llms.txt and Markdown docs
Everything on this docs site exists twice: as the HTML you're reading and as Markdown built for machine consumption. Agents need clean, link-rich text they can index, retrieve, or load into context. This page explains the three machine-readable forms and how they relate.
The corpus
- /llms.txt, the index: A curated entry point to products, developer guides, tools and machine-readable references. It follows the llms.txt convention and is small enough to fit in context. Use it as the starting point when an agent retrieves pages on demand.
- /llms-full.txt, the English guides export: Authored English docs concatenated as Markdown. It excludes generated API operation references, generated SDK references and imported documentation. Use it when your task needs a broad guide collection.
- The per-page Markdown twin: Every page is also available as raw Markdown, so an agent can retrieve one page without the rest of the corpus.
The guide export and Markdown twins use the same published sources as their HTML pages. The curated index points you to those sources. For a specific task, search the docs with the public GET endpoint: change q to your question, then fetch a matching markdown_url. Search returns page and section links plus an estimated page token count.
The Copy-page affordance
You rarely need to remember those URLs. Every page across the Guides, API reference, SDK, and knowledge-base sections carries a Copy page menu that hands the machine-readable forms to your tools directly:
- Copy page as Markdown: The current page's Markdown twin, ready to paste into a chat or context file.
- Open llms-full.txt: The English guide collection for tasks that need several guides.
- Copy MCP install command: The one-line command that adds the hosted MCP server to your client's config, so the agent reading the page can also connect the tools needed to act on it.
- Connect to Cursor / Connect to VS Code: One-click MCP setup for two common agentic editors.
The dashboard offers a narrower version of the same idea. On the email onboarding page, the Copy for AI menu copies the current code sample as a ready-to-paste prompt, or opens it directly in Cursor, Claude, or ChatGPT.
The API reference never drifts
The API reference section is generated from the OpenAPI specification that validates the API. Its Markdown twin comes from the same source. For operation signatures and schemas, read the generated reference or the public OpenAPI specification. The English guides export does not include generated operation pages. Start at the API reference introduction to see how the reference is organized.
Pricing pages carry their prices
A pricing page and its Markdown twin render from the same rate data, in the same request. /email-api/pricing.md returns the email plans and both volume ladders, /pricing/email.md the sending-plan grid at every send volume, /pricing/sms.md the per-destination rate card, /pricing/voice/us.md the per-minute call rates for a destination, and /pricing/sms/fees.md the carrier and 10DLC fees. Start at /pricing.md: it lists every product that publishes a rate, its pricing page, and the .md URL the rates live at. Rates that come from the billing catalog are fetched when you ask, not copied into the file, so the twin cannot quote a price the page has since changed. Tables identify the published currency and billing unit. Use the currency supplied by the pricing source.
Choosing a form
| You want the agent to… | Hand it… |
|---|---|
| Discover what exists and fetch pages on demand | /llms.txt |
| Read the authored English guides together | /llms-full.txt |
| Understand one topic precisely | That page's Markdown via Copy page |
| Act on Bird as well as read about it | The MCP server; docs alone cannot send an email |
For a guided, end-to-end setup that installs the MCP server, connects the editor, and wires in the corpus, follow AI onboarding.
Next steps
- AI onboarding: install the MCP server, connect the editor, and wire in the corpus.
- MCP server: let your agent act on Bird as well as read about it.
- Agent skills: pre-built workflows that teach coding agents the Bird surface.
Related resources
Continue with the documentation, guides and examples for this topic. Resources are in English.
Watch the guideSetting up your coding agentUnderstand the conceptWhat is an MCP server, and how does an agent use one to send messages?Explore the capabilityCoding agentsFollow the learning pathBuild with AI agents
Get an implementation brief