llms.txt is a plain-text Markdown file published at the root of a website (/llms.txt) that tells AI assistants like ChatGPT, Perplexity, and Copilot what the site is about and which URLs to prioritize. The spec was proposed in September 2024 by Jeremy Howard of Answer.AI as a vendor-neutral convention. Adoption depends on who you count: about 10% of the nearly 300,000 domains in SE Ranking's November 2025 study had one, while about half of the B2B SaaS sites in our October 2026 check publish a valid file. Publishing one is a low-cost AEO signal for the engines that read it, but Google has said it does not use llms.txt for AI Overviews or AI Mode.
What is llms.txt?
llms.txt is a static file placed at the root of a website that provides AI models with a structured, human-readable description of the site and its most important content. Think of it as a hybrid of three existing conventions: robots.txt (a file at the site root, read by automated systems), sitemap.xml (a structured list of URLs), and a website's "about" or documentation index page (a human-readable summary).
The file was introduced by Jeremy Howard, co-founder of Answer.AI and fast.ai, in a blog post and accompanying specification at llmstxt.org in September 2024. The motivating problem was straightforward: LLM context windows are limited, and when AI systems scrape websites to gather information, they often ingest noise - navigation menus, footer links, analytics tags, unrelated pages. A curated, Markdown-formatted list of the site's most important URLs with short descriptions would give AI systems a clean summary to work from.
The spec is open and vendor-neutral. No single company controls it, and the convention has been adopted voluntarily by documentation sites, SaaS products, and content-heavy publishers throughout 2024 and 2025. Adoption remains uneven: SE Ranking's November 2025 study of nearly 300,000 domains found about 10% of them had published an llms.txt file, while a check of 390 B2B SaaS sites in October 2026 found about half serve a valid one at the root.
The llms.txt format
The file is Markdown. The spec defines a minimal structure that is intentionally simple - easy for both humans to write and LLMs to parse.
- H1 - the name of the site or project. Required. First line of the file.
- Blockquote - a short summary of what the site is about. Optional. Sits directly below the H1.
- Intro paragraphs - zero or more paragraphs providing context, caveats, or pointers. Optional.
- H2 sections - groups of related URLs. Each H2 is a category name (e.g., "Docs", "Blog posts", "Tools"). Below each H2 is a bullet list of linked URLs, each with a short description.
- Optional H2 - a specially-named section flagging URLs that are lower-priority and can be skipped if the model has limited context.
A minimal valid file looks roughly like this structure: site name, one-line summary in a blockquote, then 2-5 H2 sections grouping the most important URLs. The full spec, including edge cases and examples, lives at llmstxt.org.
Why llms.txt matters
Publishing one costs very little. Several factors make it worthwhile even while formal AI-platform endorsement remains ambiguous.
It is a crawlable signal
Any AI system that can fetch arbitrary URLs can retrieve /llms.txt without knowing in advance what the file contains. As AI crawlers and retrieval systems evolve, a file that costs nothing to publish may end up being parsed by tools that don't yet exist. The downside risk is zero; the upside is optionality.
It forces editorial clarity
Writing an llms.txt file requires deciding what the site is about in one or two sentences and which URLs matter most. That exercise surfaces internal disagreements about positioning and content hierarchy - making the file a useful artifact for marketing and product teams even before AI systems read it.
It overlaps with emerging best practices
AirOps found that 68.7% of pages ChatGPT cited used a sequential heading structure (H1, then H2, then H3), versus 23.9% of Google's top results for the same queries (July 2025). llms.txt is one expression of that formatting discipline: structured, cleanly described, explicitly prioritized content.
How to create an llms.txt file
There are three paths.
Use a generator
AI-Advisors provides a free llms.txt Generator, a four-step form: company info, up to six key pages, optional resources, then the finished file. The tool handles the Markdown structure, and you copy, download or email the result and upload it to the site root.
Write it manually
For small sites or sites with a clear content taxonomy, hand-writing the file is fine. Start with the H1 (site name), add a blockquote summary, then group URLs under H2 sections. Keep descriptions short - one line each. Reference examples at llmstxt.org.
