GitHub - anthropics/prompt-eng-interactive-tutorial: Anthropic's Interactive Prompt Engineering Tutorial
Short summary
This is Anthropic's hands-on course teaching you how to write better prompts for Claude, with 9 chapters covering prompt structure, common failure modes, and practical techniques. You work through exercises and test examples in a live playground to see how prompt changes affect Claude's responses.
- The course teaches 80/20 techniques to fix common prompt failures and covers Claude's specific strengths and weaknesses
- It's structured as 9 chapters plus an appendix, designed to be worked through in order with practice exercises and an answer key
- The tutorial uses Claude 3 Haiku (the smallest and cheapest model) but notes that Sonnet and Opus are available as more capable alternatives
Full summary
Anthropic's released an interactive tutorial on prompt engineering for Claude. The course runs nine chapters plus an appendix, designed to teach you how to write better prompts systematically. By the end, you should know how to structure prompts effectively, spot common failure modes and fix them with practical techniques, understand Claude's actual capabilities and limits, and build prompts from scratch for real tasks.
The course is hands-on. Each lesson includes an "Example Playground" where you can experiment directly—tweak prompts, watch how Claude responds differently, see what works. There's an answer key too, so you can check your work. The structure pushes you to practice rather than just passively read, and they recommend working through chapters in order rather than jumping around.
One practical note: the tutorial uses Claude 3 Haiku, their smallest and cheapest model. Anthropic also makes Claude 3 Sonnet and Claude 3 Opus, with Opus being the most capable. Haiku's enough for learning the fundamentals, though you might want to test concepts on a stronger model once you understand the basics.