Free Tool · No signup · Results in <30 seconds

See What AI Bots Actually Read
on Your Website

Choose a crawler identity. Enter your URL. See exactly what GPTBot, ClaudeBot, PerplexityBot - and 12 other AI bots - can read, what they're blocked from, and what signals they're missing.

15 AI crawlers simulated robots.txt parsing llms.txt detection Content signal analysis
https://
🤖
Enter a URL above and select a crawler to begin simulation
robots.txt - Crawler Directive
What the Bot Can Read

This is CPS® Lite - the surface layer.

The full audit scores every page block, tracks citation frequency across 5 AI platforms, and shows which competitor wins when you don't.

Get the Full CPS® Audit

How the simulator works

01 - IDENTITY

Choose a crawler

Each AI platform sends a different User-Agent string. We simulate the exact identity each bot uses when knocking on your server's door.

02 - ACCESS CHECK

Parse your robots.txt

We read your robots.txt and evaluate whether this specific crawler is allowed, blocked, or subject to a wildcard rule. Exact same logic as the real bot.

03 - CONTENT READ

Show what it sees

If allowed, we fetch your page and extract what the crawler would actually read: visible text, headings, schema, and key signals. If blocked - it sees nothing.

04 - SIGNAL CHECK

Surface the gaps

We check for llms.txt, schema markup, FAQ content, and other technical readiness signals that affect how AI crawlers access and parse your site. Each gap is a concrete action item, not a vague score. (Note: Google's 15 May 2026 AI optimisation guide states that schema and llms.txt are not required for AI Overviews or AI Mode. These remain useful upstream signals for crawlability and entity recognition; see Platform-Specific Citation Guidance for per-platform weighting.)

This tool is built on the Citation Probability Score® (CPS®) framework, the only block-level AI citability methodology with registered UK trademarks.