How to › Shopify

llms.txt on Shopify: you already have one

This changed in 2026 and most advice about it has not caught up. Shopify now serves this path itself: the job is no longer to create the file but to look at what your store is already publishing and decide whether it says the right thing.

Can this platform serve the file at the exact path?

Yes — and it is already there, without you doing anything.

Shopify documents that a store includes a default file at /agents.md and that /llms.txt and /llms-full.txt point at that content by default, with a theme template to override it. Sources: Shopify changelog, 2026-05-28 and llms.txt.liquid template reference.

before you start

What you need first

Open https://yourstore.example/llms.txt and read what is there now. If the default already says something true and useful, you are done.
Theme code access, only if you decide to override it.

the steps

Look first, override only if you need to

Read what you already publish. Fetch /llms.txt and /agents.md on your own storefront. Shopify’s documented fallback order is your llms.txt.liquid template first, then agents.md.liquid, then its own default.
Decide whether it needs to be yours. The default is generated from your store. If the answers your buyers ask for — lead time, returns, what a size actually means — are not in it, they are not in it for an agent either.
Add the template. From your Shopify admin, Online Store › Themes, then the … menu › Edit code › Add a new template. Create it in the Templates folder as llms.txt.liquid and save.
Respect the documented constraints. Shopify documents that this template cannot be a JSON template and must be named llms.txt.liquid, that only the request and agents objects are available inside it — product and collection objects do not render — and that it is served at the bare primary domain, without a locale or market subfolder prefix.
Check it on the live storefront. Save into your published theme and fetch the path again. Shopify’s guidance for the analogous robots.txt template is that it is edited in the published theme and that changes are instant, while crawlers react in their own time.

what breaks it

The ways this goes wrong on Shopify

Trying to upload a file instead. Theme assets are documented as being served from a content-delivery domain under an /assets/ path, never from your root. Source: asset_url filter.
Trying to redirect to a page. Shopify documents that URL redirects work only from broken URLs — paths that return an error. /llms.txt now answers with a page, so a redirect from it will not take. Source: URL redirects. This is just as well: a redirect is not a pass anyway, because the agent-readiness audit errors out rather than following one.
Assuming a page at /pages/llms-txt counts. It is a different path. The audit fetches the root path and nothing else.
Editing an unpublished theme. Shopify’s equivalent guidance for robots.txt is explicit that the edit belongs in the published theme; their llms.txt page does not repeat that, so treat it as the safe assumption and verify on the live storefront.

verify it

Prove the file is really there

A file that looks published in an admin screen and returns anything other than a plain 200 at the exact path has not been published. Three checks, in order:

Open https://yourdomain/llms.txt in a private window. You want the raw text, not a styled page, and not a redirect to another path.
Confirm the first line is a level-one Markdown heading — # Your Business. Google’s agent-readiness audit fails a file with no H1 heading anywhere in it, and the llms.txt specification puts the H1 first, so first is the safe place for it.
Confirm at least one Markdown link is present, in [label](https://…) form. A file with no links in that form is reported as a failure by the same audit.

Then run it through the validator, which checks the same conditions and tells you which recommendation each one comes from. The package passes the llms.txt and page-structure checks of Google’s agent-readiness audit; the WebMCP audits cover interactive tools a fact package deliberately does not install. That is the claim we make about this file, and the only one. It does not improve your search position.

the honest part

This file is the compliance surface, not the mechanism

Publishing it is worth doing and takes ten minutes. What it will not do on its own is get you found: in a controlled test, agents given no pointer to the file opened it 0 times in 18 visits (Note 15), and in a census of nine real sites, seven published one and not one of them placed it where it gets read (Note 09).

What moved the numbers was putting the answers in the homepage itself, where a one-page reader lands: 78% of fact checks recovered against 30% in the control, with agents stopping after 1.1 pages on average (Note 41). Do this file because Google’s page-quality tooling checks for it and the package passes the llms.txt and page-structure checks of Google’s agent-readiness audit; the WebMCP audits cover interactive tools a fact package deliberately does not install. Do the fact block because it works.

Sources: MARKETING_NOTES_AGENT_VISIBILITY.md, Notes 09, 15, 41.

If somebody has told you this file moves your search position, read does llms.txt help SEO first — the answer is documented, and it is not the one they gave you.

other platforms

The same job elsewhere

free audit

See what AI sees on your site

The file is ten minutes of work. Whether your homepage answers a buyer's question is a different question, and it is the one we measure.

One model fetches your homepage and answers buyer questions from it. You get the recovery score and the specific answers it could not find. That is the whole free tier: it shows you the problem, and the fix package is not included.

Request the free audit → See a real before-and-after What the package costs