Glossary
What is llms.txt?
llms.txt is a plain-text file at your domain root that gives AI crawlers a curated map of your most important, citation-worthy pages — similar to robots.txt or a sitemap, but written for large language models. It helps answer engines find and understand your canonical content.
Why llms.txt exists
Web pages are full of navigation, scripts and repeated boilerplate that a language model has to wade through. llms.txt proposes a short, clean guide to your best content instead. To be realistic, it is a community proposal rather than an official standard, and AI vendors have not committed to using it as a ranking or citation signal. Its value is low cost and clarity, not a guaranteed boost.
How llms.txt works
You publish a Markdown file at /llms.txt on your domain. By convention it opens with a title, adds a one-paragraph summary of who you are and what you offer, then groups links to your key pages into short sections, each link with a one-line description. Typical entries are documentation, pricing, product overviews and your best guides. Some sites also publish a longer /llms-full.txt with the full text of important pages.
It does not control access. Crawling permissions still live in robots.txt, and llms.txt only points readers to what you consider most useful.
A hypothetical example
Imagine a software company with hundreds of URLs, including old release notes and tag pages. Its llms.txt names the company, summarizes the product in two sentences and lists about a dozen links: getting started, the API reference, the security overview, the pricing page and its best how-to guides, each with a short description. Someone, or something, reading that file gets the canonical picture in seconds.
Common mistakes
- Expecting a guaranteed jump in citations. There is no public commitment that engines act on the file.
- Listing every URL. The value is in curation.
- Leaving stale or broken links in the file.
- Publishing llms.txt while blocking AI crawlers in robots.txt, which sends contradictory signals.
Common questions
Does llms.txt control what AI can use from my site?
No. It is a suggestion about where your best content lives, not a permission system. Use robots.txt and other access controls to manage what crawlers may fetch.
Do ChatGPT, Perplexity and Google read llms.txt?
Support is uneven and vendors have not committed to treating it as a signal. If you publish one, check your server logs to see whether AI crawlers actually request it.
See if AI assistants recommend your brand
Run a free scan to see which AI engines mention your brand and who they cite instead of you.
Scan my site free