Context Window
How much text a model can hold in mind at once, counted in tokens. Anything beyond it is forgotten, which is why very long conversations start to lose earlier details.
Related terms
OAI-SearchBot
The crawler OpenAI uses to answer live searches in ChatGPT, separate from GPTBot. Blocking one does not block the other, so a site can be absent from ChatGPT search while still being read for training.
AI Readiness
Whether a website can be reached, understood and quoted by AI assistants. It covers crawler access, structured data, clear headings, published contact details and speed — the unglamorous things that decide whether a model will name you.
Content Signals
An extension to robots.txt that states not just who may crawl, but what they may do with what they find: appear in search, be quoted in answers, be used as training data. It lets you permit citation while refusing training.
Entity SEO
Optimising to be recognised as a specific, real thing rather than for particular keywords. In practice it means consistent naming, structured data, and being mentioned in enough other places to be corroborated.
Passage Ranking
When a search engine surfaces one relevant passage from a long page rather than judging the page as a whole. Clear headings are what make a passage findable in isolation.
llms.txt
An emerging convention: a plain-text file at your site root that gives AI systems a clean map of what is on it. It saves an assistant from crawling around to work out what your site contains.