> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anarlog.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat with your meetings

> Ask questions, find related context, and review proposed note changes.

Anarlog Chat can answer questions about the open meeting, search your other meetings, and help turn a conversation into follow-up work. Chat uses the Intelligence model selected under **Settings → Intelligence**.

## Ask about the open meeting

1. Open a meeting note.
2. Open **Chat**.
3. Check the context chips above the input. The open meeting is added automatically when its content is available.
4. Ask a question or choose a suggested prompt.

Useful requests include:

* “What are my action items from this meeting?”
* “Draft a follow-up email to the participants.”
* “What decisions did we make?”
* “Compare this meeting with the previous project review.”
* “Find meetings where we discussed the launch date.”

Chat can search meeting titles and content, recurring meeting history, contacts, and connected calendar events when the request needs them.

## Control the context

Context chips show the meetings, people, and other records Chat can use for the next message.

* Click a meeting or contact chip to open it.
* Hover over a removable chip and click its remove button to exclude it.
* Start a new chat when you want a clean conversation without the earlier message history.

Check these chips before asking about sensitive or similarly named meetings. A clear request such as “Use only this meeting” also helps keep the answer scoped.

## Review proposed changes

Chat can propose a summary edit or transcript correction. Review the proposed change before you apply it. A proposal does not silently replace your note.

For direct transcript editing, speaker reassignment, and re-transcription, see [Notes, summaries, and transcripts](/notes#correct-a-transcript).

## Privacy and external search

Chat sends the prompt and required context to your selected Intelligence provider. A local provider keeps that model request on your computer. A hosted provider receives the text needed to answer.

Chat can also search the public web when a request needs current external information. The search query leaves your device. See [Data, privacy, and retention](/data-and-privacy) before using sensitive context with hosted models or web search.