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
Speech Recognition
Turning spoken words into text. It underpins voice search, dictation and call transcription, and it now handles accents and background noise far better than it used to.
AI Agent
An AI that does things rather than only answering — browsing a site, filling a form, completing a booking. It is why websites are starting to be judged on whether a machine can use them, not only read them.
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.
Organization Schema
Structured data describing the business itself: name, logo, address, contact details, social profiles. The single most useful markup for being recognised, and the one most small sites are missing.
Fine-Tuning
Taking a general model and training it further on your own examples so it follows your tone or handles your particular task. Useful when prompting alone keeps producing nearly-right answers.
Synthetic Content
Text, images or video produced by AI. Not penalised for being synthetic, but it is judged by the same standard as anything else — and thin AI-written pages fail that standard easily.