- The essential technical standards — robots.txt, llms.txt, Content Signals, Markdown negotiation, Link header and structured data — explained plainly.
- For each signal, what to check and how to fix it, with practical examples.
- The fundamentals to be accessible to AI agents: the starting point to become the source they cite.
Free tool
Is your site agent-ready?
Analyze your site and find out how ready it is for AI agents: robots.txt, llms.txt, Markdown negotiation, Link header, structured data.
Want to download our skill? Get the agent-ready fundamentals guide.
The check takes a few seconds. No data is stored.
Free skill
Download our skill: the fundamentals for being agent-ready
A ready-to-use package for your AI assistant — a skill to install on Claude or a file to use as instructions with ChatGPT, Gemini and others — with the fundamentals for making your site accessible and citable by AI agents.
What you'll find
Request the skill
AI agents are becoming a new gateway to information: more and more people no longer search on an engine, but ask an assistant like ChatGPT, Gemini or Perplexity. This tool checks the public technical signals that make a site accessible and citable by crawlers and generative assistants, and shows you, check by check, what to improve.
Frequently asked questions
A site is agent-ready when it is structured so that AI agents — the crawlers used by search engines and assistants such as ChatGPT, Gemini and Perplexity — can read its content, understand it and cite it reliably. In practice, this means exposing standard signals (robots.txt, llms.txt, structured data, Markdown versions of pages) that make the site understandable to machines, not just to people.
More and more people are looking for information by asking an AI assistant rather than browsing through search results. If a site is not readable by agents, it risks disappearing from this new layer of intermediation: it is not cited in answers and loses visibility and qualified traffic. Being agent-ready is the minimum requirement to stay in the conversation.
SEO (Search Engine Optimization) optimizes a site for traditional search engines and their link-based results. GEO (Generative Engine Optimization) optimizes it to be understood and cited by generative AI in their responses. SEO aims to rank you; GEO aims to get you cited as a source. They are complementary: one drives clicks, the other builds authority in AI responses.
llms.txt is a plain text file, placed at the root of a site (/llms.txt), that gives LLMs a concise, curated map of the most important content in Markdown format. It helps AI assistants navigate and retrieve the right information without having to interpret the entire HTML source of a page.
It is the ability of a site to return a Markdown version of a page when an agent requests it with the Accept: text/markdown header, while still serving HTML to browsers. Markdown is cleaner and easier for AI to parse, and it reduces content misreading errors.
Content Signals are directives that declare how a site's content may be used by AI: for search (search), as input in generative responses (ai-input) and for model training (ai-train). They allow you to express an explicit preference, rather than leaving it implicit.
Start with the public fundamentals: a valid robots.txt with rules for AI bots, a sitemap, a curated llms.txt, Content Signals, Markdown negotiation, Link headers and structured data. These are the basic technical requirements. The next step — becoming the source that AI chooses to cite — is a strategic content and reputation effort: that is exactly what Sequel does.
These suggestions are generated automatically. AI can make mistakes: use your professional judgment when applying them. The check is provided as is and Sequel assumes no liability for actions taken or results arising from these automated outputs.