AI Engineering Playbook
Rapid Fire

Rapid Fire: Production

Question → 3-line answer, flashcard style.

Prerequisites

Production — 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.

Latency and cost

Latency and cost6 cards

Card 1 of 6

TTFT vs total latency — what drives each?

Reliability

Reliability6 cards

Card 1 of 6

Which errors do you retry, and how?

Testing and rollout

Testing and rollout2 cards

Card 1 of 2

What do prompt regression tests in CI look like?

Security

Security5 cards

Card 1 of 5

Direct vs indirect prompt injection?

Full treatment: Production — the mechanisms behind every answer above.

Rapid Fire: Model Landscape

On this page