
Making your docs site agent-readable: llms.txt, MCP, and the .well-known files that actually matter
The full agent-discovery stack a docs site can ship — llms.txt, OpenAPI, MCP, .well-known — and how to verify each.
Building AI dev tools and agent infrastructure — in public. Notes on Python, FastAPI, Next.js, LLM pipelines, and the tools I'm making along the way.