Building a web that agents can actually read.
Experiments, implementation guides, and strong opinions on content negotiation, clean Markdown, and the agent-readable web.
Agent readable content, content negotiation, and the infrastructure behind a more usable web.
Introducing Agent Layer
We are building Agent Layer, a platform for serving agent ready content and understanding how agents use it.
Read the article →We scanned 104 websites. The median “Markdown” response was basically HTML.
Across 1,904 page scans, agent readiness was mostly all-or-nothing. The sites that negotiated Markdown well got nearly everything else right, too.
Read the article →Your bloated HTML has an energy bill
Cleaner pages mean fewer bytes to transfer and fewer tokens to process. Content negotiation is a small but practical way to make agent traffic less wasteful.
Read the article →Paste a URL. See the page an agent has to read.
Agent Preview puts your HTML beside a clean Markdown version so the cost of browser clutter becomes impossible to miss.
Read the article →We audit Markdown responses. Here is how we serve our own.
A practical walkthrough of AgentReady.dev’s content-negotiation setup using a Next.js proxy and one Markdown route.
Read the article →You added llms.txt. Your pages are still 500KB.
Robots rules, llms.txt, structured data, and content negotiation solve four different problems. Here is what each signal does—and what to build first.
Read the article →Inside the audit: how we score a website for AI agents
We fetch every page twice, run seven checks, and turn the results into one readiness score. Here is the full pipeline.
Read the article →Your website speaks HTML. Agents would rather read Markdown.
Most sites make AI agents dig through a full browser document for a few paragraphs of useful content. Content negotiation gives them a cleaner way in.
Read the article →