Artificial Intelligence

Talk about AI for long enough and you start to feel that everyone else was handed a glossary you somehow missed. Inference, tokens, context windows, agents: the words arrive faster than the explanations, and most explanations are written either for engineers or for a sales meeting.

This section is for the person in between — including teachers who use AI to plan lessons, create materials, assess language, or simply make sense of what their students are talking about. Each explainer takes one term, defines it in plain English, shows how it works with a diagram, and then does something technical documentation rarely bothers to do: it explains the language of the word itself. Where it comes from, how its meaning has changed, what words commonly occur with it, how it is pronounced, and how to use it naturally in a sentence without sounding as if you swallowed a press release.

That distinction matters because AI vocabulary is unusually slippery. Model can mean a mathematical system, a trained set of parameters, or a product offered by a company. Training and inference sound related but describe fundamentally different processes. Agent can refer to systems with radically different capabilities. Even familiar words such as context, prompt, and reasoning can acquire more specific meanings when they enter AI.

The explainers are therefore designed to be read in an order. Start with the words that describe the basic stages of how AI systems work, then move on to the concepts built on top of them.

Every page carries a date, revision history, and sources. AI changes quickly, and an explanation that is accurate today may need updating sooner than a conventional dictionary entry. When the terminology or technology changes, the page changes with it — and the revision history shows what changed.