EST. MMXXVI · THE INSTITUTION OF RECORD FOR AI CITATION · OPEN METHODOLOGY

The AI Citation Institute sealTHE AI CITATION INSTITUTEEx corpore, auctoritas.

The AI Citation Institute · The Answers

What is an llms.txt file?

An llms.txt file is a plain-text Markdown file you place at the root of your domain (yoursite.com/llms.txt) that gives AI crawlers a curated map of the pages you most want read and cited. It's the same idea as robots.txt or sitemap.xml, but aimed at large language models rather than search bots: a short paragraph describing what the site is, followed by linked sections that point to your key data, documentation, and answer pages, each with a one-line summary. The point is orientation. Instead of leaving a crawler to guess which of your thousands of URLs actually carry the substance, you hand it a clean, human-readable index it can parse in one fetch. Being Markdown, it's trivially machine-legible and needs no special tooling to author. Two honest caveats matter. First, adoption is uneven; not every engine reads llms.txt yet, so treat it as a hint, not a guarantee. Second, it is hygiene, not a ranking lever. It helps a crawler find and parse what already exists; it will not make thin or unremarkable content get cited. If the underlying pages aren't worth citing, an llms.txt won't change that.

What goes in an llms.txt file

The format is loose but conventional: an H1 with the site or product name, one paragraph describing what it is, then Markdown link lists grouped by section. Each link gets a short summary so a crawler knows what it will find before fetching it.

Anatomy of an llms.txt file
ElementWhat it isExample
Title (H1)The site or product name# The AI Citation Institute
Summary blockquoteOne paragraph on what the site is and who it's for> The AI Citation Institute measures which pages AI engines cite.
Linked sectionsH2 groups (Docs, Data, Answers) with Markdown links## Answers
Per-link noteOne line after each link explaining the page- [Methodology](/methodology): how the panel works
Optional sectionLower-priority links a crawler may skip## Optional

Keep it curated. A dump of every URL defeats the purpose; the value is the shortlist.

How it differs from robots.txt and sitemap.xml

robots.txt tells crawlers what they may not touch. sitemap.xml lists every URL for completeness. llms.txt does something else: it's an editorial recommendation of the pages worth reading, written for a language model to skim rather than a spider to enumerate.

The three aren't substitutes. A site can and often should publish all three, each serving a different reader.

What it does not do

An llms.txt is an invitation to crawl, not a promise of citation. It lowers the odds that good content is overlooked because it was buried; it does nothing for content that wouldn't earn a citation on its own merits.

Anyone selling llms.txt as a shortcut to AI visibility is overstating it. The lever is still the substance of the pages you link to, plus the internal-link graph that connects them.

The AI Citation Institute publishes its own file at /llms.txt as a working example.

Common questions

Where does an llms.txt file go?+

At the root of your domain, served as plain text at yoursite.com/llms.txt, the same location convention as robots.txt.

Do all AI engines read llms.txt?+

No. Adoption is uneven and still growing. Treat it as a helpful hint that some crawlers use, not a standard every engine honors yet.

Will an llms.txt file get my pages cited?+

Not by itself. It helps a crawler find and parse what's already there. It's hygiene, not a ranking lever, and it won't make thin content get cited.

keep reading

See what AI says about your brand right now — free, on a live engine.

Scan your domain