create an llms.txt file for your website (with examples) — a practical GEO how-to guide from GEOly AI (geoly.ai)

How to Create an llms.txt File for Your Website (With Examples)

Summary

The hands-on build: choose your best pages, write the Markdown, deploy llms.txt to your root on Next.js, WordPress or Shopify, then verify the URL returns plain text.

GAGEOly AIGEOly Editorial Team
2026/03/07
7 min read
Updated 2026/07/07

In classic SEO, `sitemap.xml` told search engines where your pages live. In Generative Engine Optimization, `llms.txt` tells AI models what your pages mean. It is a plain Markdown file at the root of your domain that hands ChatGPT, Claude, Perplexity, and other AI agents a curated, token-efficient summary of your most important content, so they can describe and cite you accurately instead of guessing.

This is the hands-on build guide. By the end you will have written a real `llms.txt`, deployed it on your platform, and confirmed it is live and correct. If you want the strategy behind the format, which pages to prioritize and why it moves AI visibility, read [how to create an llms.txt file for GEO](/blog/how-to-create-llms-txt-file-for-geo) alongside this. Here we focus on getting the file built and shipped.

Key takeaways

- `llms.txt` is a single Markdown file served at `https://yourdomain.com/llms.txt`. There is no XML, no special encoding, just headings, a summary, and curated links with one-line descriptions. - The structure is fixed enough to be easy: an H1 with your name, a blockquote summary, then H2 sections grouping your most important links, each link followed by a short description. - Curate ruthlessly. The value is in choosing your best pages and describing them, not in listing everything. A bloated file defeats the point. - Deployment differs by platform. On a static or code-based site you drop the file in the public root; on Shopify or WordPress you route the path or use a plugin or app. - Verify by loading the URL in a browser, confirming it returns plain text with a 200 status, and checking the links resolve.

Step 1: Choose the pages worth including

Before writing anything, list the pages an AI actually needs to understand and recommend you. Think about what a model would need to answer "what is [your brand] and should I use it." That usually means your homepage or About page, your core product or feature pages, pricing, key documentation, and a few cornerstone guides. Leave out login screens, cart pages, tag archives, and thin or duplicate pages. The whole point of `llms.txt` is curation, so a focused list of ten to twenty strong pages beats a dump of two hundred.

Step 2: Write the file in Markdown

Create a file named `llms.txt` in a plain text editor. The format is standard Markdown with a specific shape: one H1 for your project name, a blockquote one-liner summarizing what you do, then H2 sections that group links, each with a short description after a colon.

