Guides
Step-by-step guides for each agent-readiness standard: what it is, why it matters, a working example, and how to verify.
Discoverability
- Easy ai-agent.json: your site's business card for AI agents What ai-agent.json is, why agents need a machine-readable site manifest, a minimal example, right vs wrong, mistakes, and how to verify.
- Easy HTTP Link headers for agent discovery What Link headers (RFC 8288) are, why AI agents use them to discover resources, an example, right vs wrong, mistakes, and how to verify.
- Easy How to write llms.txt: a guide with an example What llms.txt is, why AI agents need it, a minimal working format example, right vs wrong, common mistakes, and how to verify.
- Easy How to set up robots.txt for AI crawlers Why robots.txt matters for AI agents, a minimal working example, right vs wrong, common mistakes, and how to verify.
- Easy Sitemap with lastmod for AI: how to do it right Why AI crawlers need a sitemap with lastmod dates, a minimal working example, right vs wrong, common mistakes, and how to verify.
Content Accessibility
- Medium Markdown for agents: content negotiation for LLMs Why serve a Markdown version of pages to AI, how content negotiation works, a minimal example, mistakes, and how to verify.
- Medium Schema.org JSON-LD for AI: markup agents actually read What Schema.org JSON-LD is, why it matters for AI and rich results, a minimal example, right vs wrong, mistakes, and how to verify.
Bot Access Control
- Easy AI Bot Rules: explicit AI-crawler sections in robots.txt Why add separate sections for GPTBot/ClaudeBot/PerplexityBot beyond the wildcard rule, an example, common mistakes, and how we score it.
- Easy Content Signals: allow search but control AI training What Content-Signal is, why separate search / ai-input / ai-train, a minimal example, right vs wrong, mistakes, and how to verify.
- Easy Web Bot Auth: how a bot cryptographically proves who it is What Web Bot Auth and HTTP Message Signatures (RFC 9421) are, why agents sign requests, an example, mistakes, and how to verify.
API / Auth / MCP
- Hard Agent Skills: a registry of what your agent can do What an Agent Skills index is, why orchestrators need a machine-readable skills list, an example, right vs wrong, mistakes, and how to verify.
- Hard A2A Agent Card: your agent's card for orchestrators What an A2A Agent Card (Google A2A Protocol) is, why it matters for agent-to-agent comms, an example, right vs wrong, mistakes, and how to verify.
- Medium API Catalog at /.well-known: how agents find your APIs What /.well-known/api-catalog (RFC 9727) is, why AI agents need it, a minimal linkset example, mistakes, and how to verify.
- Medium auth.md: a native registration path for agents What auth.md (the WorkOS open protocol) is, why agents need their own onboarding instead of faking clicks, a minimal file example, right vs wrong, mistakes, and how to verify.
- Hard MCP Server Card: how agents discover your MCP server What an MCP Server Card is, why agents need MCP server auto-discovery, a minimal example, right vs wrong, mistakes, and how to verify.
- Hard OAuth Discovery for agents: let the agent find where to authenticate What OAuth Authorization Server Metadata (RFC 8414) is, why agents need OAuth endpoint auto-discovery, an example, mistakes, and how to verify.
- Hard OAuth Protected Resource: where an agent goes to get a token What OAuth Protected Resource Metadata (RFC 9728) is, why agents need it, a minimal example, right vs wrong, mistakes, and how to verify.
- Easy RateLimit headers: let agents back off gracefully What standard RateLimit headers are, why AI agents need them, a minimal example, right vs wrong, mistakes, and how to verify.
- Hard WebMCP: MCP over HTTP, no local install What WebMCP (MCP over HTTP/SSE) is, why a remote MCP with no install matters, a minimal example, mistakes, and how to verify.
Commerce
- Hard ACP (Agentic Commerce Protocol): checkout without exposing the card What ACP (OpenAI + Stripe) is, how Shared Payment Tokens work, how to declare support, and how we verify it.
- Hard MPP (Machine Payments Protocol): machine-to-machine payments What MPP (Stripe + Tempo Labs) is, how it differs from x402, how to declare support, and how we verify it.
- Hard UCP (Universal Commerce Protocol): the full purchase cycle for an agent What UCP (Google + Shopify/Visa/…) is, why it's broader than x402/MPP, how to declare support, and how we verify it.
- Hard x402: HTTP 402 payments for AI agents What x402 (Coinbase) is, how an agent pays via HTTP 402, a minimal example, how to declare support, and how we verify it.