anthropics/prompt-eng-interactive-tutorial

Anthropic's Interactive Prompt Engineering Tutorial

What this project is

An interactive tutorial that teaches you how to write effective prompts for Claude, Anthropic's AI assistant. It's a hands-on course with lessons, exercises, and a playground for experimenting.

What you'll learn

By the end, you'll be able to:

  • Structure a good prompt
  • Spot common mistakes and fix them with simple '80/20' techniques
  • Know what Claude is good and bad at
  • Build strong prompts from scratch for everyday uses

How it's organized

The course has 9 chapters plus an appendix, meant to be done in order. Each chapter has a lesson and exercises. At the bottom of each lesson is an Example Playground where you can tweak prompts and see how Claude's answers change. There's also an answer key (linked in the README).

Chapter topics (from the table of contents)

  • Beginner: Basic prompt structure, being clear and direct, assigning roles
  • Intermediate: Separating data from instructions, formatting output, thinking step by step, using examples
  • Advanced: Avoiding hallucinations, building complex prompts for real industries (chatbots, legal, financial, coding), plus an appendix on chaining prompts, tool use, and search/retrieval

Which model it uses

The tutorial runs on Claude 3 Haiku — Anthropic's smallest, fastest, and cheapest model. The README notes that Anthropic also has two smarter models (Sonnet and Opus), but this course sticks with Haiku.

How to access it

You can go through the tutorial directly in the repository (start with 01_Basic Prompt Structure). There's also a Google Sheets version using Anthropic's Claude for Sheets extension, which the README recommends as more user-friendly.

Key takeaway

This is a practical, exercise-heavy course for anyone who wants to get better at prompting Claude — no prior experience assumed, just a willingness to practice.

Related

  • Project
    stanfordnlp/dspy

    DSPy is a framework that allows developers to build modular AI systems using Python code instead of manual prompt engineering, automatically optimizing prompts and model weights for better performance.

  • Project
    patchy631/ai-engineering-hub

    AI Engineering Hub is a community-driven collection of 93+ hands-on AI engineering projects and tutorials, sorted by difficulty (beginner/intermediate/advanced), with a learning roadmap, contribution guidelines, and an optional newsletter. All content is grounded purely on the provided README.

  • Project
    RSSNext/Folo

    Folo is an open‑source, cross‑platform RSS/feed reader that integrates AI for summarising, translating, querying and automating content, syncing across devices and offering many integrations.

  • Project
    google/langextract

    LangExtract is a Python library for LLM‑driven, grounded extraction of structured data from any text. It chunks long documents, runs parallel LLM calls (Gemini, OpenAI, Ollama or custom providers), maps each extraction back to its exact character span, and produces an interactive HTML visualiser. Install via pip, define a prompt + few‑shot examples, call `lx.extract`, and save/visualise the results. Supports cloud, local, and batch processing, with a plugin system for new model providers.