Validate whether your site has a correctly formatted llms.txt file — the emerging standard that tells AI tools what your site is about and which pages matter most.
llms.txt is a plain Markdown file served at /llms.txt on your domain. Proposed by Answer.AI in 2024, it gives large language models a structured, human-readable map of your site during inference. Where robots.txt governs crawl access and sitemap.xml lists URLs for indexers, llms.txt is designed for the moment an AI tool needs to quickly understand your site's purpose and key content — before it decides whether to surface your pages in a response.
The format is deliberately minimal. AI tools often operate under tight context windows; a concise, well-structured file is more useful than an exhaustive dump.
A valid llms.txt file follows this structure:
# Site Name
> One-sentence description of what the site does.
## Section Name
- [Page Title](https://example.com/page): Optional short description.
- [Another Page](https://example.com/other)
## Optional Second Section
- [Contact](https://example.com/contact)Rules that validators check:
/llms.txt with HTTP 200text/plain#)[text](url)) must be presentAn optional companion file, /llms-full.txt, can include the full text of your most important pages inline — useful for sites whose content is too long for a single prompt but where you want AI tools to have complete detail on specific documents.
AI-powered tools like Perplexity, ChatGPT with Browse, and Claude Projects fetch live content when answering queries. Without a clear content map, these tools rely entirely on their crawlers' ability to parse your HTML — which means JavaScript-rendered content, deeply nested navigation, and non-semantic markup can all be silently skipped.
llms.txt solves this by giving AI tools a deterministic, crawler-independent entry point. Sites with a well-structured llms.txt are more likely to be represented accurately when an AI tool decides whether to cite them.
For the full picture of what affects your AI visibility, see the AI SEO checklist. To understand how AI crawlers actually access your site, see the robots.txt AI crawlers reference.
llms.txt at your web root.>) with a one-sentence description.Check whether your site has a valid llms.txt — free, takes 30 seconds.
Scan my site →No single file guarantees citation. LLM outputs depend on training data, retrieval pipelines, and prompt context. However, llms.txt ensures AI tools that fetch live context can quickly understand your site's structure and find your most authoritative pages.
Not yet — it is a community proposal with growing adoption. Answer.AI published the initial spec, and several AI companies have expressed support. Think of it the way early adopters treated robots.txt before it became a de-facto standard.
llms.txt is a compact index — titles, URLs, and short descriptions. llms-full.txt embeds the actual page content inline, giving AI tools the full text without further fetches. Use llms.txt for navigation and llms-full.txt for depth on your most important pages.
It has no negative effect on traditional search engine indexing. Google and Bing crawlers will simply ignore a file they do not parse. It is purely additive — an extra signal layer for AI tools on top of your existing SEO stack.