Inth founder Christopher Burns explains how C15T became increasingly discoverable through recommendations from Claude, ChatGPT, Codex and Gemini. He treats agent discoveryAI agent discoverability is the degree to which an agent can find, identify, and correctly understand a product, library, capability, or authoritative information source. as a developer-experience problem built from several small, measurable improvements rather than a single optimization trick.
Burns recommends a concise hand-written llms.txtA large language model text file is a concise website file, commonly named llms.txt, that points AI systems to authoritative descriptions and documentation for the site or project., a fuller documentation index and Markdown versions of individual pagesMachine-readable documentation is authoritative product or technical guidance formatted and organized so software can retrieve, parse, and use it reliably without depending on visual page interpretation.. He also describes content negotiation and agent-friendly URL parameters that let tools retrieve lower-cost Markdown instead of parsing full HTML.
For software libraries, Burns argues that coding agents often inspect repositories and installed packages instead of visiting documentation sites. C15T therefore bundles current Markdown and an agents.md guideAn agent instruction file is a repository document that defines durable rules, workflow constraints, conventions, and verification expectations for coding agents. inside its package, helping agents find authoritative local instructions while reducing search and token overhead.
Watch on YouTube
