What is llms.txt and how to create one?
llms.txt is a plain-text file, placed at the root of your site (/llms.txt), designed to guide AI crawlers. It gives them a curated summary of your site and an index of your most important pages, in a format that's easy for a language model to read.
Think of it as a text-based map for AI engines like ChatGPT, Perplexity, and Gemini — a companion to your sitemap and your robots.txt, not a replacement for either.
llms.txt vs robots.txt vs sitemap.xml
- robots.txt — access rules: what each bot is or isn't allowed to crawl.
- sitemap.xml — a complete list of URLs for engines to index.
- llms.txt — a curated summary plus your key links, optimized so an LLM understands what your site is about.
They don't compete; they complement each other. robots.txt controls access, sitemap.xml enumerates everything, and llms.txt explains and prioritizes. An AI engine reading all three has the clearest possible picture of your site.
What it's for
- Reduces ambiguity. The model understands your value proposition and your key sections instead of guessing from raw HTML.
- Highlights your most citable content. You point to the pages you actually want quoted, not every URL on the domain.
- It's low-cost and gaining adoption. Writing one takes minutes, and a growing share of the AI ecosystem reads it.
It won't, on its own, get you cited in AI answers — your content still has to be accurate, well-structured, and crawlable. But it's a cheap clarity signal that removes friction for the models deciding whether to use you.
How to create one (example)
It's plain Markdown. A simple structure looks like this:
# Your Brand Name
> One clear sentence describing what your company does and who it's for.
## Main pages
- [Home](https://yourdomain.com/): what you offer.
- [Pricing](https://yourdomain.com/pricing): plans and costs.
## Guides
- [Guide X](https://yourdomain.com/guide-x): short summary.
The format is intentionally minimal: an # H1 with your brand name, a > blockquote with a one-line description, and ## sections listing your key links with a brief note after each one. Keep the descriptions short and honest — this is a map, not a sales page.
Save the file as llms.txt and publish it at the root of your domain, served as text/plain. Verify it by opening https://yourdomain.com/llms.txt in your browser: you should see the raw text, not a 404 or a styled HTML page. Many teams also add a longer llms-full.txt variant with the full body text of key pages, but the short index above is the place to start.
How to know if you're missing it
The simplest check is to load https://yourdomain.com/llms.txt yourself. If it 404s, you don't have one. But llms.txt is only one of several AI-readiness signals — it's worth pairing it with a quick look at whether your sitemap.xml exists and whether the AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) are actually allowed through your robots.txt and CDN.
AEON42 checks all of this automatically. It tells you whether your site has an llms.txt, whether your sitemap.xml is in place, and whether AI crawlers can reach you — and it shows that next to your real SEO performance from Search Console, so you see GEO, AEO, and SEO in one view instead of three disconnected tools. See the plans or keep reading with what is GEO and how to allow AI crawlers.
Frequently asked questions
- Does llms.txt replace robots.txt?
- No. robots.txt tells each bot what it may crawl; llms.txt is a curated text map that helps AI models understand what your site is about and which are your key pages. They're complementary, not interchangeable.
- Where does the llms.txt file go?
- At the root of your domain, reachable at https://yourdomain.com/llms.txt, served as plain text (text/plain).
- Is llms.txt required?
- It's not an official standard yet, but it's low-cost and adoption is growing. Treat it as one more clarity signal for AI crawlers rather than a mandatory file.
Want to measure this on your site? AEON42 connects your Search Console and tracks your AI visibility alongside your SEO.
View plans