Question 1

What is agentic browsing readiness?

Accepted Answer

It measures how easily AI agents — ChatGPT, Claude, Perplexity, Gemini and the new wave of browser assistants — can read, understand and act on your website. Google added an Agentic Browsing category to Lighthouse in 2026 that scores the same signals: llms.txt, WebMCP, the accessibility tree and layout stability.

Question 2

What is an llms.txt file?

Accepted Answer

llms.txt is a plain-Markdown file at your domain root (/llms.txt) that gives AI models a concise, machine-readable map of your site: a title, a one-line summary, and linked sections. It's the agentic web's equivalent of robots.txt or sitemap.xml. We check that yours exists and follows the format.

Question 3

Why does AI crawler access matter?

Accepted Answer

If your robots.txt blocks GPTBot, ClaudeBot or PerplexityBot, those assistants can't read your content — so you won't appear in their answers. We check the major AI user-agents and show which are allowed or blocked.

Question 4

What is WebMCP?

Accepted Answer

WebMCP (Web Model Context Protocol) is a browser standard from Google and Microsoft that lets a website expose structured tools — search, filter, book, buy — to AI agents via the navigator.modelContext API, instead of agents parsing screenshots. It's still emerging (Chrome 146+), so we report it as a forward-looking signal.

Question 5

Do you store the sites I check?

Accepted Answer

No. We fetch the domain's llms.txt, robots.txt and homepage at scan time, analyze them in memory, and return the result. Nothing is logged or stored — same zero-data policy as the rest of whatsmy.fyi.

Question 6

How is the score calculated?

Accepted Answer

Each signal carries a weight: llms.txt (30), AI crawler access (25), metadata & semantics (20), structured data (15) and WebMCP (10). We sum what your site earns and turn it into a 0–100 score and an A+ to F grade. Partial credit is given where a signal is present but incomplete.

Question 7

My site scored low. What should I fix first?

Accepted Answer

Start with the highest-weight wins: add an /llms.txt file, make sure robots.txt doesn't block AI crawlers, and add JSON-LD structured data. Those three alone move most sites from F to B. WebMCP is optional today but future-proofs you.

Question 8

Can you detect live WebMCP tools and layout shift?

Accepted Answer

This scan runs from the edge, so it detects static WebMCP signals in your page source and the readiness fundamentals. Live tool registration and real layout-shift (CLS) measurement need a full browser render — those are on our roadmap as a deeper scan.

AI Agent Readiness Checker

Six signals. One scan.