What is an llms.txt file and does your website need one?

An llms.txt file is a plain text file at the root of your domain that summarizes what your site is and links to the pages you most want an AI system to read. It takes about twenty minutes to write, it cannot hurt you, and it is not a ranking switch.

How it differs from files you already have

robots.txt tells crawlers what they may not fetch. It is a set of permissions.
sitemap.xml lists every URL you want indexed. It is an inventory, and it is machine oriented and unranked.
llms.txt is editorial. It says, in plain language, what this company is, and here are the dozen pages that best explain it. It is a curated shortlist with context, not a dump.

That difference is the whole point. A sitemap with four hundred URLs gives a model no idea which twelve matter.

The honest read on adoption

This is a proposed convention, not a standard that every AI vendor has committed to honoring, and no major assistant has published a guarantee that it reads the file. So treat it the way you would treat a well written about page: cheap, low risk, potentially useful, and absolutely not a substitute for having good content on crawlable pages. If someone tells you an llms.txt file will get you cited by ChatGPT, they are overselling it.

What to put in it

A one paragraph description of the business, then grouped links with a short sentence each: core service pages, your knowledge base, your best explanatory blog posts, and your contact page. Keep it current. A stale file pointing at dead URLs is worse than no file. The build steps are laid out in our guide to creating an llms.txt file.

Spend your real effort on the pages themselves. The file is a map, and a map of nothing is still nothing.

What is an llms.txt file and does your website need one?

A plain text map that tells AI crawlers what your site is and where the answers are.

How it differs from files you already have

The honest read on adoption

What to put in it