Generate it from existing metadata
Static site generators and headless CMSs can often render an llms.txt file from existing content metadata - page titles, descriptions, and category data. For Next.js sites, a dynamic route or build step that reads from the same metadata used in sitemap generation is the cleanest approach.
Once the file is in place, publish it at /llms.txt at the root of the domain. The spec also allows a file at any subpath, such as /docs/llms.txt, and 40 of the B2B SaaS sites in our October 2026 check published only on a docs subdomain, so if your documentation lives on its own subdomain, publish a file there too.
llms.txt vs robots.txt vs sitemap.xml
All three files live at the root of a site. They serve different purposes and should be published together.
A well-prepared AI-visibility stack publishes all three at the site root and keeps them aligned: robots.txt permits the crawlers you want, sitemap.xml lists every URL you want indexed, and llms.txt highlights the few URLs you want prioritized.
Common misconceptions
llms.txt replaces sitemap.xml
It doesn't. sitemap.xml is machine-optimized URL inventory for search engines. llms.txt is a curated human-readable summary for LLMs. They serve different systems and solve different problems. Publish both.
llms.txt is officially endorsed by major AI platforms
As of early 2026, major AI companies have not formally confirmed that llms.txt is parsed as part of their retrieval pipelines. Adoption is community-driven. That does not mean it is useless - it is discoverable by any crawler and is increasingly read by AEO and AI-visibility tooling. But claims that ChatGPT or Perplexity "definitely reads llms.txt" should be treated cautiously until the platforms say so publicly.
More is better
The whole point of llms.txt is curation. A file that lists every URL on a site is just an inferior sitemap. The file should highlight the 5 to 30 URLs that best explain what the site is and what it is authoritative about - not every blog post or landing page.
Frequently asked questions
#What is llms.txt in simple terms?
llms.txt is a plain-text file placed at the root of a website (example.com/llms.txt) that tells AI assistants like ChatGPT, Perplexity, and Copilot what the site is about and which URLs are most important. It is to AI what sitemap.xml is to search engines - a structured hint about what to prioritize. Google has said it does not use llms.txt for AI Overviews or AI Mode. The file uses Markdown format so it is easy for both humans and LLMs to read.
#Who created the llms.txt spec?
The spec was proposed in September 2024 by Jeremy Howard, co-founder of Answer.AI and fast.ai. The official specification lives at llmstxt.org. It is an open, vendor-neutral convention - no single company controls it, and adoption is driven by the broader AI and web community.
#Do AI models actually read llms.txt?
The public evidence is thin. Major AI companies have not formally confirmed they parse llms.txt as part of their crawling or retrieval pipelines, Google has said Google Search does not use it, and Ahrefs found that 97% of about 38,000 valid files on its customers' sites received no requests in May 2026. The file is still discoverable by any model that can fetch arbitrary URLs. Despite the ambiguity, publishing one has become common in B2B SaaS, where about half of the sites in our October 2026 check serve a valid file: it costs almost nothing, it is a useful signal to the tooling ecosystem growing around AI search, and it forces a brand to articulate what matters most on its site.
#What does an llms.txt file look like?
The format is Markdown. A minimal file has an H1 (the site name), an optional blockquote (a short summary), then H2 sections that group related URLs with short descriptions. Sections like 'Docs', 'Blog posts', 'Tools', and 'About' are common. An 'Optional' H2 can be included to flag lower-priority URLs. The full spec with examples is at llmstxt.org.
#How do I create one quickly?
The fastest path is to use a generator. AI-Advisors provides a free llms.txt Generator, a four-step form that takes your company details, up to six key pages and any optional resources, and produces a formatted file in under two minutes. Otherwise, the file can be hand-written in any text editor and uploaded to the root of the site at /llms.txt. Most content management systems support it as a static file.
#Is llms.txt the same as robots.txt?
No. robots.txt controls which crawlers can access which URLs - it is an access rule. llms.txt is a content hint that says 'here is what this site is about and what to read first.' A site should publish both. They operate at different layers of the AI visibility stack and neither replaces the other.
