What is llms.txt, and does it actually work?
What the llms.txt file is, how to write one, and what is known and not known about its effect on AI visibility.
Last updated:
Short answer
llms.txt is a file placed at your site's root that tells AI systems, in Markdown, what your site is and which pages matter most. It is cheap to set up and does no harm; but no major AI platform is confirmed to use it for ranking or source selection, and in a measurement across 137,000 domains 97% of llms.txt files received no requests at all. Add it, but do the real work in content and sources.
What goes in the file
- At the top, the site's name (# heading) and a one- or two-sentence summary (> quote).
- Links to the important pages, each with a short description.
- Optionally an llms-full.txt with all the content in one file.
Why its effect is debated
Search engines have read standards such as robots.txt and sitemaps for years; llms.txt is not yet a standard but a proposal. Which AI crawler reads it, and whether it changes anything, is unknown, and measurements show most sites' files are never requested.
What works better
- Not blocking AI crawlers in robots.txt (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot).
- Question-and-answer pages that are quotable and current.
- Being present on third-party sources (lists, reviews, communities).
- Offering an official connector (MCP) assistants can read your site through; Turkey's Evrim Ağacı does this, and so does Mavzena.
Frequently asked
Does llms.txt replace robots.txt?
No. robots.txt says what crawlers may access; llms.txt is only a summary and a map.
Does Mavzena have an llms.txt?
Yes: mavzena.com/llms.txt, and mavzena.com/llms-full.txt with all the guides.
Sources
Does your brand show up in AI?
See what ChatGPT, Gemini, Claude and other engines say about your brand with a free audit.