How to write an llms.txt file (with example)
llms.txt is a plain-text file that tells AI tools what your site is and where the important content lives. Here's the format and a working example.
By Faraaz Khan
llms.txt is a plain-text Markdown file at the root of your site (`/llms.txt`) that gives AI tools a concise, curated map of what your site is and where the important content lives. Think of it as a `robots.txt` for meaning rather than access, a summary an LLM can read in one fetch.
The format
It's Markdown with a loose convention: an H1 with your site name, an optional blockquote summary, then H2 sections of links with short descriptions. There's no strict schema, clarity is the point.
- 1.Start with `# Your Site Name`.
- 2.Add a one-line `> blockquote` describing what you do.
- 3.Group key URLs under `##` headings (Docs, Products, Guides), each link followed by a short description.
- 4.Keep it short and curated, link the pages you most want cited, not everything.
- 5.Save it as `llms.txt` at your web root so it's reachable at `https://yoursite.com/llms.txt`.
A minimal example
A few lines is enough to start: a title, a summary, and your most important links with one-line descriptions. The goal is that a model fetching this one file understands your site and knows where to look next.
Does it help yet?
Adoption is still emerging, so treat llms.txt as low-cost insurance rather than a guaranteed ranking lever. The fundamentals, readable HTML, schema, answer-shaped content, matter far more. But it's cheap to add and our readiness checker looks for it.
Frequently asked questions
Where do I put llms.txt?
- At the root of your domain, reachable at https://yoursite.com/llms.txt, the same place as robots.txt.
Is llms.txt the same as robots.txt?
- No. robots.txt controls which crawlers may access which paths. llms.txt is a human- and LLM-readable summary of what your site is and where the important content lives. They serve different purposes.
Do AI engines actually use llms.txt?
- Adoption is still early and not universal. It's a low-effort, low-risk addition, but readable HTML, structured data and trustworthy content remain far more important for AI visibility.