anthropics/courses

Analysis updated 2026-05-18

★ 21,061Jupyter NotebookAudience · developerComplexity · 2/5Setup · moderate

Mindmap

mindmap
  root((repo))
    What it does
      API fundamentals
      Prompt engineering
      Real-world scenarios
      Production evaluations
      Tool use
    Learning format
      Jupyter Notebooks
      Step-by-step tutorials
      Interactive exercises
      Low-cost examples
    Tech stack
      Claude API
      Python
      Jupyter
    Use cases
      Learn Claude integration
      Build AI applications
      Evaluate prompt quality
      Add tool calling

mindmap root((repo)) What it does API fundamentals Prompt engineering Real-world scenarios Production evaluations Tool use Learning format Jupyter Notebooks Step-by-step tutorials Interactive exercises Low-cost examples Tech stack Claude API Python Jupyter Use cases Learn Claude integration Build AI applications Evaluate prompt quality Add tool calling

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Learn how to call the Claude API and configure model parameters for your first AI application.

USE CASE 2

Master prompt engineering techniques and apply them to solve complex real-world problems.

USE CASE 3

Build production systems by writing evaluations to measure and improve Claude's output quality.

USE CASE 4

Add tool use to your workflows so Claude can call external functions and APIs.

What is it built with?

PythonJupyter NotebookClaude APIClaude 3 Haiku

How does it compare?

	anthropics/courses	bloc97/anime4k	accumulatemore/cv
Stars	21,061	20,932	20,713
Language	Jupyter Notebook	Jupyter Notebook	Jupyter Notebook
Setup difficulty	moderate	hard	easy
Complexity	2/5	3/5	2/5
Audience	developer	vibe coder	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires a valid Anthropic API key and Python environment setup.

License could not be detected automatically. Check the repository's LICENSE file before use.

In plain English

This repository contains Anthropic's official educational courses for learning to work with the Claude AI API. It currently holds five courses designed to be taken in order. The first covers API fundamentals, getting an API key, working with model parameters, writing multimodal prompts, and streaming responses. The second is an interactive step-by-step tutorial on prompt engineering techniques. The third focuses on applying those prompting techniques to complex, real-world scenarios. The fourth teaches how to write production-grade prompt evaluations to measure output quality. The fifth covers tool use, explaining how to give Claude the ability to call external functions in your workflows. The courses are delivered as Jupyter Notebooks and tend to use Claude 3 Haiku to keep API costs low for students, though any Claude model can be used.

Copy-paste prompts

Prompt 1

Walk me through the first Anthropic course notebook to understand how to set up the Claude API and make my first request.

Prompt 2

Show me how to use the prompt engineering course to improve my prompts for a customer support chatbot.

Prompt 3

Help me implement the production evaluation techniques from course four to measure if my Claude-powered system is working well.

Prompt 4

Explain how the tool use course teaches Claude to call external functions, and show me a simple example I can adapt.

Prompt 5

I want to go through all five courses in order, what's the learning path and what will I be able to build by the end?

Frequently asked questions

What is courses?

Official Anthropic courses teaching how to build with Claude AI, from API basics through prompt engineering to production evaluations and tool use.

What language is courses written in?

Mainly Jupyter Notebook. The stack also includes Python, Jupyter Notebook, Claude API.

What license does courses use?

License could not be detected automatically. Check the repository's LICENSE file before use.

How hard is courses to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is courses for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub anthropics on gitmyhub

Verify against the repo before relying on details.