> For the complete documentation index, see [llms.txt](https://docs.3techagency.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.3techagency.com/documentation/workflows/in-editor-assistant-and-command-palette.md).

# In-editor assistant and command palette

Use Chat inside the block editor and Elementor, find Playbooks with the WordPress command palette, and see what the AI knows.

## Chat inside the editor

The block editor and Elementor both have an **Ask AI about this page** button that opens Chat in a side panel, scoped to the post you are editing.

{% tabs %}
{% tab title="Block editor" %}

1. Open a page or post in the block editor.
2. Open the **WP AI Manager** sidebar from the editor's plugin menu.
3. Ask for the change, for example "Tighten the intro paragraph and add a call to action button".
   {% endtab %}

{% tab title="Elementor" %}

1. Open the page in Elementor.
2. Select **Ask AI about this page** to open the side panel.
3. Ask for the change. Elementor must be active and the page must be an Elementor document.
   {% endtab %}
   {% endtabs %}

When the AI writes to the page you are editing:

* If you have **no unsaved edits**, the editor reloads to show the change ("The AI changed this page. Reloading the editor to show it…").
* If you **have unsaved edits**, it does not reload. It warns: "The AI saved a change to this page, but you have unsaved edits. Saving now would overwrite the AI change." Choose **Reload and discard my edits** to keep the AI change, or keep editing and accept that saving overwrites it.

You can also start from the **Pages** list: **Edit with AI** opens Chat for that page.

## Find a Playbook with the command palette

WordPress owns **Cmd+K** (Ctrl+K on Windows) for its command palette on every admin screen. WP AI Manager adds Playbooks to it.

1. Press **Cmd+K** / **Ctrl+K** anywhere in wp-admin.
2. Type a playbook name or a keyword such as "alt text", "redirects" or "sale".
3. Choose **Playbook: name**. On the Chat screen it opens in place; elsewhere it opens Chat.

Opening a playbook never sends a message or spends tokens. In Chat, **Find a playbook** opens the same search scoped to Playbooks. **New chat** is **Cmd+Shift+K** / **Ctrl+Shift+K**.

## What the AI knows

**What the AI knows** opens a drawer beside Chat showing exactly what the assistant is given:

* Brand voice and audience
* **Site rules**: the rules and facts the AI always follows (if site rules are switched off, the drawer says so)
* **Top memories**: approved memories, which you can edit or archive
* **What it can use**: active integrations
* How the current page is built (block editor, classic editor or a page builder)

Edits here write straight to Site Knowledge and apply from the next reply ("Saved to Site Knowledge. The next reply uses it."). Only an administrator can change what the AI knows. See [Site Knowledge](/documentation/reference-and-help/site-knowledge.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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.3techagency.com/documentation/workflows/in-editor-assistant-and-command-palette.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.