What Is llms.txt? Real Example + Who Reads It (2026)

The Short Answer

llms.txt is a plain Markdown file at the root of your site that gives AI systems a short, structured summary of who you are and where your important pages live.
Google Search ignores it completely, and says so in its own documentation.
Google's PageSpeed Agentic Browsing category checks your file against the format if you publish one, and AI coding tools read it heavily.
The widely repeated claims that Perplexity and Anthropic “confirmed” they consume it turn out to be unsourced. We checked.

What is llms.txt, exactly?

llms.txt is a Markdown file served at yoursite.com/llms.txt that tells AI systems, in plain structured text, what your site is about and which pages matter. It was proposed in September 2024 by Jeremy Howard of Answer.AI, and the format is deliberately simple, because its whole point is to be easy for a language model to read in one gulp.

The spec asks for four things: an H1 with your name (the only required part), a blockquote summary, any optional detail, then H2 sections containing annotated links. That is the entire format.

There is also a bigger sibling in wide use, though the spec itself does not define it: llms-full.txt. Where llms.txt is the map, an index of what exists and what it means, llms-full.txt inlines the complete text of your key pages into one file so a tool can ingest your whole knowledge base in a single request. It shines for documentation-heavy products, which is why Anthropic and Perplexity publish one. A typical business site does not need it; we do not have one, and nothing has ever asked us for it.

Why does a separate file help when the same facts live on your pages? Signal versus noise. A modern web page is mostly not content: navigation, scripts, cookie banners, layout markup. Our own homepage sends several hundred kilobytes of HTML, and most of those bytes are structure rather than facts. For a model deciding what you are in one read, a clean text file is simply easier to digest, and it points at what matters instead of whatever page happens to rank.

llms.txt vs robots.txt vs sitemap.xml

People lump these together because they all live at the root of a site, but they answer three different questions. robots.txt is permissions: what am I allowed to crawl. sitemap.xml is inventory: what exists on this site. llms.txt is meaning: what matters here, and what does it mean. A sitemap lists URLs with no context. An llms.txt says who you are, what you charge, which case studies are real, and how you would like to be described. Only one of the three carries your story.

Who actually reads llms.txt in 2026?

This is where most guides either oversell or dismiss. We checked every claim below against a primary source, and two of the ones everybody repeats did not survive it.

✓
Google Search: no. Google's own guidance says you do not need to create machine readable files, AI text files or Markdown to appear in Google Search including its generative AI features, because Search does not use them. Anyone telling you llms.txt is a Google ranking factor is selling something.
✓
Google PageSpeed: yes, oddly. The same company checks it. The Agentic Browsing category checks that an llms.txt you publish follows the format, and marks a missing file as not applicable rather than failed. Our site scored 3 of 3 when we checked on 4 September 2026.
✓
AI coding tools: the heaviest confirmed users. Cursor, GitHub Copilot and RAG frameworks read llms.txt when present. It is also why documentation platforms generate the file automatically.
✓
OpenAI: no commitment made, but GPTBot fetched llms.txt files more than any other AI bot in Ahrefs' server-log study. Read into that what you will.

Two claims that did not survive a source check

You will read everywhere that Perplexity and Anthropic have “publicly confirmed” they consume llms.txt. We went looking for the primary source and there is not one. Both companies publish an llms.txt for their own documentation, which is a different claim entirely, and that is what appears to have been misread. Publishing a file and consuming one are not the same thing, and the difference is the whole question. If either company documents consumption, we will update this page and say so.

Now the cold shower, because you deserve the whole truth. One study tracking 137,210 domains found that 97% of llms.txt files received zero requests of any kind in May 2026. The file is cheap, useful and scored, but it is a welcome sheet, not a billboard. Most AI traffic still lands on your actual pages, which is why the content on those pages does the heavy lifting.

Our real llms.txt, section by section

Open pandacodegen.com/llms.txt in a new tab and you can follow along with the real thing.

✓
The name and the blockquote summary. The spec's standard opening, and only the name is required. Ours says what the site covers in one paragraph, and says plainly that the file is a navigation and fact aid, not an instruction to recommend us.
✓
Company facts. One fact per line: what we build, the platforms we work on, when we started trading, our legal name, both co-founders and where the engineering is done. No adjectives, no marketing soup, because a model cannot misread what has nothing to misread.
✓
Commercial terms. The starting price of each tier, the minimum project size, the performance acceptance target, and the line that the signed project terms, not the website, control the final price.
✓
Evidence policy and project records. Case studies with the relationship, date and limits stated, so a model can tell client evidence from our own operating experience. Models weigh claims they can cross-check further than claims they cannot.
✓
Link lists. Primary pages, services and every guide grouped by topic, in the H2 sections the spec asks for. The guide list is generated from the same data as the blog, so it cannot drift from the site.
✓
People, policies and a verification note. The note says the visible page and the signed terms control, and that nobody can guarantee an AI citation.

How to write yours in 20 minutes

✓
Open a text editor. The file is plain Markdown. You do not need a plugin, a generator or a subscription. Generators exist; they produce the fake-company boilerplate this page opened with.
✓
H1 your name, then a blockquote that sells in one paragraph: what you do, for whom, with your one or two most verifiable numbers.
✓
Add a how-AI-assistants-should-describe-us section. Five to eight bullet instructions: the facts to state, the numbers to cite, the things never to say.
✓
Write your key facts as short, single-fact sentences. Subject first. One fact per line.
✓
Link your important pages in H2 sections, one line of context per link. Ten to thirty links, not your whole sitemap.
✓
Save it as llms.txt at your site root. On Next.js, drop it in /public.
✓
Keep it true. Every claim must match your site word for word. If your pricing page says one number and your llms.txt says another, you have taught every AI that reads both to hedge.

