A 17-lesson Python tutorial that builds a Claude Code-like agent harness from scratch, starting with a single loop and bash.
anthropics/prompt-eng-interactive-tutorial
An interactive, chapter-based course that teaches developers how to write effective prompts for Claude.
- Stars
- 38,673
- Forks
- 4,287
- Open issues
- 64
- Last commit
- 2 months ago
What is it?
This is a hands-on prompt engineering course from Anthropic, built as a set of Jupyter notebooks. It walks through nine chapters, from basic prompt structure and clear instructions to role assignment, separating data from instructions, formatting output, step-by-step reasoning, few-shot examples, and reducing hallucinations. An appendix covers chaining prompts, tool use, and search and retrieval.
Each lesson includes an example playground where readers can edit prompts and compare Claude's responses. The course is meant to be worked through in chapter order, with exercises for practicing and troubleshooting prompts. It uses Claude 3 Haiku, and the project also notes a Google Sheets version that uses the Claude for Sheets extension.
The course targets developers who want a systematic way to build prompts for common use cases, from chatbots to legal, financial, and coding tasks.
Key features
- 01Nine chapters progress from basic prompt structure to advanced techniques.
- 02Each lesson has an example playground for editing prompts and comparing responses.
- 03Includes exercises for practicing prompt writing and troubleshooting.
- 04Appendix covers prompt chaining, tool use, and search and retrieval.
Use cases
- Learning prompt engineering fundamentals for Claude from scratch.
- Building prompts for chatbots, legal, financial, or coding workflows.
- Reducing hallucinations and improving output formatting in LLM applications.
Quick start
- 1
Open the course on Google Sheets (recommended, more user friendly)
- 2
Or clone the repository locally
- 3
Go to the 01_Basic Prompt Structure lesson to begin
Things to know
- The tutorial uses Claude 3 Haiku, and the Google Sheets version requires Anthropic's Claude for Sheets extension.
- The README gives no license, so reuse terms are unclear.
Topics
FAQ
- What is prompt-eng-interactive-tutorial?
- An interactive, chapter-based course that teaches developers how to write effective prompts for Claude. This is a hands-on prompt engineering course from Anthropic, built as a set of Jupyter notebooks. It walks through nine chapters, from basic prompt structure and clear instructions to role assignment, separating data from instructions, formatting output, step-by-step reasoning, few-shot examples, and reducing hallucinations. An appendix covers chaining prompts, tool use, and search and retrieval.
- Is prompt-eng-interactive-tutorial free to use? What license does it have?
- prompt-eng-interactive-tutorial has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is prompt-eng-interactive-tutorial still maintained?
- Updated within 6 months. The last commit to prompt-eng-interactive-tutorial was on Aug 28, 2026.
- What can I use prompt-eng-interactive-tutorial for?
- Learning prompt engineering fundamentals for Claude from scratch. Building prompts for chatbots, legal, financial, or coding workflows. Reducing hallucinations and improving output formatting in LLM applications.
- How do I install prompt-eng-interactive-tutorial?
- Open the course on Google Sheets (recommended, more user friendly) Or clone the repository locally Go to the 01_Basic Prompt Structure lesson to begin
- Where can I get prompt-eng-interactive-tutorial?
- The source code and installation instructions are on GitHub: https://github.com/anthropics/prompt-eng-interactive-tutorial
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A collection of Jupyter notebook recipes showing how to build with the Claude API, from classification and RAG to tool use and evals.
A curated directory of Agent Skills, the SKILL.md instruction files that teach AI coding assistants like Claude, Codex and Copilot new tasks.
A step-by-step Go workshop that teaches you to build a coding agent on the Claude API, adding file, shell and search tools one at a time.
A Chinese-language step-by-step guide and demo code for learning LLMs, from calling APIs to local deployment and fine-tuning, with Kaggle/Colab versions.
A guide to running autonomous AI coding loops with Geoff Huntley's Ralph methodology, covering planning, building, specs and prompt templates.