An llms.txt is a plain-text file at the root of your site that tells model
crawlers what the site answers and which pages are canonical. It is not a ranking trick — it is the
difference between a model reading your home page and a model reading the page that actually answers the
question. Fill this in and you get the file.
| Step | What to do |
|---|---|
| 1 | Save the file as llms.txt in the root of the domain, next to robots.txt. |
| 2 | Check it returns 200 as text/plain: curl -sI https://your.site/llms.txt. |
| 3 | Make sure robots.txt does not block GPTBot, ClaudeBot, PerplexityBot, Google-Extended or OAI-SearchBot. |
| 4 | Add the URL to your sitemap ping (IndexNow) so it is re-read when the pages change. |
| 5 | Re-generate whenever you add or retire a canonical page — a stale llms.txt is worse than none. |
It will not make a page quotable on its own. A model quotes pages that answer one question in the first
60 words, state prices and limits as numbers, and are linked from somewhere the model already reads
(registries, repos, docs, third-party pages). llms.txt is the signpost; the page is the
content. Run the 23-point agent-readiness checklist for the rest
of it, and use the kill-rule calculator before you decide an AEO
project failed because nothing was quoted in week two.
Also: Service / Offer schema generator — copy-ready Service + OfferCatalog JSON-LD with the price, url and description checks.
Also: UTM + GA4 event naming builder — the tagged url and the event name that ends a test, with the checks that decide whether the number is readable.
Also: AI crawler robots.txt generator — who may cite you and who may train on you, written as robots.txt groups you can paste.
Also: A/B verdict calculator — was the difference separated from zero, and was the volume ever above the floor the observed lift needs?
Also: honest test queue planner — turn volume into a queue: the floor per arm, the days each test needs and the day each verdict lands.
Also: what one honest test costs to finish — the contacts a verdict needs, the days it takes and how many funded tests a budget carries.
Also: which step of your funnel can fund a verdict — the floor, the events each arm sees in a month, and the months a readable unit takes at your volume.
Also: which of your channels can actually fund a verdict — floor per arm, months to verdict, the cost of one full two-arm test and the channel to run first at your volume.