# microsoft/ai-agents-for-beginners

18 Lessons to Get Started Building AI Agents

Repository: https://github.com/microsoft/ai-agents-for-beginners
Canonical: https://ross.abutalabs.com/products/ai-agents-for-beginners
Homepage: https://aka.ms/ai-agents-beginners
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: agentic-ai, agentic-framework, agentic-rag, ai-agents, ai-agents-framework, autogen, generative-ai, semantic-kernel, foundry, foundry-local, microsoft-foundry
Last push: 2026-08-27T00:08:41+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 45
- inputs: {"age_days": 643, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 73281, forks 24237 (observed 2026-08-28T04:12:21.270156+00:00)

## What it is
An 18-lesson open course from Microsoft teaching how to build AI agents, delivered as Jupyter Notebooks with code samples using frameworks like AutoGen, Semantic Kernel, and Microsoft Foundry. It covers agentic design patterns, tool use, and agentic RAG for beginners.

## Use cases
- learn how to build AI agents from scratch
- understand agentic design patterns and tool use
- get started with agentic RAG
- compare agent frameworks like AutoGen and Semantic Kernel
- find hands-on Jupyter notebook tutorials for generative AI agents
- teach a course or workshop on building AI agents

## When to choose
- you are a beginner wanting a structured, lesson-based introduction to AI agents
- you prefer learning through runnable Jupyter Notebook code examples
- you want free, MIT-licensed educational material with multi-language translations
- you want exposure to multiple agent frameworks including Microsoft's ecosystem

## When to avoid
- you need production-ready agent code or a maintained framework rather than a course
- you are already an expert seeking advanced agent architecture guidance
- you want framework-agnostic content with no vendor-specific tooling
- you need a non-Python or non-.NET learning path

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, rag, llm-inference, prompt-engineering, developer-tools
- domain: artificial-intelligence, large-language-models, tutorials, education
- platform: python, cross-platform
- tags: course, jupyter-notebooks, agentic-ai, autogen, semantic-kernel, microsoft-foundry, beginner-friendly, ai-agents, retrieval-augmented-generation

## Member repositories
- microsoft/ai-agents-for-beginners (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.270156+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:15:24.522278+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/ai-agents-for-beginners (fetched 2026-08-28T04:12:21.270156+00:00, sha b54f9662b0a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.