AI Agents for Beginners
Curated by @tripp
Updated Sep 18, 2026
Microsoft's open-source AI Agents for Beginners curriculum (MIT), ported for LearnOS: 6 modules and 20 lessons on agent design patterns, tool use, agentic RAG, trustworthy agents, planning, multi-agent systems, metacognition, protocols (MCP, A2A), context engineering, memory, and production deployment and security. Searchable and citable inside Claude Code, Cursor, or Codex.
Learning is better together
Bring a question from this course or share what you made with other learners.
Quality
Scored on six categories — citations, structure, content richness, retrieval-readiness, scaffolding, and writing quality.
How densely lessons cite external sources, and how varied those sources are.
Module balance and reasonable lesson sizing.
Code examples, diagrams, and math — the multimodal payload.
How well-sectioned lessons are for search, citations, and deep links.
Models used
Models the creator uses in this course — chat, study guides, flashcards, ingest. Updated when the listing is republished.
Syllabus
Folder tree from your library — expand modules to see lessons.
View full syllabusChangelog
- v1.12026-10-12
Synced with upstream microsoft/ai-agents-for-beginners (4c9a275). Tool Use Design Pattern: new section on loading tools from an MCP server with MCPStreamableHTTPTool, with a web-search example (~32 min, up from 29). AI Agents in Production and Deploying Scalable Agents: refreshed links (LLM Guard, GSM8K dataset, Foundry Model Router docs).
- v1.02026-09-18
Initial port of microsoft/ai-agents-for-beginners at commit 25b7985 (Sept 17, 2026): 18 upstream lessons regrouped into 6 modules plus a syllabus with roadmap, upstream attribution on every lesson. Tracked weekly for upstream changes.
Attribution
LearnOS is a learning workspace, not a content host. This listing curates external resources; original creators retain ownership. Learners may need to obtain materials separately where noted.