Guide · Updated 2026-08-15
llms.txt guide
llms.txt is a plain-text discovery file that summarizes the important pages and facts an AI system should know about a website. It complements robots.txt and sitemap.xml; it does not replace either.
What llms.txt should contain
Include the product summary, core pages, docs, pricing, comparisons, tools, policies, and any pages that answer common buyer or support questions. Keep links absolute, descriptions short, and sections easy to scan.
How it differs from sitemap.xml
A sitemap is built for crawlers and lists indexable URLs. An llms.txt file is built for language-model readers and should explain why pages matter. It can group links by intent instead of only listing every URL.
How it differs from robots.txt
robots.txt tells crawlers what they can fetch. llms.txt gives AI systems a concise map of useful content. You still need robots.txt to define crawler policy and sitemap.xml to support normal search indexing.
What to avoid
Do not stuff keywords, include private URLs, or make claims that are not supported by the linked pages. Treat llms.txt as a clean source of truth, not a hidden landing page.
How usedocs uses the pattern
usedocs publishes a short llms.txt and a richer llms-full.txt so AI systems can quickly understand the product, free tools, comparison pages, and docs-support positioning.
FAQ
Is llms.txt an official search ranking factor?
No public search engine treats it as a universal ranking factor. It is a discoverability and clarity file for AI readers.
Should llms.txt include every page?
No. Include important pages and clear descriptions. Use sitemap.xml for exhaustive URL discovery.
Where should it live?
At the site root: /llms.txt. A richer companion file can also be linked from that file.