If you've just finished Module 0, this page is sixty seconds of revision — skim it and crack on. If you came in this door fresh, here's the one mental model everything else hangs off.
When you type "Write me an email to a customer who's late paying" and the AI hands back something sensible, it isn't thinking like a person and it isn't looking up the one correct answer. During training it read an enormous pile of text and learned the patterns: after these words, these words tend to follow. Your reply gets built one piece at a time, each piece picked to fit the pattern. That's it — pattern matching for language, scaled up until it feels like magic. Everything else — "reasoning", Deep Research, thinking modes — is layers on top of that one trick.
Why that matters for you
- It's brilliant at language-shaped tasks — drafts, summaries, rewrites, explanations, ideas, code-shaped text.
- It can be confidently wrong — it predicts plausible text, not verified truth. Always sanity-check anything that matters (money, health, law, safety).
- Your prompt steers the pattern — vague in, vague out; specific in, useful out. (You'll practise exactly this later in the lesson.)
- The mode picker steers cost and depth — "fast" vs "thinking" is the same brand charging you different amounts of compute for harder work. More on that shortly.
A prompt isn't a Google search
| You might think… | What's closer to the truth |
|---|---|
| It looks up the right answer | It generates text that looks like an answer |
| Same question → same answer every time | A bit of built-in randomness can change the wording |
| It "knows" your business | It only "knows" what's in the chat (until you wire in docs or tools later) |
| One subscription = one capability | In 2026 you're buying a menu — chat, research, images, agents — each with its own limits |
Continue — next we map that menu across the big platforms.