Draft an llms.txt for any site from its home page and sitemap, then copy or download it.
llms.txt is a proposed convention, described at llmstxt.org: a Markdown file at the root of a site that gives a language model a short summary of the site and a list of the pages worth reading. It is a proposal, not a standard, and no major AI engine has confirmed that it reads the file when answering questions. Publishing one is cheap, so some sites do it in case that changes.
/sitemap.xml and the home page's own links, and lists up to 20 pages on the same host./llms.txt.It is a draft. Page labels come from link text and URL slugs, so rename them, drop pages that do not matter, and add a line of context to the ones that do.
Check which AI crawlers a site allows with the AI crawler checker, or see all free tools.
A proposed convention from llmstxt.org: a Markdown file at /llms.txt that summarises a site and lists its most useful pages for language models. It is not a standard, and no major AI engine has confirmed that it reads the file.
The heading and summary come from the home page's title and meta description. The page list comes from /sitemap.xml and the home page's links on the same host, up to 20 pages. Nothing is written by an AI model.
It does not run JavaScript, so links a page adds in the browser are missed. It does not read each page to describe it, group pages into sections, or check that the listed pages still load. Review and edit the draft before publishing it.
At the root of your site, so it loads at https://yourdomain.com/llms.txt, served as plain text. The AI crawler checker reports whether a site already has one.
There is no published evidence that it does. Search engines do not use it for ranking, and no major AI engine has said it reads it. Treat it as low-cost groundwork, not a fix.