What is llms.txt?
llms.txt is a proposed text file, usually at /llms.txt, that gives language-model tools a short Markdown overview of a site and links to important pages. It is a convention, not a replacement for robots.txt or a sitemap. Publishing it does not guarantee that any engine will crawl or cite you.
Why it matters for AI visibility
Assistants and crawlers have limited context. A concise file can point them at the pages that explain what you sell, how pricing works, and which guides matter, instead of leaving that selection to whatever they fetch first. That can help AI visibility only as a supplement. Access is still decided by robots.txt, by whether the pages are public, and by each product’s own crawler. Discovery of URLs is still the job of links and sitemaps. llms.txt does not set a rank, a citation preference, or a permission to train. Keep the file accurate when offers change, and do not hide claims there that the HTML pages do not support. If a page is blocked or thin, listing it in llms.txt does not repair it.
Example
A B2B site adds /llms.txt with a one-paragraph description and links to the product page, pricing, a comparison, and two guides. The file matches the visible site. The team still allows the crawlers they want in robots.txt and keeps those pages indexable. They do not report the file itself as an AI citation.
Related terms
An AI crawler is what may or may not fetch the file. Schema markup for AI is a different layer: structured data in the page, not a site-level overview. Grounding still depends on the pages an engine retrieves, not on the presence of this filename.