llms.txt Generator and Checker
Write an llms.txt file for your site, or test the one you already have.
Open tool →AEO · GEO · AI search visibility
Research and free tools for getting your pages quoted inside AI answers, not just listed beneath them.
Answer
Answer engines quote pages that state a clear answer early, back it with checkable sources, and let crawlers read the page without friction. Start with one direct sentence per question, add structured data, and publish an llms.txt file.
Four topics, each with sourced guides.
Browser-based, no sign-up. Three tools, each built to answer one question.
Write an llms.txt file for your site, or test the one you already have.
Open tool →Produce valid JSON-LD for articles, FAQs and organisations.
Open tool →Enter a URL and see which signals answer engines can and cannot read.
Open tool →Four pieces, in reading order.
A monthly report on how AI crawlers treat real websites.
| Crawler | Operator | Purpose |
|---|---|---|
| GPTBot | OpenAI | Training data |
| OAI-SearchBot | OpenAI | Search results |
| ClaudeBot | Anthropic | Training data |
| PerplexityBot | Perplexity | Search results |
| Google-Extended | Control token |
What we record
First report: 16 December. New reports follow monthly.
New articles publish every two days from 17 November. Until then, the free tools above work today.
AEO Services
We review how answer engines read your site, fix what blocks citation, and track the result over time.
Contact us →Short answer
Answer engine optimization (AEO) is the practice of making content easy for AI systems to find, quote and verify. That means a direct answer near the top of the page, clear structure and sources a reader can check.
Short answer
The terms overlap. Generative engine optimization (GEO) usually refers to engines that write an answer from several sources. AEO covers any system that returns an answer instead of a list of links.
Short answer
It is optional. llms.txt is a proposed convention that gives language models a short, curated map of your site. Support varies by engine, but the file costs little to publish and maintain.
Short answer
Only after weighing what you lose. Blocking a search crawler can remove your pages from that engine's answers. Several operators publish separate user agents for training and for search, so you can treat them differently in robots.txt.
Short answer
Partly. Server logs show which crawlers reach your pages, and a fixed set of prompts, sampled on a schedule, shows whether your domain is cited. Neither gives a complete picture, so track both over time.