Capability gap · explainer

What is llms.txt and do you need one?

llms.txt is a proposed plain-text file, served at yoursite.com/llms.txt, that summarizes your site for AI systems in a format simpler than your HTML. It's an emerging convention, not a required or officially adopted standard — support across AI systems is inconsistent and unconfirmed in places. It costs almost nothing to add, which is the honest case for doing it.

What it actually is

Proposed in 2024 as an analog to robots.txt and sitemap.xml, llms.txt is a Markdown file listing your site's name, a short description, and links to your most important pages — written for a language model to parse quickly, instead of requiring it to crawl and interpret full HTML. Some sites also publish an llms-full.txt with expanded content inline.

What it is not

It is not a guarantee that any assistant reads or uses it. There's no public confirmation from OpenAI, Anthropic, Google, or Perplexity that their production systems consume llms.txt files as part of citation or retrieval decisions — adoption is still informal and vendor-by-vendor. Treat any claim that llms.txt directly causes citations as unverified. It's also not a replacement for actual crawl access (see which bots need robots.txt permission) or for content that's actually written in an answerable shape.

The honest case for adding one anyway

Even without confirmed adoption, an llms.txt file is cheap: a static text file, a few minutes of writing, no ongoing maintenance beyond keeping the link list current. If any current or future AI system does parse it, you're already covered. If none do, you've lost nothing. That asymmetry — near-zero cost, plausible but unconfirmed upside — is the actual argument, not a promised ranking effect.

What to put in one

• Your site or product name and a one-sentence description of what it does
• Links to your most important pages (docs, pricing, key product pages) with a short description of each
• Anything you'd want a model to know before answering a question about you — kept factual, not marketing copy

Build one with our llms.txt builder — it generates the file from a short form, no account needed.

Frequently asked

Does adding llms.txt guarantee ChatGPT or Perplexity will cite me?

No. There's no confirmed mechanism by which it directly causes a citation — it's a low-cost hygiene item with plausible, unconfirmed upside.

Is llms.txt an official web standard?

No — it's a community-proposed convention, not a standard ratified by a standards body or confirmed as required by any AI vendor.

Does it replace robots.txt?

No. robots.txt controls crawler access (can a bot fetch your pages at all); llms.txt is a separate, optional summary file. You may want both — see which AI bots to check for in robots.txt.

Related

For the crawler-access side of AI visibility: Do AI chatbots crawl your website? Which bots, and how to check. For the full list of things that plausibly help: How to get your business recommended by ChatGPT.