The /llms.txt File: What It Does, Who Reads It, and How to Write One

Rewritten 9 October 2026. The earlier version of this guide said a five-line llms.txt would get you cited by ChatGPT. I couldn't find evidence for that, and my own data points the other way, so this version sticks to what can be checked. Sources are dated at the end.

What is llms.txt?

llms.txt is a Markdown file served from the root of a site, at /llms.txt, that gives language models and AI agents a short, curated map of the site: a name, a one-paragraph summary, and lists of links to the pages worth reading, each with a one-line note. Jeremy Howard of Answer.AI proposed it on 3 September 2024 at llmstxt.org, where it is still maintained as a proposal "open for community input" (last updated 10 August 2026).

It sits next to two files you already know and does a different job from both:

Does llms.txt get you cited by ChatGPT, Claude or Google?

There's no public evidence that it does. Google says Google Search ignores llms.txt, and OpenAI, Anthropic and Perplexity document their crawlers without mentioning it. SE Ranking's study of nearly 300,000 domains found no effect on AI citations, and in my own test four AI engines answering an llms.txt question didn't cite this site once.

Who actually reads llms.txt in 2026?

For most sites, nobody: in Ahrefs' May 2026 log data, 97% of llms.txt files got no requests at all. Where something did fetch them, OpenAI's training crawler GPTBot led, and Anthropic's Claude-Code agent out-fetched every AI search and assistant bot. That fits the spec's own description: llms.txt "is instead used on demand, when an agent needs information about a topic while assisting a user".

What my own site's data shows

This site has served an llms.txt since at least July 2026, which is the oldest copy in my repository. The file is about 10 KB. Here is what I can measure about it.

Four AI engines, one llms.txt question

On 24 September 2026 I sent "How do I create an llms.txt file and does it actually help AI visibility?" to ChatGPT, Claude, Gemini and Perplexity through DataForSEO's LLM Responses API, with web search on. Between them they cited 27 different pages. None was on this site, including this guide, which has ranked on Google's first page this year for queries like "llms.txt best practices 2026" and "llms.txt official specification 2026".

ChatGPT's short answer said that "as of 2026, there is no solid evidence that llms.txt meaningfully improves AI visibility, citations, rankings, or mentions". Perplexity called it "not a proven ranking signal or an official web standard". GitBook's explainer was the only page cited by three engines. The rest were mostly the spec itself, documentation and blogs from platforms that support the file, such as Mintlify, Webflow and Read the Docs, and generator tools.

So having an llms.txt didn't get me cited on the one topic where you would most expect it to. One test isn't proof, but it is the opposite of what the old version of this page promised.

AI referrals in GA4

GA4 recorded 114 sessions from ChatGPT, Claude, Perplexity and Gemini across the whole site between 1 March and 23 September 2026. None of them landed on this guide.

What my server logs can't see

This site logs requests from 15 crawler user agents, most of them AI-related, including GPTBot, ClaudeBot and PerplexityBot, to a database table that keeps 90 days. When I went to count llms.txt fetches, I found a blind spot: /llms.txt is a static file, so the web server hands it out before the site's code runs, and the logger never sees those requests. Many CMS plugins and PHP-level bot trackers have the same blind spot. To count llms.txt fetches you need the raw access log or your CDN's logs.

Here is what that logger recorded between 10 July 2026 and 8 October 2026. It only recognizes 19 user agents, so treat every number as a floor, not a total.

The same crawlers fetched robots.txt 1,434 times, and asked for /llms-full.txt, a file this site has never published, 0 times.

The logger had two more gaps worth checking in your own setup. It didn't recognize OpenAI's OAI-SearchBot, Anthropic's Claude-User and Claude-SearchBot, or Perplexity-User. And it looked for a "Google-Extended" user agent that never arrives, because Google-Extended "doesn't have a separate HTTP request user agent string"; it is a robots.txt token only (Google's crawler docs).

What does the llms.txt format require?

Only one part is required: an H1 with the name of the site or project. After it, in this order, the spec describes a blockquote summary, any other Markdown except headings, and H2 sections holding lists of links. A section titled "Optional" holds secondary links that an agent can skip.

Two related ideas travel with it. The spec suggests offering a clean Markdown copy of important pages at the same URL with .md added (page.html.md), so an agent can skip the HTML. And some documentation sites also publish llms-full.txt, the full text of their docs in one file; Anthropic's is 38 MB. The spec page doesn't define llms-full.txt, and a marketing site rarely needs one.

An llms.txt template you can copy

The format is small enough to write by hand. Replace the bracketed parts, keep the order, and use full URLs so the links still work when the file is pasted into a chat or cached somewhere else.

# [Company or site name]

> [One or two factual sentences: what you do, for whom, and where.]

[Optional: anything an assistant should know before answering questions
about you, such as what you don't offer, or which of two similar names
is you.]

