> 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/reference-and-help/site-knowledge.md).

# Site Knowledge

Brand Kit, brand presets, content defaults, Context and Memory: everything the AI knows about your site.

**WP AI Manager > Site Knowledge** holds everything the AI knows about this site. It has five tabs. You can also see and edit the most important parts beside Chat in **What the AI knows** ([details](/documentation/workflows/in-editor-assistant-and-command-palette.md)).

## Brand Kit

| Field         | Use                                                              |
| ------------- | ---------------------------------------------------------------- |
| Brand name    | How the site refers to itself                                    |
| Audience      | Who the site is for, in one or two sentences                     |
| Voice         | For example "Confident, plain-spoken, no hype. Short sentences." |
| Colors, Fonts | Used for page builds and the Elementor kit                       |
| Dos, Don'ts   | One per line                                                     |
| Primary CTA   | For example "Book a free consultation"                           |

**Auto-fill from this site** pulls your Elementor kit, `theme.json`, logo and tagline into the fields. Review, then **Save Brand Kit**. **Apply to Elementor active kit** writes colors and fonts to Elementor; undo from History.

## Brand presets

Ready-made brand starting points. Applying a preset fills the Brand Kit fields; review them before saving.

## Content defaults

Starting values for every content brief. A Playbook or a chat can override any of them for one piece.

| Field                | Falls back to                     |
| -------------------- | --------------------------------- |
| Default content type | None                              |
| Tone                 | Brand Kit voice                   |
| Default length       | None                              |
| Audience             | Brand Kit audience                |
| Language             | Site locale (for example `en_US`) |
| Call to action       | Brand Kit primary CTA             |

An empty field keeps the fallback. Keywords are always per piece. A Task Run snapshots these values when it starts.

## Context

Long-form rules and facts about the site that the AI always follows: editorial rules, product facts, things never to say. Keep it short and current. In the drawer these appear as **Site rules**.

## Memory

Short facts, preferences and rules, for example "Our phone number is +254 …". Only **approved** rows reach future chats.

* **Add a memory** with a **Scope** (site-wide, a specific page or post, or a specific user) and a **Type** (Fact, Preference or Rule).
* **Pending** lists memories the AI suggested. **Approve**, **Archive** or **Delete** each one.
* **Approved** and **Archived** lists let you archive, restore or delete.

Settings on this tab:

* **Ask me in the chat when the AI suggests a memory**: shows a **Remember this?** card in the thread. Off sends suggestions to Pending without interrupting the chat.
* **Let the AI suggest memories**: off removes the tool, so the AI cannot propose anything.

Either way the AI can never save a memory by itself.

{% hint style="warning" %}
Site Knowledge is sent to your AI provider with requests. Do not store passwords, keys or customer personal data here. Long rules go in Context; how-to steps go in Skills.
{% endhint %}


---

# 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/reference-and-help/site-knowledge.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.