Build Your Prompt Book: A Step-by-Step Workshop
By Dorian Laurenceau
📅 Last reviewed: April 24, 2026. Updated with April 2026 findings and community feedback.
The best prompt engineers do not write prompts from scratch every time, they maintain a prompt book: a curated library of tested, versioned templates. By the end of this workshop, you will have built your first prompt book with 5 production-ready templates.
Why You Need a Prompt Book
Every time you write a prompt from scratch, you pay a creativity tax. You reinvent structure, forget constraints, and get inconsistent results. A prompt book eliminates this waste.
Think of it like code libraries. No developer writes sorting algorithms from scratch, they import a library. Your prompt book is the same: tested, reusable, version-controlled.
Workshop: Build 5 Templates in 30 Minutes
Building Your First Prompt Book
5 templates, each following the R.C.T.F framework
Template 1, Email Writer
Role: You are a professional business writer.
Context: [SITUATION]. Recipient: [AUDIENCE]. Tone: [TONE].
Task: Write an email that [GOAL]. Max [N] sentences.
Format: Subject line + body. No emojis. Sign as [NAME].💡 Variables in brackets make the template reusable across situations.
The Iterative Refinement Process
Good templates are not written, they are refined. Here is the process.
Before vs. After: Email Template Evolution
← Scroll horizontally →
What is the main benefit of version-controlling your prompts?
Organizing Your Prompt Book
Common Template Anti-Patterns
Test Your Understanding
Prompt Book Workshop Check
0 / 5 answered
Q1.What is the main advantage of a prompt book over ad-hoc prompting?
5 questions remaining
Where to Go From Here
You now have a 5-template prompt book and the skills to refine and expand it. In the next module, you will learn to get structured outputs from AI, JSON, tables, and schemas, the backbone of production AI workflows.
Continue to Structured AI Outputs to master JSON extraction and data formatting.
Module 1 — LLM Anatomy & Prompt Structure
Understand how LLMs work and construct clear, reusable prompts.
Dorian Laurenceau
Full-Stack Developer & Learning DesignerFull-stack web developer and learning designer. I spent 4 years as a freelance full-stack developer and 4 years teaching React, JavaScript, HTML/CSS and WordPress to adult learners. Today I design learning paths in web development and AI, grounded in learning science. I founded learn-prompting.fr to make AI practical and accessible, and built the Bluff app to gamify political transparency.
One practical AI workflow in your inbox
Methods, resources and new exercises. Free, unsubscribe at any time.
→Related Articles
FAQ
What will I learn in this Prompt Engineering guide?+
Create your personal prompt library with templates for every situation. Learn iterative refinement, A/B testing, and prompt version control in this hands-on workshop.