Define prompt engineering and identify what it actually touches. · Zenaique

Attempt it

Your answer

Quick reference

TL;DR

Prompt engineering designs the input the model sees at inference time; the model's weights stay frozen across every call.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine a librarian who has read every book in the library and can answer any question. You cannot change what they have read; that knowledge is locked in. But you CAN change how you ask: 'in three sentences, like you would explain to a child, and please cite the books.' The librarian (the model weights) is unchanged. The way you asked (the prompt) is the only thing that moved between a useless answer and a perfect one. Prompt engineering is the practice of asking well.

Key concepts

Inference time Model weights (frozen)System prompt

Detailed answer & concept explanation

~4 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

3 min: the input vs weights split + what lives in the input + why iteration is cheap + when prompting hits a ceiling + two production examples.

Real-world examples

Real products, models, and research that use this idea.

Anthropic Workbench is a dedicated prompt engineering surface; you iterate on the system prompt and few-shot examples while Claude Opus 4.7 stays untouched.
Cursor and GitHub Copilot rewrite the prompt every keystroke (current file + neighboring files + your cursor context) against a fixed code model.
Perplexity composes retrieved web snippets plus instructions into a prompt for each query; the underlying LLM never trains on your session.
OpenAI's Structured Outputs and Anthropic's tool-use both expose schemas in the request; they constrain decoding without touching GPT-5.5 or Claude's parameters.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QIf the weights never change, why does adding a single example to the prompt sometimes flip the output completely?

Sign in or go Pro to see the approach for this follow-up.

QIs in-context learning the same as prompt engineering?

Sign in or go Pro to see the approach for this follow-up.

QHow does prompt caching change the cost equation of long system prompts?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Saying 'I prompt-engineered the model to be better at math' as if the model itself changed. The model is identical; only the input around it changed.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.