Skip to main content
eCommerce

llms.txt for UK Shops: What It Does, What It Doesn't and How to Add One

28 October 2026 AAM Services
Flat illustration of a small shop front, a signpost with blank arrows and a closed garden gate on a solid green background, with a small robot looking up at the signpost

If you run an eCommerce shop, someone has probably told you that you need an llms.txt file "for AI". Some SEO tools now flag it as missing, and plugins will create one in a click.

So is it worth adding one, and what does it actually do? We looked at the spec, what Google, OpenAI, Anthropic and Perplexity have published, and how Shopify, WooCommerce and OpenCart handle the file today.

The short answer: llms.txt is a plain Markdown file that gives AI tools a short guide to your site and its most useful pages. No major search or AI engine has confirmed that it uses the file to rank or cite sites, and Google Search says it ignores it. It is cheap to add and harmless, so add a tidy one if you like, but don't expect it to change your traffic.

What an llms.txt file is

llms.txt is a proposal, first published in September 2024 by Jeremy Howard and now on version 2 at llmstxt.org. It is not an official web standard. The idea is simple: AI models struggle with pages full of menus, scripts and adverts, so a site can offer a short, clean summary at /llms.txt.

The format is ordinary Markdown with a light structure:

  • One H1 with the name of the site or project. This is the only required part.
  • A short summary in a blockquote.
  • Optional notes in plain paragraphs.
  • Sections with H2 headings, each holding a list of links with a short note about each one.
  • An optional section literally called "Optional" for links an AI tool can skip if it is short on space.

How llms.txt differs from robots.txt

The names look alike, but the jobs are different.

robots.txt controls access

robots.txt tells crawlers what they may and may not fetch. Google, OpenAI, Anthropic and Perplexity all document their crawlers as following it. If you want to allow search bots but block bots that collect training data, robots.txt is where you do it. Our free Robots.txt Tester shows which of the main AI and search bots your current file allows or blocks, and we explained the thinking behind it in our post introducing the tester.

llms.txt offers a reading list

llms.txt does not allow or block anything. The spec describes it as information used "on demand, when an agent needs information about a topic while assisting a user". Think of it as a signpost rather than a gate. A bot that ignores llms.txt can still crawl your whole site, and a bot you block in robots.txt is still blocked even if your llms.txt lists every page.

If you only have time for one of the two, get robots.txt right first.

What Google and the AI companies actually say

This is the part most "you need llms.txt" articles skip.

Google Search ignores it

Google's own guide to optimising for generative AI features in Search is clear. It says you don't need to create new machine readable files or AI text files to appear in Google Search, "as Google Search itself doesn't use them". It adds that creating llms.txt "will neither harm nor help your site's visibility or rankings in Google Search, as Google Search ignores them."

That matches earlier comments. In April 2025 John Mueller compared llms.txt to the old keywords meta tag, noting that none of the AI services had said they used it. In July 2025 Gary Illyes said Google doesn't support it and isn't planning to.

Chrome's Lighthouse checks for it

There is one twist. Chrome's Lighthouse has an experimental Agentic Browsing category that includes an llms.txt audit. It calls the file "an emerging convention" and marks a missing file as not applicable, because providing one "is optional at the moment". It does fail a file that returns a server error. That is a readiness check for browser agents, not a ranking signal.

OpenAI, Anthropic and Perplexity point to robots.txt

The crawler documentation from OpenAI, Anthropic and Perplexity explains how to control their bots with robots.txt. None of those pages says it reads other sites' llms.txt files. The same companies do publish llms.txt files for their own developer documentation, which is where the format is most useful today: helping coding assistants read technical docs.

Some site owners have seen AI bots fetch the file in their logs. Fetching it is not the same as using it to choose which shop to recommend.

Should a UK shop add one?

For most shops, it is a "nice to have" that takes under an hour.

Reasons to add one

  • It costs very little and Google has said it won't harm you.
  • It gives any tool that does read it a clean list of your key pages, such as delivery, returns and your main categories.
  • It may help an AI assistant that is already on your site answer a customer's question faster.

Reasons not to expect much

  • It will not improve your Google rankings or get you into AI Overviews.
  • AI answers about products still depend on what crawlers can read on your real pages: clear product content, structured data, accurate stock and prices, and a sensible robots.txt. That groundwork is covered in our agentic commerce guide.
  • An out of date llms.txt pointing at old pages does more harm to your credibility than having none.

How to add llms.txt on Shopify, WooCommerce and OpenCart

Each platform handles the file differently, and two of them have a catch.

Shopify serves one for you already

Shopify now serves /llms.txt on every store by default. It mirrors Shopify's /agents.md file, which lists the store's name, policies and the endpoints AI shopping agents use. You can see yours by visiting your domain followed by /llms.txt.

You still can't upload a file to the root of a Shopify store. To replace the default, Shopify's llms.txt.liquid documentation explains the method:

  1. Go to Online Store, then Themes, then Edit code on your live theme.
  2. Under Templates, add a new file called llms.txt.liquid.
  3. Write your Markdown in that file and save.

