# Bluebricks Docs for AI Agents

Bluebricks publishes an `llms.txt` file so AI agents can discover and load the documentation automatically.

## llms.txt

`llms.txt` is a standard that tells AI agents what documentation exists and where to find it. Most coding agents (Claude Code, Cursor, Copilot, etc.) already know how to look for it.

The Bluebricks file lives at:

```
https://bluebricks.co/docs/llms.txt
```

It contains a structured list of categorized links to every page in the docs. A companion `llms-full.txt` file provides the full content of all pages in a single file, optimized for LLM context windows.

```
https://bluebricks.co/docs/llms-full.txt
```

You don't need to download or configure anything. When an agent encounters Bluebricks resources, it checks for `llms.txt` at the docs root and pulls in the relevant pages.

## Context files

If your team uses agent context files (`AGENTS.md`, `CLAUDE.md`, `.cursorrules`, etc.), you can add a pointer to the Bluebricks docs so your agent loads them automatically when working on infrastructure code.

For example, in your repo's `AGENTS.md` or `CLAUDE.md`:

```markdown
## Bluebricks

This project uses Bluebricks for infrastructure orchestration.

- Documentation: https://bluebricks.co/docs/llms.txt
- Full docs (single file): https://bluebricks.co/docs/llms-full.txt
- API reference: https://bluebricks.co/docs/api
```

This gives the agents the context they need to answer questions about your Bluebricks setup, write correct CLI commands, and reference the right API endpoints.


---

# Agent Instructions: 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 current page URL with the `ask` query parameter:

```
GET https://bluebricks.co/docs/integrations/docs-for-agents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.