llms.txt
weight 18A markdown file at /llms.txt that gives AI systems a curated map of your site: what you are, and which pages matter.
Free scan
Is your site ready for AI search?
ChatGPT, Claude, Perplexity and Google's AI answers describe your business from a handful of public signals. Check whether yours are actually there — in about ten seconds, no signup.
✓ No signup ✓ No install ✓ Public files only
Checking public GEO signals…
—
Checklist
Next steps
Loading…
The full report has a shareable link and prints to PDF for clients.
Ask the AI engines directly
Opens with the audit prompt pre-filled, so you can compare what each engine believes against what is true.
What the scan looks at
Nine weighted signals decide the score, plus two informational ones tracking conventions that are still settling. Each is something an AI crawler can read without executing your JavaScript — which is how most of them work.
robots.txt AI bots
weight 18The rules in /robots.txt that apply to AI crawlers — GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot and others.
Schema.org JSON-LD
weight 14Structured data embedded in the page as JSON-LD, describing what the page and the organisation behind it actually are.
Sitemap
weight 12A valid, reachable sitemap.xml — either at the root or declared in robots.txt.
Title & meta description
weight 10The document title and meta description of the page being scanned.
llms-full.txt
weight 8An optional companion to llms.txt carrying extended context — deeper product facts, documentation, positioning.
Canonical URL
weight 8A link rel="canonical" declaring the authoritative URL for the page.
Open Graph
weight 6og:title, og:url and og:image metadata.
Indexable page
weight 6Whether the page carries a noindex directive in its robots meta tag.
Why AI visibility is its own problem
Search sends people to your page so they can read it themselves. AI answers the question directly and names a few sources. That changes what matters: not just whether a page can rank, but whether a model can state facts about your company without guessing.
The failure mode is quiet. Nobody gets an error when an assistant describes your product wrongly, or leaves you off a shortlist because a crawler was blocked years ago. You simply stop appearing, and nothing in your analytics explains it.
Check as you browse
The free extension runs these same checks on whatever tab you have open — useful when you are working through a set of client sites rather than one domain.
Questions
Is this SEO or GEO?
Adjacent. Classic SEO signals still matter — sitemaps, canonicals, metadata. GEO adds the AI-specific layer on top: llms.txt, crawler policy for AI agents, and structured data clear enough for a model to state facts about you confidently.
Does a high score guarantee AI citations?
No, and be sceptical of anyone who says otherwise. This measures whether engines can read and understand your site — the necessary groundwork. Whether they cite you also depends on your content, your authority and the question being asked.
Do you scan the whole site?
The free scan reads one page plus your public discovery files, which is where nearly all of these signals live. Full-site crawls with per-page llms.txt generation are a paid product.
What do you do with my data?
We fetch public URLs and keep the resulting report so its link stays shareable. No login, no private data, nothing executed on your site, and nothing sold.
How often should I re-scan?
After every redesign, migration or CMS change. These signals break quietly — a noindex rule that escapes staging, or an SPA rewrite that turns llms.txt into an HTML shell, will not announce itself.