Collect canonical URLs
Your home, product, pricing, docs and language hubs — public, indexable pages only. Never link login walls.
katman / What is llms.txt?
GUIDE
What is llms.txt?
llms.txt is a plain-text (Markdown) file you publish at the root of your site — yoursite.com/llms.txt — that lists your most important pages with short, factual descriptions, so AI models can find and cite the right source without guessing.
What it is not
It is not a ranking factor, not a substitute for good content, and not read by every model today. It is a cheap, honest routing document — the same role robots.txt plays for crawlers, adapted for answer engines.
How to create one
Write factual one-liners
One short description per page, in plain language a model can quote. No superlatives without proof.
Publish at /llms.txt and keep it updated
Add it to your deploy checklist: new important page → new line. Then test whether models cite you, with a dated observation.
Generate yours in 30 seconds
The free generator reads your sitemap and drafts the file for you — then our audit checks the rest of your AI visibility stack.
FAQ
Where does the file go?
At the root of your domain: yoursite.com/llms.txt. It should be publicly reachable and listed in your sitemap workflow like any other important URL.
Does it work for every AI model?
No guarantee — adoption varies by tool and changes over time. That is exactly why you measure with dated observations instead of assuming.
Can it hurt my SEO?
It is a plain-text file at a separate URL; it does not change your pages. The only risk is listing low-quality or private URLs, which you control.
How is it different from sitemap.xml?
A sitemap lists every URL for crawlers. llms.txt is a curated, human-written subset with descriptions, optimized for models that want the few pages worth citing.