llms.txt: what it is and whether it matters yet

Updated November 14, 2026 · 4 min read
Short answer

llms.txt is a proposed file, first published in 2024, that gives AI tools a plain markdown summary of a website with links to its key pages. Google says Google Search, including its AI features, ignores it, and the crawler documentation from OpenAI, Anthropic and Perplexity does not say their assistants read it on ordinary websites. It is harmless to add, but it belongs near the bottom of a practice's list.

What llms.txt is

llms.txt was proposed by Jeremy Howard on llmstxt.org in September 2024. The idea is a markdown file at the root of a website, at your domain followed by /llms.txt, written for large language models rather than people. The proposal calls itself exactly that, a proposal, not a standard adopted by any standards body.

The format is simple. The file opens with the site's name as its only required element, followed by a short summary set off as a quotation, optional paragraphs of detail, and then sections that list links to the site's most useful pages, each with a short note. The proposal says the authors expected it to be mainly useful when an AI tool is answering a question, rather than for training models.

Think of it as a table of contents and an elevator pitch, written for a machine.

Who actually reads it

This is the question that matters, and the answer is less than the hype suggests.

Google: in its 2026 guide to optimizing for generative AI features, Google says you do not need to create new machine readable files, AI text files, markup or Markdown to appear in Google Search, including its generative AI features, because Google Search itself does not use them. It adds that it is fine to maintain llms.txt for other services that use it, and that doing so will neither harm nor help your visibility in Google Search.

OpenAI, Anthropic and Perplexity: their published crawler documentation names their search and training crawlers and explains robots.txt controls. None of those pages says the crawlers read llms.txt files on the sites they visit.

The AI companies' own sites: llmstxt.org points out that AI labs publish llms.txt files for their own developer documentation. That helps programmers whose coding tools read documentation. It is not evidence that a consumer assistant reads a practice's file when a patient asks for a doctor.

See your Surge Score in about a minute

Does ChatGPT recommend your practice?

The Surge Score measures five things about your practice website: how often ChatGPT, Gemini and Perplexity recommend you, your PageSpeed, your structured data, your indexing and your reviews, each with its evidence and date. Free.

Why it is not a priority for a practice

Everything an assistant needs to know about your practice should already be on your pages: who you are, where, which providers, what you treat, which insurance, when you are open and how to book. If those pages are crawlable and clearly written, an llms.txt file restates them. If they are not, a summary file does not fix the underlying problem, because any system that wants detail will still go to your pages.

The more common barrier is that pages cannot be read at all, because content loads only through scripts or a crawler is blocked. Our guides on JavaScript sites and AI crawlers and robots.txt and AI crawlers cover those, and both matter more than this file.

If you want one anyway: what to put in it

Adding a file takes little time, and some tools may use it. If you do, keep it short and factual. A file for a hypothetical practice might contain, in order:

  • The practice's name as the top heading
  • A one sentence summary: specialty, city, and who you treat
  • A short paragraph with key facts: locations, whether you accept new patients, the main insurance plans and how to book
  • A section listing links to each location page, with a note on the address
  • A section listing links to provider bios
  • A section listing links to your main service, condition and procedure pages
  • A section with links to new patient information, insurance and booking

Every fact in it must match your site. Use the same practice name and wording you use everywhere else.

Risks and upkeep

The main risk is not harm from the file; it is a second place where facts can go stale. If you change your hours, add a location or drop an insurance plan, the llms.txt file has to change too. A stale file that contradicts your website gives any tool that reads it the wrong answer.

Two other points. Put nothing in it that is not already public on your site. And do not treat it as a control: it does not block or allow anything. If you want to keep a crawler away from your site, robots.txt is the documented mechanism, and if you want a page kept out of Google, Google's documentation says to use noindex or password protection.

Better uses of the same hour

If you have an hour for AI visibility, these are likely to do more than an llms.txt file:

  • Confirm your robots.txt does not block OAI-SearchBot, PerplexityBot or Claude-SearchBot
  • Check that your provider names, hours and insurance appear in the page source, not only after scripts run
  • Update your Google Business Profile, which Google says can help businesses appear in AI responses
  • Make your name, address and phone identical on your site and major directories; see your practice as an entity
  • Ask the assistants your patients' questions and record what they say

If all of that is done and you still have time, adding llms.txt is a reasonable last step. Revisit this page as assistants publish more about what they read.

Checklist

  • Robots.txt and security settings allow the search crawlers of the major assistants
  • Key practice facts appear in the page source of your website
  • If you add llms.txt, every fact in it matches your website
  • Someone owns updating llms.txt whenever hours, locations or insurance change
  • Nothing in llms.txt is information you do not already publish

Frequently asked

Will llms.txt help my practice appear in ChatGPT?

There is no public evidence that it does. OpenAI's crawler documentation explains how OAI-SearchBot surfaces sites in ChatGPT search and does not mention llms.txt. Allowing that crawler and having clear, crawlable pages is what OpenAI's documentation points to.

Does Google use llms.txt?

No. Google says Google Search ignores llms.txt files, including for its generative AI features, and that having one will neither harm nor help your visibility or rankings in Google Search.

Is llms.txt the same as robots.txt?

No. Robots.txt tells crawlers which parts of a site they may visit and is followed by major search engines. llms.txt is a proposed summary of a site's content and does not allow or block anything.

My web vendor says llms.txt is essential. Are they wrong?

Essential overstates it. It is optional and harmless when kept accurate. Ask the vendor which assistant they believe reads it and where that company documents it. If they cannot point to documentation, treat it as a small extra rather than a priority.

Sources

  1. The /llms.txt file, llmstxt.org
  2. Optimizing your website for generative AI features on Google Search, Google Search Central
  3. Latest documentation updates, Google Search Central
  4. Overview of OpenAI crawlers, OpenAI
  5. Does Anthropic crawl data from the web, and how can site owners block the crawler?, Anthropic
  6. Perplexity crawlers, Perplexity
  7. Introduction to robots.txt, Google Search Central
Prefer to talk it through?

Book a strategy call with the team.

Twenty minutes. We'll walk through the specific opportunities in your market and what a MedPracticeGrowth engagement would look like for your practice.

AI patient discovery audit

Is AI recommending you, or your competitor?

See who ChatGPT, Gemini and Perplexity recommend to patients in your area.

Free. Built by physicians.