Here is a working example you can adapt:

``` # Acme Analytics

Acme Analytics is a GEO monitoring platform for DTC brands that tracks how AI models mention and cite them.

## Core pages - [About Acme](https://acme.com/about): Who we are, what we build, and who it is for. - [Pricing](https://acme.com/pricing): Current plans and what each tier includes. - [Product overview](https://acme.com/product): How the platform works, end to end.

## Documentation - [Quickstart](https://acme.com/docs/quickstart): Get set up in five minutes. - [API reference](https://acme.com/docs/api): Full endpoints and parameters.

## Key concepts - [What is AIGVR](https://acme.com/blog/aigvr): How the AI visibility score is calculated. - [Share of Model explained](https://acme.com/blog/share-of-model): How to read your share versus competitors. ```

Keep the summary blockquote factual and specific, since models often lift it verbatim. Write each link description as a clean, one-line statement of what the reader will find. Use absolute URLs, not relative paths, because the file may be read out of context.

Step 3: Deploy it to your domain root

The file has to answer at exactly `https://yourdomain.com/llms.txt`. How you get it there depends on your stack.

On a static site or one you deploy from code (Next.js, Astro, Hugo, plain HTML), drop `llms.txt` into your public or root output directory, for example `public/llms.txt`, and redeploy. On WordPress, upload the file to the site root via your host's file manager or SFTP, or use an SEO or `llms.txt` plugin that generates and serves it. On Shopify, you cannot write to the true root directly, so create a page or use an app that serves the content at the `/llms.txt` path, or add a redirect from that path to a hosted file; see [the Shopify GEO optimization guide](/blog/shopify-geo-optimization-guide-geoly) for platform-specific handling. Whatever the platform, the test is the same: the raw URL must return your Markdown as plain text.

Step 4: Keep it accurate and current

An `llms.txt` full of stale facts is worse than none, because you are feeding wrong information straight to the models. When your pricing changes, update the file. When you publish a cornerstone guide, add it. When a linked page moves, fix the URL. Treat it as a living document you review whenever your core pages change, and pair it with clean `robots.txt` rules so the crawlers you invite can actually reach the pages you list. See [how to configure robots.txt for AI crawlers](/blog/configure-robots-txt-ai) for that side.

How to verify

Load `https://yourdomain.com/llms.txt` in a browser. You should see your raw Markdown as plain text, not a rendered page or a 404. Confirm the response is a 200 with a text content type, then click through a few links to make sure they resolve to live pages. Finally, sanity-check the facts in your summary and descriptions against your actual site.

To confirm it is doing its job, watch whether AI answers about your brand get more accurate over time. GEOly, a GEO data platform, helps here: its 29-point GEO audit checks AI-readiness signals including whether crawlers can reach your key pages, and its monitoring tracks how ChatGPT, Gemini, Perplexity, Copilot, and Grok describe and cite you, so you can see the effect of the file rather than assume it. Free trial at `app.geoly.ai`; more at [what is GEOly AI](/blog/what-is-geoly-ai) and the [GEOly AI author page](/blog/author/geoly-ai).

Common mistakes

- Listing every page instead of curating. The file's value is selection, and a bloated one buries your best pages. - Using relative URLs. The file may be read without your domain as context, so always use absolute links. - Letting facts go stale, especially pricing and product claims, which then get quoted back at you. - Assuming deployment worked without loading the URL. A file sitting in the wrong directory helps no one. - Inviting crawlers in `llms.txt` while blocking them in `robots.txt`. The two files have to agree.

FAQ

Is llms.txt an official standard AI models must follow?

It is a widely adopted community convention, not a mandate every model is guaranteed to honor. Adoption is growing because it is cheap to create and genuinely useful, and it costs you nothing to provide a clean, curated map even for crawlers that read it opportunistically.

What is the difference between llms.txt and robots.txt?

`robots.txt` controls access, telling crawlers what they may or may not fetch. `llms.txt` provides understanding, pointing models at your best content with context. One is a gate, the other is a guide, and you want both configured consistently.

How is this guide different from your other llms.txt article?

This one is the hands-on build: writing the file, deploying it per platform, and verifying it is live. The companion piece, [how to create an llms.txt file for GEO](/blog/how-to-create-llms-txt-file-for-geo), covers the strategy of what to include and why it affects AI visibility. Read them together.

Do I need a separate llms-full.txt file?

Some sites add an `llms-full.txt` with expanded content for models that can ingest more. Start with a tight `llms.txt` first, since a well-curated core file delivers most of the value. Add the fuller version later if your documentation is large enough to justify it.

Will llms.txt guarantee AI models cite my brand?

No. It makes your content easier to understand and reduces guesswork, but citations still depend on entity clarity, crawler access, and trusted third-party sources. Treat `llms.txt` as one high-ROI layer in a broader GEO strategy, not a silver bullet.

See your brand in AI search

GEOly tracks how ChatGPT, Gemini and Google AI mention, cite and recommend your brand — and helps you win the AI shelf.

Start Free Trial

3-day free trial · No card required

Add GEOly as a preferred source on Google

Trusted by leading consumer brands

Anker SOLIX
eufy
soundcore
PLAUD
xTool
Ulike
Jackery
Roborock
Dreame
EcoFlow
Insta360
TCL
Beatbot
CASETiFY
Creality
Shokz
Segway
realme

12,000+ brands track & win AI search with GEOly

From Anker SOLIX to xTool — the brands above already see how ChatGPT, Gemini and Google AI mention, cite and recommend them. Your brand is being talked about in AI right now. See it.

See Your Brand in AI — Free

3-day free trial · No card required