AI glossary in plain English
An AI glossary for people who use the tools, not build them. Eight terms that turn up in every article, one page each, with an example and the mistake most people make.
Terms
The prompt meaning in AI is simple: a prompt is the instruction you give a model so it does something. It is the text the model reads to work out what you want, and it is a brief, not a magic word.
Prompt engineering is the practice of writing the instruction you give an AI deliberately instead of guessing. It is not a collection of magic phrases: it is the work of giving a model enough context, one clear task and a standard for what a good answer looks like.
So what is a token in AI? It is the piece of text a model counts with: not a letter and not exactly a word, but something in between. A common chunk of characters the model turns into numbers before it can work with them.
The LLM meaning is large language model: a program trained on an enormous amount of text to predict what text comes next. ChatGPT, Claude and Gemini are all built on one.
The GPT meaning is generative pre-trained transformer. Three words, three pieces of information: it produces text, it was trained in advance, and it is built on the architecture called a transformer.
The chatbot meaning is straightforward: a program you work with by having a written conversation. The word covers two very different things, depending on whether you mean the 2015 kind or today's kind.
The context window is how much text a model can keep in view at once: your questions, whatever you pasted and the model's own answers, all together. It is measured in tokens, and when it fills up the start of the conversation drops out.
The machine learning meaning is this: instead of writing rules into a program, you give it examples and it works out the rule itself. Most of today's AI tools are built this way.
Longer reads
These three got a full article, because a glossary entry would be too short for them.
Common questions
Who is this AI glossary for?
People who use AI at work and keep hitting words that nobody defines: prompt, token, context window, LLM. Every entry gives the plain definition first, then what it means for your own work.
Where can I practise this, not just read it?
In the app every term sits inside a lesson, with a quiz and a glossary you build yourself while reading. The first two tracks are free.