# llms.txt

> Polylane's documentation is published as machine-readable text files and raw markdown routes so language models and coding agents can consume it directly.

Every Polylane docs page is also published as plain text through the [llms.txt convention](https://llmstxt.org).

## Endpoints

<table>
<thead>
  <tr>
    <th>
      URL
    </th>
    
    <th>
      Contents
    </th>
  </tr>
</thead>

<tbody>
  <tr>
    <td>
      <a href="/llms.txt">
        /llms.txt
      </a>
    </td>
    
    <td>
      Title, description, and a structured index of every page, grouped by section
    </td>
  </tr>
  
  <tr>
    <td>
      <a href="/llms-full.txt">
        /llms-full.txt
      </a>
    </td>
    
    <td>
      The full markdown of every page concatenated into one file
    </td>
  </tr>
</tbody>
</table>

Use `/llms.txt` as a map for agents that fetch pages on demand. Use `/llms-full.txt` to give a model the entire corpus up front.

## Raw markdown for a single page

Prefix any docs path with `/raw/` and append `.md` to get that page as raw markdown. For example, this page is served at [/raw/docs/llms.md](/raw/docs/llms.md), and the automation triggers page at [/raw/remediation/automations/triggers.md](/raw/remediation/automations/triggers.md).

The response is served as `text/markdown`. If the page body does not start with a level one heading, the route prepends the page title as a level one heading and the description as a blockquote, so the file stands alone.

## When to use which

- **Agent with web access**: point it at `/llms.txt` so it can fetch individual pages through the [docs MCP server](/docs/mcp), the `/raw/` routes, or a plain HTTP fetch.
- **Offline prompts or fine-tuning**: use `/llms-full.txt` to bundle the docs into a single context window or dataset.

## Sections

The `/llms.txt` index groups pages to match the docs navigation: Getting Started, Context, Detection, Investigation, Remediation, Coding agents, Administration, and Docs.