# Use the AI assistant in a room

> Click the AI Assistant button (sparkle icon, bottom right of the room) or Ask AI on a selected item, then type or dictate a question or instruction; the assistant answers from the room's content and can create notes, docs, images, comments, and more on the canvas.

Category: AI and integrations
Web page: https://www.pactto.com/help/ai-assistant
All guides: https://www.pactto.com/help.md

## What the assistant is

The AI assistant (your "Room Copilot") lives inside each room. Ask it about the room's content, such as PDFs, images, docs, comments, and what was said in meetings, or ask it to do things on the canvas for you.

It can:

- Answer questions and summarize a PDF, a Pactto Doc, a web link, or the room.
- Describe an image or read the text in it, and generate or change images.
- Create and edit Pactto Docs, tables, sticky notes, text, shapes, arrows, and boards.
- Move, resize, align, distribute, or delete items, and edit their text.
- Add comments and set review statuses.

## Ask the assistant

1. In the room, click **AI Assistant** (sparkle icon) in the row of buttons at the bottom right. On a computer the panel is open when you enter the room.
2. Type in **Type your instruction or question here** and press **Enter** (**Shift+Enter** for a new line). Or click **Dictate a message**, speak, and click **Stop dictation**.
3. While it works you see **Thinking...**. Click **Stop** to cancel.
4. Under an answer, use **Copy answer** or **Create doc with this content** to turn it into a Pactto Doc on the canvas.

Opening the assistant closes the Chat and Live captions panels.

## Ask about a specific item

1. Select an image, video, PDF, or board on the canvas.
2. Click **Ask AI about this asset** in the item's title bar. The assistant opens with the item attached.
3. Type your question, or click one of the suggested prompts above the text box, for example **Summarize this PDF**, **Describe this image**, or **What are the action items?** (for a Pactto Doc).

Selected items appear as small tags in the text box. Click the **×** on a tag to leave that item out. When items are selected, actions apply to those items.

## Note capturing and proactive suggestions

- **Note capturing**: when on, the assistant reads the room's messages, discussions, comments, and asset updates to build context for summaries, approvals, and action items. The panel then shows **AI context starts from** and a time. It turns on by itself once two or more people are in the room, unless someone turned it off. You can pause it any time; the assistant still answers from what it already captured.
- **Proactive suggestions**: when on, the assistant follows the conversation and suggests next steps, like generating or editing assets, summarizing discussions, creating action items, and flagging approvals. Suggestions show as cards with **Do it** and **Cancel**; they disappear after 30 seconds if you ignore them. It is off by default.

Only the room owner and people with **Can edit** access can turn these on or off.

## Room instructions

Room instructions tell the assistant how to behave in this room (tone, what to focus on, what to leave alone). They apply to every reply.

1. In the assistant header, click the sliders icon (**Edit room instructions for the assistant**, or **Assistant settings** and then the instruction row).
2. Write your instructions, for example "Summarize in short bullet points. Flag anything that needs legal sign-off."
3. Click **Save**.

The limit is 65,536 characters. The assistant may also propose changes to the instructions; you can **Accept** or reject them. Only the owner and people with **Can edit** access can change room instructions.

## Who can do what

- Owner and **Can edit**: everything.
- **Can review**: can ask questions, and the assistant can add sticky notes, text, shapes, arrows, lines, comments, and review statuses. Creating or editing other content stops with a message saying edit access is needed.
- **Can view**: can ask questions, but the assistant cannot add or change anything on the canvas.

## If something goes wrong

- **The assistant couldn't be reached. Check your connection and try again.**: a network problem. Try again.
- **Something went wrong**: use the retry option on the message, or rephrase the request.
- A permission message: your room role does not allow that change. Ask the room owner for edit access.

## Good to know

- Answers come in the language you write in.
- Changes the assistant makes are made as you and everyone in the room sees them.
- You can also use outside assistants such as Claude or ChatGPT with your rooms through the Pactto MCP server, or coding agents through the Pactto CLI.

## Related guides

- [Read the transcript and live captions of a meeting](https://www.pactto.com/help/transcripts.md): Pactto transcribes what each person says while their microphone is on; open the Live captions panel (the CC button at the bottom right of the room) to read the transcript, translate it, or show captions on screen.
- [Leave feedback with comments](https://www.pactto.com/help/comments.md): Click the Comment tool (or press K), then click an item or an empty spot on the canvas, type your feedback, and press Enter to post it.
- [Set a review status on an item](https://www.pactto.com/help/review-status.md): Select a video, image, PDF, Pactto Doc, or board and pick a status (Draft, In progress, Needs review, Needs changes, Approved, or your own) from the status menu in its title bar.
- [Connect Claude or ChatGPT to Pactto (MCP server)](https://www.pactto.com/help/connect-ai-assistant-mcp.md): Add the Pactto MCP server URL (https://live.pactto.com/mcp) to Claude, ChatGPT, or another assistant as a custom connector, sign in, and click Allow; it needs the Pro plan.
- [Use the Pactto CLI and create an API key](https://www.pactto.com/help/pactto-cli.md): The Pactto CLI lets Claude Code, Codex, scripts, and CI read and update your rooms from the terminal; create an API key in Account settings under API keys (CLI) (Pro plan), then follow the setup at pactto.com/cli.
