# Prompt Engineering
Stop Guessing or Fall Behind

- Price: $12.99 (Kindle ebook)
- Level: Beginner
- Pages: 241
- Best for: Anyone shipping prompts they cannot prove still work
- You finish with: A golden set, a calibrated judge, and a CI gate that blocks a bad prompt change before a user sees it
- Series: Agentic Coding: Ship Bigger Projects with AI, book 3 of 3
- Buy on Amazon: https://amzn.to/45AyUXH
- Web page: https://youcanbuildthings.com/books/prompt-engineering

## What you get

You change a prompt to fix one case and you do not know what else you just broke. In 30 days you build the system that tests, scores, and versions every prompt you ship: a versioned spec, a 20-case golden set, a calibrated judge, a one-command eval, and a CI gate that blocks a bad change before it reaches a user.

You cannot prove a prompt works by reading about golden sets. You cannot catch a silent regression with a bag of tips. Everyone else describes the system. Nobody makes you run it.

Every template ships in a free companion repo at github.com/regardo911/prompt-system-kit: the spec, the golden set, the judge, the eval config, the CI gate, and the report, plus an emptied copy of all fourteen files to point at your own task.

## Chapters

1. Prompt Engineering Isn't Dead. It Grew Up.: The skill did not die. It turned into an engineering discipline with numbers attached.
2. A Prompt Is Not a Sentence. It's a Spec.: Turn a loose sentence you already use into a versioned, tested artifact.
3. If You Can't Say What "Good" Means, You Can't Test It: Write the standard down before you write another prompt.
4. Your First Golden Set: Twenty cases that catch a regression before your users do.
5. The Machine That Scores Your Prompt: A calibrated LLM-as-judge that grades any prompt against your own standard.
6. Turn the Score Into a Harness You Run on Every Change: One command scores every prompt version side by side.
7. From a Failed Score to a Fix That Holds: Read the failure, make the change, prove the fix did not break something else.
8. Never Get the Monday Support Ticket Again: A CI regression gate that blocks a bad prompt change before it ships.
9. The System That Survives the Next Model: A cross-model scorecard that turns a model release into a five-minute check, not a rewrite.
10. Get Paid for the Thing Nobody Else Can Prove: A client-ready eval report worth $2,000 or more. The billable proof a prompt pack cannot compete with.
11. Where Prompting Ends and Context Engineering Begins: The line between a prompt problem and a window problem, and how to tell which one you have.
12. Your Next 30 Days: The full plan: a versioned library, an eval on every output, a scorecard you keep current.