llms.txt examples and a template you can copy

An llms.txt example is easiest to understand as a short markdown file at yoursite.com/llms.txt: an H1 with your site name, a one-line summary in a blockquote, then H2 sections listing your most useful pages as links with a note on each. Below is a complete file you can copy, a blank template, and what Google says the file does and does not do.

What is llms.txt?

llms.txt is a markdown file that gives AI agents a curated map of your site. It does not hold crawl rules and it does not replace your sitemap. It is a short, readable guide to the pages that matter.

The llmstxt.org proposal describes it as a /llms.txt markdown file that provides LLM-friendly content: brief background information, guidance, and links to detailed markdown files. The proposal draws the contrast with sitemaps directly: while sitemaps list all pages for search engines, llms.txt offers a curated overview for LLMs. It also says agents are expected to view or search llms.txt to find the information they need, then follow the relevant links.

So write it as a starting point, not an index. A list of every URL on your site defeats the purpose.

What does an llms.txt example look like?

Here is a complete llms.txt example for a fictional software company. It follows the llmstxt.org layout: an H1, a summary blockquote, a short note, H2 link lists, and an Optional section at the end.

# Northwind Analytics

> Northwind Analytics builds reporting software for hospital finance teams.
> This file lists the pages an agent needs to answer questions about our
> product, pricing model, security and support.

Northwind is a software company. We do not offer medical advice. Prices on
the pricing page are list prices; contracts are quoted per organisation.

## Product

- [Product overview](https://www.example.com/product.md): what the platform does and who uses it
- [Integrations](https://www.example.com/integrations.md): supported data sources and export formats
- [Security and compliance](https://www.example.com/security.md): hosting, access control and audit logs

## Company

- [About us](https://www.example.com/about.md): team, history and office locations
- [Pricing](https://www.example.com/pricing.md): plans, what each includes, how billing works
- [Contact and support](https://www.example.com/contact.md): sales, support hours and response channels

## Optional

- [Blog](https://www.example.com/blog.md): articles on finance reporting and analytics
- [Release notes](https://www.example.com/changelog.md): product changes, newest first

Four things make this file useful rather than decorative:

• The H1 is the name of the site. The proposal calls this the only required section, so never leave it out.
• The blockquote says what the company does in plain words. An agent that reads nothing else still gets the right summary.
• Every link has a note after the colon saying what the page answers. A bare list of links forces the agent to guess.
• The Optional section holds secondary pages. The proposal says that, by convention, it is used for links an agent can skip when a shorter context is needed.

The links point to .md versions of pages because the proposal describes llms.txt as linking to detailed markdown files. If you have none, linking your normal pages still gives an agent a curated path.

How to turn this llms.txt example into your own file

Start from the blank template below and fill it in from the pages you already have.

# [Your company or site name]

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

[Optional short paragraph: anything an agent must not get wrong, such as
what you do not offer, or which page is authoritative on a topic.]

## [Main topic, e.g. Services]

- [Page name](https://www.yoursite.com/page.md): [what this page answers]
- [Page name](https://www.yoursite.com/page.md): [what this page answers]

## [Second topic, e.g. Company]

- [About](https://www.yoursite.com/about.md): [who you are]
- [Contact](https://www.yoursite.com/contact.md): [how to reach you]

## Optional

- [Page name](https://www.yoursite.com/page.md): [secondary material an agent can skip]

Then work through it in this order:

1. Write the H1 exactly as your organisation is known: the brand name people search for, not a slogan.
2. Write the blockquote as the answer to "what is this company and who is it for?" Keep it factual.
3. Pick the pages a customer or journalist would need: services or products, pricing model, about, contact, policies. Group them under two to four H2 headings.
4. Add a note to every link saying what the page answers, not what it is called.
5. Move blogs, archives and release notes into the Optional section.
6. Save it as plain UTF-8 text named llms.txt and upload it to the root of your domain, so it loads at /llms.txt.
7. Open the URL in a browser and confirm you see the raw markdown, not a 404 page or your homepage.

