Stall library · Discover
No llms.txt to orient AI agents
llms.txt is a plain text file at the root of a site listing its important pages with a short description of each, intended to give an assistant a fast orientation without crawling. It is the lowest severity item Ottom reports, and deliberately so: the evidence that it changes outcomes is weak compared with a product feed or structured data, and a store with an hour to spend should not spend it here.
Why the agent stops
The mechanism llms.txt offers is orientation rather than access. An agent that reads it learns which pages you consider important and what they contain, which can save a crawl. Nothing about the file grants access, describes a product, or makes a checkout completable.
It costs very little to publish, so the honest position is that it is worth doing and not worth prioritising. If the choice is between llms.txt and a readable shipping policy, publish the shipping policy.
How often we see this
Not stated here. A frequency means nothing without the cohort it was counted over, and this page is about one stall rather than one category. Where a category has enough stores measured at every stage, the share of them showing this stall is published on its benchmark page, with the methodology beside it.
See it for yourself
- Open https://yourstore.com/llms.txt and check it returns plain text rather than a 404.
- Confirm it lists your key pages: the catalogue, the main collections, shipping, returns and contact.
- Check each URL in it resolves. A file advertising pages that 404 is worse than no file.
What to change
- Publish /llms.txt with a one line site description followed by your key URLs, each with a short description.
- Regenerate it when you publish, so it never advertises a page that has moved.
- Do not put anything in it you would not put on a public page. It is a public file.
- Treat it as a finishing touch after the feed, the structured data and the checkout path are right.
What Ottom looks at
Ottom checks for /llms.txt during the discover stage and records whether it was found. It is reported at low severity, which is the honest weight for it.
Questions
Do assistants actually read llms.txt?
Support is uneven and publicly contested, and we are not going to claim otherwise to sell you a fix. Ottom publishes its own llms.txt because it costs almost nothing, and reports a missing one at low severity for the same reason.
What should a store put in its llms.txt?
Your catalogue entry points, your main collections, and your shipping, returns and contact pages. Those are the pages an agent needs to answer a shopper about you, and they are often the hardest ones to find by following links.