ClaudeMap

Generative AI for Beginners

Microsoft's 21-lesson course on building with generative AI — from prompting to agents.

Tutorials & Guidesofficialmicrosoftcoursebeginners
Visit projectmicrosoft/generative-ai-for-beginners

Microsoft's free 21-lesson course (118k+ stars) covers the full generative-AI building spectrum: prompting, embeddings, RAG, function calling, safety, and agents, each lesson with video, written guide, and runnable Python/TypeScript samples. The broader sibling of AI Agents for Beginners — start here if the agents course feels too narrow.

What it does

  • 21 lessons covering generative AI fundamentals, each labeled Learn (concept only) or Build (concept plus code)
  • Code examples in both Python and TypeScript where possible; a separate .NET edition exists for C# developers
  • Version 3 of the course by Microsoft Cloud Advocates, with a Keep Learning section in every lesson
  • Ships 50+ community language translations of the full course

When to use it

A structured starting path for developers new to generative AI who want conceptual grounding with runnable examples, before specializing in a particular provider or tool.

Getting started

git clone --filter=blob:none --sparse https://github.com/microsoft/generative-ai-for-beginners.git — the README recommends this sparse checkout (skipping the translations directories) because the 50+ translations make a full clone heavy.

Things to know

The repo carries 50+ language translations, so a full clone downloads far more than the course content itself — use the sparse-checkout command from the README. Content is courseware (Version 3), not a maintained SDK.

Repository

microsoft/generative-ai-for-beginners

Charted

Related on the map

  • Code with Claude Workshops

    Guide

    Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.

    • official
    • workshops
    • anthropic
    • managed-agents
    View

  • Building Effective Agents

    Guide

    Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.

    • official
    • agents
    • engineering
    • patterns
    View