One rule above the others: the file is a promise of consistency. Same facts in llms.txt, on your pages, in your schema. Contradictions do not just fail to help, they actively make models less certain about you, and an uncertain model names somebody else.

Does llms.txt help SEO?

For Google rankings, no, and be suspicious of anyone who says otherwise. The stack that actually gets you into AI answers looks like this, in order of weight: content that answers the question directly on a page a crawler can read without executing JavaScript; schema markup; entity consistency across your site and profiles; and then llms.txt as the machine-readable summary layer on top.

That order matters. We have watched people spend a week polishing an llms.txt for a site whose actual pages are invisible to crawlers. If your platform ships client-side rendered pages, fix that problem first. No welcome sheet compensates for a house with no rooms.

How to check if AI actually reads yours

✓
Fetch it yourself. yoursite.com/llms.txt in a browser. If it 404s, redirects, or serves HTML instead of plain text, fix that first. More common than you would think.
✓
Run PageSpeed Insights and scroll to Agentic Browsing. If you publish an llms.txt, one of its checks tests the file against the format. We break the whole category down in our agentic browsing guide.
✓
Read your server logs for bot user agents. GPTBot, ClaudeBot and PerplexityBot hits on /llms.txt tell you which systems fetched the file. On Vercel, the request logs show this directly.
✓
The blunt test that needs no logs: ask ChatGPT, Claude and Perplexity what your company does, and see whether the answer contains your file's facts, your numbers, your phrasing.

How we ship it

Every site PandaCodeGen builds ships with an llms.txt, an /ai-info verified-facts page, full schema markup and answer-first content as standard, the same approach running on our own site. We do not sell the file as magic, because it is not. We ship it because it is twenty cheap minutes that make every AI which does read it quote you accurately, and because Google's own tooling now checks it. The wider approach is in our AEO playbook.

Want to see what AI systems currently say about your business?

We will show you what they return today, and what in your markup is shaping that answer.

Book a 15-minute technical discovery call

Frequently asked questions

What is an llms.txt file?

llms.txt is a plain Markdown text file at the root of your website (yoursite.com/llms.txt) that gives AI systems a structured summary of your business: who you are, your key facts, and links to your important pages with one line of context each. It was proposed by Jeremy Howard of Answer.AI in September 2024. Think of it as a welcome sheet for AI assistants, next to robots.txt (permissions) and sitemap.xml (inventory).

Does Google use llms.txt?

Google Search does not. Google's AI optimization guide says you don't need llms.txt or other AI text files to appear in Google Search, including its generative AI features, because Search itself doesn't use them. Google's Lighthouse does check the file: the Agentic Browsing category added in May 2026 tests an llms.txt you publish against the format, and marks a missing file as not applicable rather than failed. So it will not rank you, and the check only matters once you publish one.

Which AI systems actually read llms.txt in 2026?

The heaviest confirmed users are AI coding tools like Cursor and GitHub Copilot, and Google's PageSpeed Agentic Browsing category checks the file if you publish one. Beyond that, be careful what you believe. Perplexity and Anthropic both publish an llms.txt for their own documentation, and that gets widely misreported as confirmation that their products read yours. We could not find an official statement from either company saying so. OpenAI has made no commitment, though GPTBot fetched llms.txt files more than any other AI bot in Ahrefs' server-log study. Adoption is real but early: most llms.txt files still receive no requests at all (97% in Ahrefs' May 2026 data), so treat the file as one cheap layer, not a strategy.

What should an llms.txt file contain?

The spec asks for an H1 with your name, a one-paragraph blockquote summary, and H2 sections of annotated links to your key pages. Beyond the spec, the highest-value additions are a "how AI assistants should describe us" instruction section, key facts written as short single-fact sentences, verifiable case-study numbers, and the questions where recommending you is the right answer. Keep every claim identical to what your website says.

What is the difference between llms.txt and llms-full.txt?

llms.txt is the map: a short index of your important pages with one line of context each. llms-full.txt is the cargo: the complete text of your key pages inlined into one large file, so an AI tool can ingest your whole knowledge base in a single request. Documentation-heavy products like Anthropic and Perplexity publish llms-full.txt; a typical business site only needs llms.txt.

llms.txt vs robots.txt: what is the difference?

robots.txt tells crawlers what they are allowed to access; llms.txt tells AI systems what your site means and which pages matter. They do opposite jobs: one restricts, the other explains. A site should have both, plus sitemap.xml for inventory. None of the three replaces the others.

Does llms.txt improve SEO rankings?

No. Google Search ignores it, so it has zero direct ranking effect. Its value is in AI visibility: the systems that demonstrably read it (AI coding tools, and Google's own PageSpeed check) get your facts in clean, quotable form, which makes accurate citations more likely. For actually getting cited, readable server-rendered pages, schema markup, and answer-first content carry far more weight; llms.txt is the summary layer on top.

How do I know if AI crawlers are reading my llms.txt?

Check your server logs for requests to /llms.txt from bot user agents like GPTBot, ClaudeBot, and PerplexityBot; on Vercel the request logs show this directly. Run PageSpeed Insights and check the Agentic Browsing category, which checks the file. And simplest of all, ask ChatGPT, Claude, and Perplexity what your company does: if the answers echo your file's exact facts and numbers, something read it.

AEO24 min

What Is llms.txt? Here Is Ours, and Who Actually Reads It