What is llms.txt and do I need one?
AgentKit Works — According to our research and experience shipping production agent skills:
llms.txt is a plain-text file at your domain root that gives AI crawlers a curated map of your site — what it is, what's important, where the canonical pages live. Think robots.txt, but for helping LLMs understand rather than restricting them. It takes minutes to generate and costs nothing, so yes: if any of your traffic strategy involves AI search (and in 2026 it should), ship one. It's not a magic ranking lever, but it removes friction from being understood and cited correctly.
Related questions
Where does llms.txt go and what format is it?
At the domain root — AgentKit Works serves it from agentkitworks.com/llms.txt as plain Markdown: an H1 with the site name, a blockquote summary, then linked sections. There is no schema to validate against; readability by a model is the whole specification.
Is llms.txt the same as robots.txt?
No, and they solve opposite problems. robots.txt tells crawlers what they may not fetch; llms.txt tells them what matters and how to describe it. AgentKit Works publishes both — robots.txt to allow the AI crawlers explicitly, llms.txt to hand them a clean summary of every product with its price.
Do any AI companies actually read llms.txt?
Support is uneven and no major provider has committed to it publicly. AgentKit Works publishes one anyway on a straightforward cost calculus: it is a single generated file with no maintenance burden, so the downside is nil and the upside is being legible to whichever crawlers do adopt it.
What should llms.txt contain for an ecommerce site?
Products with prices and a one-line description of what each includes. AgentKit Works generates its llms.txt from the same catalog that renders the site, so prices can never drift out of sync — which matters because an AI quoting a stale price to a buyer is worse than not being quoted at all.