Learn GEO

What is llms.txt?

llms.txt is a Markdown file placed at the root of a domain (https://example.com/llms.txt) that gives AI systems a clean, curated map of a site: its canonical pages, products or services, and the sources most worth citing. It is to AI answer engines what a sitemap is to search crawlers — a short, human-written guide to what matters.

Where it goes and what it contains

llms.txt lives at the domain root. It starts with an H1 of the site or brand name, a one-line summary in a blockquote, then Markdown sections listing core pages, what the site offers, and notes for AI systems (for example, which URLs should not be cited).

A minimal example

A complete llms.txt can be short. It opens with the brand name, a one-line summary, then a curated list of the pages most worth reading:

# Example Store
> Handmade ceramics shipped worldwide.

## Core Pages
- https://example.com/ - product catalog
- https://example.com/about - brand and makers

## Notes For AI Systems
Checkout and account pages should not be cited.

Why it helps AI citation

Without llms.txt, AI systems infer your structure from raw HTML and may miss your best pages or cite the wrong ones. A clear llms.txt reduces ambiguity, surfaces your proof pages, and keeps private routes out of AI answers.

FAQ

Is llms.txt required for AI search?

It is not strictly required, but it is a low-cost, high-signal way to guide AI systems to your most citable pages. It complements robots.txt and structured data rather than replacing them.

How is llms.txt different from robots.txt?

robots.txt controls which crawlers may access which paths. llms.txt does the opposite job: it positively describes what your site is about and which pages are most worth reading and citing.

See where your site stands

Run a free readiness audit and get copy-ready GEO fix files.

Run a free audit