked page before relying on it for anything important.
Creating Images
If the assistant is allowed to create images, you can ask for an illustration or a photo-style picture — with Tools → Create Image, or simply in words.
- Describe the scene: the subject, the setting, the light, the style.
- The status line shows Generating image... and a placeholder card appears while the picture is drawn. This takes several seconds.
- The status changes to Image ready and the picture appears inside the answer.
Changing an image
Ask for a change — "make the mug orange", "simplify the background" — and the assistant edits the picture instead of drawing a new one. It can edit a picture it created earlier in the conversation or an image you attached.
Under an edited picture you get two buttons, Before and After, so you can flip between the original and the result. If the original is not available to you, only the result is shown.
- Image creation is for pictures. For a chart, a table or a flowchart, ask for a table or a diagram instead — see Artifacts & Documents.
- Text inside a picture can come out misspelled, especially long text and Turkish characters. Check any wording before you use the image.
- Creating and editing images depend on your organization's installation and on the assistant's setup. Where they are not available, the assistant tells you.
Actions That Need Your Approval
When the assistant is about to create, change or trigger something, it stops and shows an Action Requires Approval card in the chat instead of just doing it.
What's on the card
| Part | What it tells you |
|---|---|
| Action Requires Approval (with a shield icon) | The assistant is waiting for you |
| A one-line description | What will happen — e.g. "This will create a new task in your project." |
| The action name | Which action is about to run |
| A list of details | Every value that will be used, as label-and-value rows |
| Also being sent | Shown only when the action carries a value that is not already in the rows above — nothing that is about to be sent is left out |
| A warning line | Shown only in the two cases described below |
| Approve / Cancel | Your decision |
The detail rows change depending on the action. For a new task you'll typically see Title, Description, Priority, Assigned to, Deadline and Department. For a status change you'll see the Task and its New Status. For a time entry you'll see the Task, the Duration and a Description.
Warnings on the card
| Warning | When it appears | What to do |
|---|---|---|
| "This answer was prepared by reading external content (a web search, a document, or a service) — verify it before sending." | The assistant read outside content before proposing the action | Check that the details are what you meant |
| "Caution: this action was proposed after content was READ from a connected service, and it targets a destination you did not specify. Check the recipient above before approving." | The action goes somewhere you did not name yourself, after the assistant read content from a connected service | Check the recipient or destination carefully. If you did not ask for it, press Cancel |
Descriptions you may see
| The assistant wants to | The card says |
|---|---|
| Create a task | This will create a new task in your project. |
| Change a task's status | This will change the status of a task. |
| Add a comment to a task | This will add a comment to a task. |
| Log time on a task | This will log a time entry for a task. |
| Update a position in the org chart | This will modify a position in the org chart. |
| Update an employee's profile | This will update an employee's profile data. |
| Save something to a project's memory | This will save information to the project's memory. |
| Create a service request | This will create a new service request. |
| Start a blueprint | This will start a new blueprint workflow instance. |
| Run a workflow | This will run one of your workflows on your behalf. |
| Act in a connected app | This will run an action on one of your connected third-party services on your behalf. |
If an action has no description of its own, the card falls back to "This action will modify data. Please review before approving."
Approving or cancelling
- Approve (green, with a check icon) — the action runs. The card switches to a spinner and Executing... until it finishes.
- Cancel (white, with a cancel icon) — nothing runs. The assistant is told you declined and can suggest something else.
Read the detail rows before approving — this is the moment to catch a wrong assignee, a wrong date or a typo in a title. If something is off, press Cancel and rephrase your request rather than fixing it afterwards.
Working in Your Connected Apps
The assistant can also work in the third-party services your organization has connected — for example Slack, Notion, Confluence and Google. It finds which actions are available, checks what information each one needs, sees which services you've connected, and then runs the action.
Anything that sends or changes data in a connected service always shows an approval card first, listing the exact Service, the Action, a What it does line, and every value that will be sent.
This is switched off unless your admin turns it on for the assistant you're using. See Connected Apps for the full picture.