The proposal also allows the file at a subpath, such as /docs/llms.txt, covering the pages under that path. That suits a site with a large documentation section that deserves its own map. For a business website, one file at the root is the place to start.

Does Google use llms.txt for Google Search?

No. Google says plainly that Google Search does not use llms.txt, and that the file will neither help nor harm your rankings there.

Google's guide to optimising for generative AI features is direct: "You don't need to create new machine readable files, AI text files, markup, or Markdown to appear in Google Search (including its generative AI capabilities), as Google Search itself doesn't use them." It goes on: "It's completely fine if you decide to create and maintain LLMS.txt files (or other similar files) for other services or systems that use these files. Doing so will neither harm nor help your site's visibility or rankings in Google Search, as Google Search ignores them."

That note was added on purpose. Google's documentation updates log records an entry titled "Clarifying guidance on llms.txt files", which added a note to the AI optimisation guide clarifying Google Search's usage of llms.txt files.

So llms.txt is not a Google ranking lever. For AI Overviews and AI Mode, Google's guide says a page must be indexed and eligible to be shown in Google Search with a snippet. That is ordinary technical SEO, and it comes first.

Should you use an llms.txt generator or write it by hand?

Use a generator for a first draft if your platform offers one, then edit it by hand. The value of the file is the curation, and curation is a human judgement about which pages matter.

The llmstxt.org proposal notes that documentation platforms generate one automatically, which makes sense for a docs site where the structure already exists. For a business website, an llms.txt generator that walks your sitemap tends to produce exactly what the format is meant to avoid: a long, flat list with no notes. In our practice we check four things in any generated file before it goes live:

• Did it pick the right H1, or did it use a page title with a tagline attached?
• Is there a summary blockquote, and is it true?
• Are thank-you pages, tag archives, login pages or staging URLs in the list? Remove them.
• Does every link carry a note that says what the page answers?

How do you check an llms.txt file before and after publishing?

Check the format by eye against the proposal, then check that the live URL returns the file. There is no single official llms.txt validator, but the format is simple enough that a short checklist covers it.

The proposal says llms.txt is in a precise format that allows fixed processing methods, such as parsers and regex. That is good news: if your file follows the layout, a simple script can read it, and so can you. Our own llms.txt validator checklist:

• The file loads at /llms.txt with a 200 status, as plain text, not wrapped in your site template.
• The first line is a single H1 with the site or company name.
• A blockquote summary follows the H1.
• Sections use H2 headings, and each list item is a markdown link followed by a colon and a note.
• Every linked URL returns 200. A file that sends agents to 404 pages is worse than a short one.
• Secondary links sit under a heading named exactly Optional.
• Your firewall or CDN does not block the file for non-browser user agents.

Presence is now something tools look for. The llmstxt.org proposal says Chrome's Lighthouse audits sites for one as part of its agentic browsing checks. Our free AI visibility checker also checks whether llms.txt and a sitemap exist, alongside reading your robots.txt rules for 11 AI crawlers and requesting your homepage once with each crawler's user agent. That request is the checker's own, sent from Cloudflare, not the real crawler's, and it covers the homepage only. It can confirm the file is there; it cannot tell you how any AI service uses it.

What we have seen. On one SEO Autopilot engagement, a US healthcare analytics company on WordPress behind a firewall, the llms.txt score went from 0 to 85 between a baseline frozen on 15 July 2026 and a re-measure on 18-19 August 2026 across all 39 sitemap URLs. In our AI Visibility rubric, llms.txt carries 15% of the score. AI schema and structured data carry 25% and AI crawler access 20%, which is why we never treat llms.txt as the whole job. On that same site the firewall returned 403 to OpenAI's and Anthropic's search crawlers on every page, a problem no llms.txt file could fix. We wrote that up in our AI crawlers list, and the wider picture is in our guide to LLM SEO.

If you would rather not maintain these files yourself, SEO Autopilot covers llms.txt, crawler access, schema and content for one site at ₹20,000 a month (about US$230), with no setup fee and no minimum term.

Frequently Asked Questions