Blog
Insights on AI agents, content negotiation, and the agentic web.
Serving agents clean content is an environmental issue, not just a performance one
Every unnecessary token your site forces an AI agent to process burns real energy. A 400KB HTML page vs 15KB of markdown is not just a latency difference. It's a carbon one.
New: one-click agent content preview for any URL
Paste a URL, see exactly what AI agents get vs. what they should get. The new Agent Preview tool shows the difference in seconds.
How we serve markdown on AgentReady.dev
A quick walkthrough of how we implemented content negotiation on our own site using Next.js middleware and a single API route.
llms.txt vs content negotiation: what you actually need
Everyone's talking about llms.txt. But there's a whole landscape of signals that tell AI agents how to access your site. Here's what each one does, what it doesn't, and what to implement first.
How our audit works: crawling and scoring your site for AI readiness
A technical walkthrough of how we fetch pages, compare HTML and Markdown responses, and turn seven weighted checks into a single readiness score.
Why AI agents need your site to speak Markdown
Most websites dump 500KB of HTML on AI agents when 2KB of Markdown would do. Content negotiation fixes this. Here's how it works and why you should care.