Question 1

What is llms.txt?

Accepted Answer

llms.txt is a proposed convention (llmstxt.org) for a plain Markdown file at your domain's root that gives AI models a clean, curated map of your site — a title, short summary, and links to the pages that matter most, without the noise of a full crawl.

Question 2

Where do I put the generated file?

Accepted Answer

Save it as llms.txt and publish it at your domain root, e.g. https://yourcompany.com/llms.txt, the same way robots.txt or sitemap.xml sit at the root.

Question 3

What if crawling my site fails?

Accepted Answer

Some sites block automated fetches or render everything client-side, so the crawl step can fail. You can always fill in the title, summary and links by hand below — the file it generates is identical either way.

Question 4

Does having an llms.txt guarantee AI models will use it?

Accepted Answer

No convention here is officially standardised or guaranteed to be read by every model, but it costs nothing to publish and gives crawlers that do respect it a much cleaner source than scraping your rendered HTML.

Give AI models a clean map of your site

One Markdown file

Crawl to prefill

Always editable

Step 1 · Crawl to prefill (optional)

Step 2 · Details

llms.txt

About llms.txt