Generative AI: 10 key words to know

Conversations about AI are riddled with jargon. To follow the news without dropping out, about ten words are enough. Here they are, with no jargon to explain the jargon.

1. Model

A model is the trained “brain” that produces the answers. ChatGPT, Claude and Gemini each rely on a model. When a provider announces a new version, it usually means a new model, more capable than the last. To understand how this “brain” produces its answers, see what an LLM is, explained simply.

2. Generative AI

This is the family of AI that creates content (text, image, code) rather than merely classifying or predicting. An assistant that drafts an email is doing generation. It is what sets it apart from “classic” AI, which classifies and predicts.

3. Prompt

The prompt is your instruction: the question or command you give. The quality of the answer depends directly on the quality of the prompt. It is the most underrated lever.

4. Token

Models do not read words but “tokens,” fragments of text. A common word is often one token; a long word, several. It is the unit used to measure length and, often, price.

5. Context window

This is the amount of text a model can keep “in mind” at once. The larger it is, the more documents you can submit at once without it forgetting the start.

6. Hallucination

When a model states something false with confidence, we call it a hallucination. It is not a rare bug: it is a structural limit. Hence the rule: check what matters. The mechanism is detailed in why AI “hallucinates”.

7. Fine-tuning (specialisation)

Adapting an existing model to a specific use by re-training it on targeted data. Useful for a particular tone or domain, but rarely necessary for everyday use.

8. RAG (retrieval-augmented generation)

A technique that connects a model to a base of documents so it answers from your content rather than from its memory alone. It is what lets an assistant cite your own files.

9. Agent

An assistant that does not merely answer but chains actions together to reach a goal. You give it an objective, it handles the steps.

10. Multimodal

A multimodal model understands several formats: text, image, sometimes sound or video. You can show it a photo and ask a question about it.

The false friends not to confuse

Four pairs come up constantly and cause confusion. Telling them apart is enough to avoid most misunderstandings:

• Model ≠ agent: the model answers; the agent acts (it chains steps to reach a goal).
• Fine-tuning ≠ RAG: the first re-trains the model; the second connects it to your documents without changing it.
• Generative AI ≠ classic AI: one creates content, the other classifies or predicts from existing data.
• Token ≠ word: a token is a fragment; a long word counts as several. That is why text is billed in tokens, not words.

The cheat sheet at a glance

Keep this table at hand: each term in one line, and above all what it changes for you in practice.

Term	In one sentence	What it changes for you
Model	The trained “brain” that answers	A new version = a more capable model
Generative AI	An AI that creates content	It writes, draws, codes — not just analyses
Prompt	Your instruction	Better prompt = better answer
Token	A fragment of text	Used to measure length and price
Context window	What the model keeps in mind	Larger = more documents at once
Hallucination	A false but confident claim	Check what matters
Fine-tuning	Re-training on targeted data	Rarely needed day to day
RAG	Connecting the model to your documents	It cites your own files
Agent	An assistant that chains actions	It acts, not just answers
Multimodal	Understands text, image, sound…	Show it a photo, ask a question

Key takeaway

You do not need to be an engineer to follow AI. With these ten words, you can decode the essentials of the announcements. The rest are mostly commercial variations on these same ideas. To dig deeper into these notions, browse our deep dives.