AI Engineering Playbook
Rapid Fire

Rapid Fire: LLM Fundamentals

Question → 3-line answer, flashcard style.

Prerequisites

LLM Fundamentals — work through the full section first. This deck strengthens recall of material you already understand; it will quietly fail you on material you don't.

How to use this deck

Cover the answer. Read only the question. Say your answer out loud, in full sentences, as if explaining it to someone who hasn't read the page. Then uncover and compare — not "did I know it?" but did I say it as cleanly as that?

Recognising an answer feels almost identical to being able to produce one, and the two come apart the moment you have to actually explain something. Anything you couldn't say fluently is a signal to reread its full page, one click away below.

Core mechanics

Core mechanics5 cards

Card 1 of 5

How does an LLM generate text?

Tokens and context

Tokens and context3 cards

Card 1 of 3

What is a token?

Sampling and determinism

Sampling and determinism3 cards

Card 1 of 3

What does temperature do?

Prompting and structured output

Prompting and structured output5 cards

Card 1 of 5

Zero-shot vs few-shot prompting?

APIs, streaming, caching

APIs, streaming, caching2 cards

Card 1 of 2

How does streaming work at the protocol level?

Hallucination

Hallucination2 cards

Card 1 of 2

Why do LLMs hallucinate?

Full treatment: LLM Fundamentals — the mechanisms behind every answer above.

On this page