> For the complete documentation index, see [llms.txt](https://passion-io.gitbook.io/help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://passion-io.gitbook.io/help/make-your-ai-answer-well/set-boundaries.md).

# Set Boundaries for Your AI

Name the topics your AI should decline so conversations stay inside your scope.

> **Your AI** is available on certain plans and app types. If you don't see the AI block in your sidebar, please check our pricing page for more information.

![Setting boundaries for your AI](https://2428968841-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTPk2caKn6lTiyi0ejFkg%2Fuploads%2Fgit-blob-0877a32b90078a3660ef4311bcbe74a324c0b0c8%2Fset-boundaries.png?alt=media)

## Add a Boundary

Boundaries are the topics or content categories your AI should decline to engage with. Use them to keep conversations inside your scope.

1. In the sidebar, open the AI block and select **Behavior**.
2. Find **Boundaries**.
3. Type a topic into the **Add a topic your AI should decline** field and select **Save**.
4. Each boundary shows as a chip. Select the **×** on a chip to remove it.

Start-with suggestions like **Legal advice**, **Financial advice**, **Tax advice**, **Refund disputes**, or **Topics outside your expertise** are one tap away.

When a client raises a topic you've ruled out, your AI declines and steers back to what you do cover.

## Boundaries Are About Scope, Not Safety

Boundaries shape what your AI talks about — they're not a safety control. Core safety defaults are already on without any setup from you, so you only need to add the topics that fall outside your own expertise.

## Related

* [Add Custom Rules for Your AI](/help/make-your-ai-answer-well/add-custom-rules.md)
* [How Your AI Decides What to Say](/help/make-your-ai-answer-well/how-your-ai-decides.md)

For more assistance, please contact us.