What You Can Ask For
| Category | Examples |
|---|---|
| Tasks | "Create a high-priority task for Sarah due Friday", "Move the onboarding task to In Review", "Add a comment to the budget task", "Log 90 minutes on the audit task", "What's on my plate this week?" |
| Documents & knowledge | "Search for the vacation policy", "Summarize the handbook", "Which documents mention the new supplier?" |
| Files & images | "Write this up as a Word document", "Turn this into a short presentation", "Draw a cover image for the report" |
| Organization & HR | "Who manages IT?", "Show me the reporting chain for the design team", "Find someone who knows data analysis", "Which positions are open?" |
| Service desk | "Submit an IT request for a new laptop", "What requests are still open for my department?" |
| Processes | "Start the onboarding process for John" (Blueprints), "Run the weekly report workflow" (Workflows) |
| Analytics | "Are any tasks at risk of missing their deadline?", "How are we doing on our service level targets?", "Prepare a status report for this project" |
| Web | "Search the web for the latest regulations on..." |
| Connected apps | "What can I do with Slack?" |
Which of these are actually available depends on how your admin configured the assistant you're talking to. Different assistants can have different abilities. Tasks and Blueprints exist only when your organization's package includes them.
Who Can Do What
What the assistant can do for you follows your own access — it cannot do more in chat than you could do yourself.
| What | Who |
|---|---|
| Looking things up — documents, tasks, the org chart, the web | Everyone who can use chat, within what they are allowed to see |
| Actions that change data — creating a task, starting a blueprint, running a workflow, updating a position, creating a department, deleting a task | People whose role has the permission for that action on its own page. If you can't do it there, the assistant can't do it for you |
| Company-wide overview, project status and risk reports, trend analysis | By default the Executive and Admin roles |
If the assistant says it can't do something, it's usually one of two reasons: your role doesn't have the permission for that action, or the action was turned off for that particular assistant. Ask your admin if you think you should have access — see Roles & Permissions.
Asking About an Employee
If your role is Executive or Admin, you can put a team member in context before you ask a question.
- Open the + menu next to the message box.
- Choose Select Employee.
- In the Select Employee window, use Search by name or email... to find the person, then click them.
- A chip with their name appears at the top of the message box.
Now ask your question:
"What's on their plate this week?" · "Summarize their open tasks"
The selection applies to the message you send next. Once it is sent, your message carries an About {name} label and the chip is cleared — select the person again if you want to ask another question in their context. To drop the selection before sending, click the × on the chip.
Select Employee appears in the + menu only for the Executive and Admin roles — people with the Member role don't see it.
Generated Documents
Ask the assistant to produce a real file — a report, a spreadsheet, a presentation — with Tools → Create Document or Create Presentation, or in words. It delivers a download card in the chat with the file name and format (Word, Excel, PDF, PowerPoint).
While a longer document is being written, a progress card shows its outline and ticks off each section, sheet or slide as it is finished.
The download card has two icon buttons: the eye icon (Preview in panel) opens the file in the side panel, and the download icon (Download) saves it.
See Artifacts & Documents for the full details.
Tips
- Be specific with names — "Create a task for John Smith" works better than "for John".
- Put the details in one message — priority, due date, assignee and department together, so the approval card is right the first time.
- Say where the answer should come from — "using our documents" or "search the web for" removes the guesswork.
- Read the approval card before confirming — it's a full preview of what's about to happen.
- Combine requests — "Show my overdue tasks and prepare a summary report" is a single ask.
- Follow the sources — for anything you'll act on, open the sources under the answer and read the original.
- Use the Tools actions when the format matters — Create Document or Create Presentation makes it clear you want a file, not an answer in the chat.
Troubleshooting
| Problem | What to do |
|---|---|
| The assistant says it can't do that | Your role doesn't have the permission for that action, or it's turned off for this assistant |
| No approval card appeared for something that changed data | Nothing that creates or changes data runs without a card — if you didn't see one, the assistant only looked something up |
| Wrong details on the approval card | Press Cancel and rephrase with clearer instructions |
| The action failed after you approved it | Read the message the assistant returns — it usually explains what went wrong |
| No sources under the answer | The answer wasn't based on documents or web pages. Turn on Document Search or Web Search and ask again |
| No Web Search or Document Search switch | That assistant wasn't set up with it. Try a different assistant, or ask your admin |
| No Create Image, Create Document or Create Presentation in the Tools menu | That assistant isn't allowed to create them. Try a different assistant, or ask your admin |
| No Summarize File in the Tools menu | Attach a file first — the action appears once a file is waiting under the message box |
| There is no Tools button | The assistant has no actions and no search switches |
| A message says document features aren't available | Some document features can be unavailable depending on your organization's data settings — check with your admin |
Related Pages
- Starting a Chat — the message box, the toolbar and how answers appear
- Connected Apps — working in Slack, Notion, Confluence and other connected services
- Thinking Mode — have the assistant reason through a question before it answers
- Attachments — adding your own files to a conversation
- Artifacts & Documents — generated files and the side panel
- Tips & Best Practices — getting better answers