By Steve Merrill · August 3, 2026
The biggest llms.txt mistake Shopify stores make is treating the file like a proven ranking channel. It isn't one yet. llms.txt is a community proposal from Jeremy Howard at Answer.AI, published at llmstxt.org in 2024, and no major AI company has confirmed they use it. Set it up right anyway. It's cheap, it takes an hour, and the downside is close to zero. Here are the eight mistakes I see Shopify stores make.
1. Treating llms.txt like a confirmed ranking factor
This is where most people get burned. Google, OpenAI, and Anthropic have not said they read llms.txt, so anyone promising you AI traffic from it is guessing. The fix is simple. Treat llms.txt as a low-cost bet that helps models find your best pages if adoption grows, not as a lever you can pull for guaranteed results.
2. Confusing llms.txt with robots.txt
These two files do opposite jobs. Robots.txt tells crawlers what they can and can't access. llms.txt is a curated Markdown file that points models to the content you want them to read. Use robots.txt for access control. Use llms.txt to hand a model a clean map of your store.
3. Putting the file in the wrong location
The spec at llmstxt.org is clear. The file lives at the root of your domain, so yourstore.com/llms.txt. I've seen stores drop it in a blog folder or a theme asset directory where nothing can find it. On Shopify, host it as a static file at the root or route to it so the root URL resolves.
4. Writing it as HTML instead of Markdown
llms.txt is a Markdown file, not a web page. Some stores export a chunk of their sitemap or paste raw HTML and call it done. The format matters because Markdown is what the proposal specifies and what keeps the file readable. Start with an H1 for your store name, a short blockquote summary, then Markdown link lists under H2 sections.
5. Dumping every URL into the file
A 4,000-product catalog does not belong in llms.txt. The whole point is curation. Pick your highest-value pages: your best collections, your key product education, your policies, your top blog answers. That's it. A short, sharp file beats a full site dump every time. Aim for the 15 or 20 pages you'd hand a new employee on day one.
6. Letting it go stale
Stores set it up once and forget it. Then the linked pages 404 after a collection gets renamed or a product retires. A file full of dead links is worse than no file. Put a recurring reminder on your calendar to check the links every quarter, and update it whenever you restructure collections or run a big product refresh.
7. Skipping short descriptions on each link
A bare list of URLs gives a model no context. The llmstxt.org format lets you add a short note after each link, and that's where the value is. Write one plain sentence per link explaining what the page covers. "Return policy: 30-day returns, who pays shipping, how refunds work." That one line does the work.
8. Relying on llms.txt while blocking AI crawlers
Here's the contradiction I see most. A store publishes a beautiful llms.txt, then blocks GPTBot and other AI crawlers in robots.txt. If you block the bots, the file never gets read. Decide what you want. If you want AI visibility, check your robots.txt and your Shopify settings so you're not blocking the same crawlers you're trying to guide. Shopify explains its own crawler controls in its SEO documentation.
How We Chose This List
These eight come from setting up and auditing llms.txt files across live Shopify stores and cross-checking every claim against the published proposal at llmstxt.org. We flagged only the mistakes that either break the file or oversell what it does.
FAQ
Does Shopify generate an llms.txt file automatically?
No. Shopify does not create an llms.txt file for you. You add it as a static file or through an app or theme edit, and you maintain it yourself.
Do AI models actually read llms.txt yet?
There is no public confirmation from Google, OpenAI, or Anthropic that they use llms.txt for ranking or answers. It is a community proposal, so treat it as a low-cost bet, not a guaranteed channel.
Is llms.txt the same as robots.txt?
No. Robots.txt controls what crawlers may access. llms.txt is a curated Markdown guide pointing models to your best content. They serve different jobs.
Where does the llms.txt file go on a Shopify store?
It belongs at the root of your domain, so yourstore.com/llms.txt. A file buried in a subfolder will not be found.
Want your Shopify store set up right for AI shopping, from llms.txt to the rest of your AEO stack? See how we do it at WRKNG Digital's agentic commerce page.
