AI Agent — Glossary — Angkor Design

Microdata

An older way of marking up facts, written as attributes on the HTML itself rather than in a separate block. Still understood, but JSON-LD is now the safer choice.

AI & Answer Engines

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.

AI & Answer Engines

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.

AI & Answer Engines

Reinforcement Learning

Training by trial, error and reward rather than by examples. It is how models are tuned to be helpful and to refuse things they should refuse.

AI & Answer Engines

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.

AI & Answer Engines

Content Provenance

A record of where a piece of content came from and how it was made, sometimes attached to the file itself. Emerging as a way to tell an original photograph from a generated one.

Related terms

Microdata

Context Window

Inference

Reinforcement Learning

Chunking

Content Provenance