> For the complete documentation index, see [llms.txt](https://docs.perisclaw.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.perisclaw.com/security-and-control/chat-modes.md).

# Chat modes & autonomy

You're always in control of how active Perisclaw is in any given chat. Each chat has a **mode** that decides when — if ever — your assistant acts on its own.

## The three modes

| Mode                                                | What it means                                     | When the assistant acts                                               |
| --------------------------------------------------- | ------------------------------------------------- | --------------------------------------------------------------------- |
| **Blocked**                                         | Your assistant stays completely out of this chat. | Never — not even with `/claw`.                                        |
| **On request** *(default for other people's chats)* | It only steps in when you ask.                    | When you summon it with `/claw`.                                      |
| **Autonomous**                                      | It can read new messages and reply on its own.    | Whenever the other person messages — it responds in the conversation. |

Your **self-chat** is always your private workspace where you and your assistant talk freely. The modes above apply to your **other** chats — DMs and groups.

## Changing a chat's mode

Just tell your assistant, from inside the chat or your self-chat:

* *"/claw switch this chat to autonomous"* — let it reply on its own here.
* *"/claw turn yourself off in this chat"* — block it.
* *"/claw go back to on-request"* — only act when summoned.

You can also adjust this and other per-chat settings from the dashboard.

## Draft-first by default

{% hint style="success" %}
Whenever Perisclaw is about to **send a message to someone else** on your behalf, it shows you the draft in your self-chat and waits for your OK first. You approve with a tap. The exceptions are when you use `/claw` directly in a chat, or when you've set that chat to **Autonomous** — then it sends without the extra step.
{% endhint %}

## Auto-engagement (advanced, off by default)

If you want, Perisclaw can also start helping in chats you *haven't* explicitly switched on — for example, warmly replying to a contact you haven't spoken to in a while. This **auto-engagement** is **off by default**; you turn it on by asking (*"enable auto-engagement"*) and describing the rules you want, and you can exclude any chats you'd rather it never touch. Until you turn it on, your assistant only acts in chats you've set to Autonomous or summoned it in.

For how this ties into what your assistant is allowed to access overall, see [Permissions & access](/security-and-control/permissions-and-access.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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.perisclaw.com/security-and-control/chat-modes.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.