> For the complete documentation index, see [llms.txt](https://docs.avonnicomponents.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avonnicomponents.com/dynamic-components/build-with-ai/for-ai-agents.md).

# For AI Agents

Everything on this site is machine-readable: Markdown URLs, a full index, a question-answering endpoint, and the Avonni MCP server.

{% hint style="warning" %}

#### 🚧 **Early access**

Build with AI is rolling out gradually and improving with every release. Something unclear, missing, or broken? [Tell us](/dynamic-components/resources/contact-support.md): your feedback directly shapes what we improve next.
{% endhint %}

This documentation is machine-readable end-to-end. If you are an AI agent, or you build with one, here is everything you can consume programmatically. No scraping needed.

## Read any page as Markdown

Append `.md` to any page URL to get clean Markdown instead of HTML:

```
https://docs.avonnicomponents.com/dynamic-components/components/data-table.md
```

## Get the full index

The site publishes a complete index of every page, and a full-corpus export:

```
https://docs.avonnicomponents.com/llms.txt
https://docs.avonnicomponents.com/llms-full.txt
```

`llms.txt` lists every page with its Markdown URL. `llms-full.txt` returns the entire documentation corpus in one response.

## Ask the documentation a question

Any `.md` URL accepts an `ask` query parameter and answers in Markdown, with sources. An optional `goal` parameter tailors the answer to what you are trying to accomplish:

```
GET https://docs.avonnicomponents.com/dynamic-components/welcome.md?ask=<question>&goal=<end_goal>
```

## Query the component catalog

Prose is one thing; the structured truth is the **Avonni MCP server**. It documents every component's properties, interactions, and styling hooks, and updates with each release:

```
https://mcp.avonnicomponents.com
```

Use the `toolset` parameter (`dynamic` for this package) on `list_components` and `list_interactions`, or filter the whole server with `?toolsets=dynamic`. Full setup in Setup.

## Install the workflows

The [avonni/skills](https://github.com/avonni/skills) repository ships the agent workflows for creating and updating Avonni artifacts:

```bash
npx skills add avonni/skills
```

{% hint style="info" %}
Human reading this? All of the above powers the Build with AI experience: connect your assistant once and it uses these sources for you.
{% 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 dynamically by asking a question.

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

```
GET https://docs.avonnicomponents.com/dynamic-components/build-with-ai/for-ai-agents.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 `build a script that syncs our docs to a CMS` 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.