# Chat

The agent aware of the context of the canvas. Once you initiate the AI agent, it will give you some suggestions based on the content of the canvas. You can click on one of them or give new instructions. ***All the chats are private to the user and are not shared.***

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIQKNeqjEeOp9UwUcB9R9%2Fuploads%2FQNF1Rw0vVU0uDySSSrOG%2Fimage.png?alt=media&token=550e585d-bbf4-495a-9139-8ba824904eb8>" %}
Suggestions based on the content of canvas
{% endembed %}

You can start a new chat or view chat history by clicking on the icon as shown below.

<figure><img src="/files/Byxg8ByAkXc8k3J9cgRZ" alt=""><figcaption><p>Cretae new chat or view chat history</p></figcaption></figure>

You can also rename a chat to ease of review. First you should click on **Chat History** as shown above then rename as shown below.

<figure><img src="/files/4sAUZTWdpf6yEFA3oWX4" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.zerve.ai/guide/canvas-view/ai-agent/chat.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
