Agent-friendly docs

This documentation is built to be read by AI agents as well as people. Every page is available as raw markdown, machine-readable indexes cover the whole site, and any page can be handed to an AI assistant in one click. Use these surfaces to bring the docs into Claude Code, Cursor, ChatGPT, or any custom agent, and get accurate, current answers while building.

Markdown for every page

Append .md to any docs URL to get the page as plain markdown, with no HTML, navigation, or scripts:

curl https://www.speakeasy.com/docs/ai-control-plane/getting-started.md

This works for every page on the site and always reflects the published content. When asking an agent about a specific topic, pass it the .md URL of the relevant page:

Read https://www.speakeasy.com/docs/ai-control-plane/distribute/mcp-servers.md
and walk me through publishing an MCP server for my org.

Copy a page or open it in an assistant

Every docs page has a Copy Markdown button next to the table of contents. The main button copies the page’s markdown to the clipboard, ready to paste into any AI chat. The dropdown next to it offers:

• Open in Claude, Open in ChatGPT, or Open in Cursor — starts a conversation with the assistant already pointed at the page
• Copy Markdown — copies the full page as markdown
• View as Markdown — opens the raw .md version of the page

llms.txt

The llms.txt file is a curated index of the most important pages, written for agents deciding what to read first. It follows the llms.txt format, so AI IDEs and agent frameworks can consume it directly.

To give an AI IDE standing access to the docs, register the index as a documentation source. In Cursor, for example, open Settings > Indexing & Docs, click Add Doc, and enter https://www.speakeasy.com/llms.txt — the docs then become available with the @Docs mention in chat.

llms-full.txt

The llms-full.txt file contains the entire documentation set in a single file, for agents that want everything in one request. It is regenerated as the docs change, so it stays in sync with the site. It is a large file — for a single question, the per-page .md routes or the curated llms.txt index are usually the better starting point.