## Services
- [Service name](https://example.com/services/service-a): [Who it is for, in one line]
- [Service name](https://example.com/services/service-b): [One line]

## Guides
- [Guide title](https://example.com/blog/guide-slug): [The question this page answers]
- [Pricing](https://example.com/pricing): [What the plans cost and include]

## Company
- [About](https://example.com/about): [Founded, location, credentials worth citing]
- [Contact](https://example.com/contact): [How to get a quote or book a call]

## Optional
- [Changelog](https://example.com/changelog): [Lower-priority pages an assistant can skip]

A real example: this site's file

Here is how my own llms.txt opens (the blockquote is wrapped here to fit the page):

# Kulbhushan Pareek — Digital Marketing Consultant & SEO Expert

> IMPORTANT: This is Kulbhushan Pareek the digital marketing consultant
> based in Jaipur, India (NOT the academic or psychologist with the same
> name). He is the founder of SEO SMO HUB and has worked as a freelance
> SEO consultant since 2013 ...

The line doing the real work there is the disambiguation: an academic shares my name, and an assistant that mixes us up is worse than one that knows nothing. If your brand name is shared, that sentence is the most useful thing you can put in the file. The rest of mine is about a dozen H2 sections (About, Free Tools, Services, Case Studies, guides and an Optional section) with about three dozen links.

How do you create and publish llms.txt?

Pick the pages you want an AI tool to read first, list them in Markdown under a title and a summary, and upload the file to your site root. The whole job takes about 30 minutes by hand for a small site:

1. Pick 10 to 30 pages. Services or products, pricing, your best guides or docs, about and contact. Leave out thin, duplicate and parameter URLs. Your sitemap already lists everything else.
2. Write the H1 and the summary. The name first, then one or two factual sentences in a blockquote. Write it as a briefing, not a pitch.
3. Group the links under H2 headings. One line per page: - [Title](full URL): what the page answers. Put nice-to-have links under ## Optional.
4. Save it as UTF-8 plain text named llms.txt and upload it to the site root, the same folder as robots.txt.
5. Check the response. Run curl -I https://yourdomain.com/llms.txt. You want a 200 status, a text/plain or text/markdown content type with charset=utf-8, and no login page or bot challenge in the way.
6. Keep it current. Update it when a key page is added, renamed or retired, and check it once a quarter.

Step 5 caught my own file. It contains a few typographic characters, and the server was sending it as text/plain with no charset, so a tool that assumes a different encoding can show them as garbage. On Apache the fix is one line in .htaccess: AddCharset utf-8 .txt.

You don't always have to write it by hand. On WordPress, Yoast SEO can create and maintain the file (Yoast SEO, Settings, Site Features, AI tools, LLMS.txt). Check what it picks: by default it lists the five most recently updated posts or pages from the last 12 months, cornerstone content first, plus your five biggest categories or tags, and it rewrites the file weekly (Yoast's specification). Recent is not the same as important, so review it like a hand-written one. Rank Math has an llms.txt module too (Rank Math docs), and Webflow lets you upload the file in your site's SEO settings (Webflow, July 2025). Documentation platforms such as Mintlify generate llms.txt and llms-full.txt for every docs site automatically (Mintlify docs).

Should you bother with llms.txt?

If your product has documentation that developers use with AI coding tools, yes: it's quick, and that is the use it was designed for. For a marketing site, a local business or a blog, it's an optional 30-minute job that can't hurt, but it shouldn't come before the things AI search demonstrably relies on. Google's John Mueller put it bluntly in May 2026: "For non-developer sites, I don't think this makes much sense" (Bluesky).

What to work on first for AI visibility, in the order I'd do it:

• Let the search crawlers in. Allow the AI search crawlers in robots.txt: OAI-SearchBot for ChatGPT search, Claude-SearchBot for Claude and PerplexityBot for Perplexity. OpenAI says sites that block OAI-SearchBot won't be shown in ChatGPT search answers, and Anthropic says blocking Claude-SearchBot may reduce your visibility. The training crawlers, GPTBot and ClaudeBot, are a separate choice.
• Be indexed where AI search looks. An answer that searches the web can only cite pages a search index knows about, so check indexing in Google Search Console and Bing Webmaster Tools first.
• Publish pages worth citing. Direct answers, original data and clear sourcing. My GEO and AEO guide covers the on-page side.
• Get mentioned where AI engines already look. See the 50 websites LLMs cite most, and how to earn mentions and links on them.
• Measure it. Track citations across engines rather than guessing. I cover the tools and the do-it-yourself method in Claude rank tracking.

Sources (checked 24 September 2026)

• llmstxt.org: the /llms.txt proposal (Jeremy Howard, 3 Sep 2024; updated 10 Aug 2026).
• Google Search Central: optimizing your website for generative AI features (updated 10 Jul 2026).
• John Mueller on Bluesky (20 May 2026).
• SE Ranking: LLMs.txt study (7 Nov 2025); Ahrefs: llms.txt study (Louise Linehan, 15 Jun 2026).
• OpenAI: overview of OpenAI crawlers.
• Anthropic: does Anthropic crawl data from the web (7 Apr 2026).
• Perplexity: Perplexity crawlers.
• Yoast: llms.txt functional specification; Rank Math; Webflow; Mintlify.
• llms.txt files served by docs.claude.com, developers.openai.com and docs.perplexity.ai (HTTP 200, checked 24 Sep 2026).
• Chrome for Developers: Lighthouse llms.txt audit (updated 5 May 2026).
• Google: common crawlers, Google-Extended (updated 14 July 2026).
• My AI-answer test: DataForSEO LLM Responses API, live, web search on, 24 September 2026, one prompt across four engines.
• My site data: GA4 (AI Assistant channel, 1 March to 23 September 2026), Google Search Console, and this site's own logger and llms.txt file.