Skip to content
Agentic Levels
Start hereLevelsTracksPromptsAbout
Get my levelGet my level

  • Start hereYour first useful task with AI.
  • Level quiz8 questions. No AI needed.
  • Fluency ScoreYour Level and a score, from your own AI.

  • LevelsThe 11 levels, in order.
  • LessonsShort lessons, filter by level.
  • TracksGuided paths by tool, role or goal.
  • Set up your AI tool
  • Starter packFree files that help AI remember.

  • PromptsReady prompts to copy and adapt.
  • ChatGPT vs Claude vs GeminiPick the right one for the job.
  • How-tos
  • ReferenceCommands for Claude Code, Codex, Antigravity.
  • ResourcesHand-picked reading and tools.

  • Your progress
  • Your next moveAn interview that picks your next skill.
  • Your next lessonsThe next lessons at your level.
  • Updates

  • Pricing
  • About
  • FAQ & Feedback
  • Work with us
  • How we handle your data
Sign inPreferences
AboutPricingHow-tosPromptsStarter packMy stackHow we handle your data

© 2026 Fuentes Studio

PrivacyTermsRefundsAccessibilityAI content policyCredits
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

←How-to guides
  1. Resources
  2. ›How-to guides

How to use Prompt Engineering Interactive Tutorial

Anthropic's official 9-chapter interactive prompt engineering curriculum: Jupyter notebooks with live playgrounds covering basics through tool use and RAG.

Levels 2 to 4On GitHub

Your prompts work sometimes but not consistently. You need a structured curriculum, not just tips. The tutorial covers 9 chapters from basic prompt structure through chain-of-thought, role assignment, avoiding hallucinations, and complex industry prompts. Each chapter has live Jupyter notebook playgrounds. An appendix covers advanced techniques including tool use, chaining, and RAG. Also available as a Google Sheets version with the Claude for Sheets extension.

Before you start

Anthropic API key

  1. 1Work through the chapters in order
  2. 2Apply each technique to your real work

Steps

01

Work through the chapters in order

Each chapter covers one prompting concept with live exercises. Don't skip chapters. They build on each other. Run the exercises, not just read them.

02

Apply each technique to your real work

After each chapter, take one prompt you use regularly and rewrite it using the technique you just learned. Compare outputs side by side.

Diagnose your worst prompt
Here's a prompt I use that gives inconsistent results: [YOUR_PROMPT]. Based on the Anthropic prompt engineering tutorial, what's wrong with it? Rewrite it applying: (1) clear role/task framing, (2) explicit output format, (3) examples if needed, (4) chain-of-thought where appropriate. Show me the before and after.
[YOUR_PROMPT]Your inconsistent prompt e.g. Summarize this document and extract action items

How do you know it worked?

  • You've completed at least 5 chapters with live exercises
  • You've rewritten 3+ real prompts using the techniques
  • Your rewritten prompts produce more consistent outputs

If something looks off

Do the exercises
Reading without doing the exercises won't stick. The interactive part is the point.
Practice in both contexts
These techniques apply to the API, not just Claude Code, practice in both environments.

See also

  • Claude Cookbooks
  • Claude Code memory (CLAUDE.md)

What you'll do, 2 steps

  1. 1Work through the chapters in order
  2. 2Apply each technique to your real work

Was this helpful?