Two things to know. First, the template only sees a small set of store details, so Liquid objects such as shop or collections come out blank. Plain Markdown with full URLs is safest. Second, older guides suggest a URL redirect from /llms.txt to an uploaded file. Merchants report that this stopped working once Shopify began serving the file itself, so use the template instead.

WooCommerce and WordPress with Yoast

If your WooCommerce shop uses Yoast SEO, the plugin can create the file for you. In WordPress, go to Yoast SEO, then Settings, then Site features, and switch on llms.txt under AI tools, then save. Yoast's help page covers the options, including choosing pages by hand. It is not available on multisite installs.

According to Yoast's specification, it writes a real file to your site root and refreshes it weekly, using recently updated pages and your top categories and tags. That automatic list may not be the pages you care about most, so we would use the manual selection and include delivery, returns and your main shop categories.

If you would rather write your own, switch the Yoast feature off and upload llms.txt to the same folder as wp-config.php. Yoast won't overwrite a file that is already there. Standard WordPress rewrite rules serve real files directly, so it will work without extra setup on most Apache hosts.

OpenCart needs one line changed

On OpenCart you upload llms.txt by FTP or your host's file manager to the store root, the same folder as index.php and robots.txt.

Here is the catch. The .htaccess file that ships with OpenCart 3 and 4, which you need for SEO friendly URLs, blocks every .txt file except robots.txt. The stock rule on GitHub looks like this:

<FilesMatch "(?i)((\.tpl|\.twig|\.ini|\.log|(?<!robots)\.txt))">
 Require all denied
</FilesMatch>

So your new file will return a 403 Forbidden error. To allow it while keeping other text files blocked, add a second exception to that line:

<FilesMatch "(?i)((\.tpl|\.twig|\.ini|\.log|(?<!robots)(?<!llms)\.txt))">
 Require all denied
</FilesMatch>

Back up .htaccess before editing it. On Nginx hosting the file is ignored, and your host's server settings decide what is served.

A short example llms.txt for a shop

Here is a simple example for an imaginary UK tea shop. Swap in your own pages and keep it short.

# Example Tea Co
> Example Tea Co is a UK online shop selling loose leaf tea, tea bags and brewing kit, with delivery across the UK.
We ship from the UK. Prices on the site are shown in pounds sterling.
## Shop
- [Loose leaf tea](https://www.example.co.uk/collections/loose-leaf-tea): Black, green, white and herbal teas
- [Tea bags](https://www.example.co.uk/collections/tea-bags): Everyday and speciality blends
- [Brewing kit](https://www.example.co.uk/collections/brewing-kit): Teapots, infusers and cups
## Customer help
- [Delivery](https://www.example.co.uk/pages/delivery): UK delivery options and timescales
- [Returns](https://www.example.co.uk/pages/returns): How to return an order
- [Contact](https://www.example.co.uk/pages/contact): How to get in touch
## Optional
- [Brewing guides](https://www.example.co.uk/blogs/guides): How to brew each type of tea

Link to pages that rarely change so the file doesn't go stale, and leave out personal phone numbers or email addresses.

How to check your llms.txt works

Once the file is live, run through a few quick checks:

  1. Open https://yourdomain.co.uk/llms.txt in a private browser window. You should see your Markdown, not a 403, a 404 or your home page.
  2. Paste the file into our llms.txt Checker and Generator to catch a missing H1, malformed links or duplicate URLs, then check that every link opens the right page.
  3. Run Lighthouse in Chrome DevTools with the Agentic Browsing category ticked to see the llms.txt audit.
  4. Check robots.txt with our Robots.txt Tester so the pages you list aren't blocked for the bots you want.
  5. Review the file whenever you change your main categories or policies.

llms.txt FAQs

Does llms.txt help my shop rank in Google?

No. Google says Search ignores llms.txt files, and that adding one will neither harm nor help your rankings, including in AI Overviews and AI Mode.

Do ChatGPT, Claude or Perplexity use llms.txt?

None of them has confirmed using other sites' llms.txt files to choose sources or answers. Their crawler documentation points to robots.txt for controlling access.

Is llms.txt the same as robots.txt?

No. robots.txt tells bots what they may crawl. llms.txt is a reading list of useful pages and does not allow or block anything.

Can llms.txt stop AI bots using my content?

No. To allow or block AI crawlers you need robots.txt rules for each bot's user agent, and some bots also need blocking at server or firewall level.

Where does the llms.txt file go?

At the root of your domain, so it opens at yourdomain.co.uk/llms.txt. On Shopify that means a llms.txt.liquid theme template, as you can't upload files to the root.

Do I need an llms.txt generator?

Not really. A shop's file is short enough to write by hand, and doing it yourself means you choose the pages that matter. For a head start, our free generator builds a starter file in your browser, and our launch post explains how it works.

Need a hand with llms.txt or AI search?

If you'd like us to set up llms.txt on your shop, fix an OpenCart .htaccess, or check what AI and search bots can see on your site, we can help. We work on Shopify, WooCommerce and OpenCart stores, and our SEO and AI search work focuses on the technical foundations that make the difference. Get a quote and tell us what you're working on.

Ready to Start Your Project?

Have questions about building your eCommerce store or custom web application? Let's talk.