Inference
The moment an AI actually answers, as opposed to when it was trained. Training happens once and costs a fortune; inference happens every time somebody asks, and is what you pay for per use.
Related terms
Explainability
How well a system can show why it reached a decision. It matters most where the decision affects somebody — a loan, a diagnosis, a job application — and “the model said so” is not an answer.
User-Agent
The name a browser or bot gives when it requests a page. It is how a server tells Googlebot from ChatGPT from a person, and how robots.txt rules are addressed to one and not another.
Answer Box
A boxed answer at the top of a results page, lifted from one page and credited to it. Winning one usually means having answered the question plainly and early rather than burying it.
Markdown
A plain-text way of writing formatted documents using symbols like # for a heading. AI systems read it easily because the structure is unambiguous, which is why some sites now offer it alongside HTML.
AI Search
Searching by asking a question in ordinary language and getting a written reply, rather than typing keywords and choosing from links. It changes what a website has to do: be readable and quotable by a machine, not just findable.
Chunking
Splitting a long page into smaller passages so an AI can retrieve just the relevant part. Pages with clear headings chunk cleanly; a single unbroken wall of text does not.