microsoft/agent-academy

Curated lessons on getting started building agents with Copilot Studio

What it is

A GitHub repository that hosts a three-part course for people who want to build agents using Microsoft Copilot Studio (Microsoft's tool for creating AI agents).

Where to access it

The course itself lives on a website: https://aka.ms/agent-academy — the repo is primarily the source code and content behind that site.

What the course covers

The README doesn't describe the course content in detail, but the contributing guide references three named course tracks:

  • Recruit missions
  • Operative missions
  • Commander missions

There are also two other content types mentioned:

  • Special Ops — standalone missions
  • Cowork Collective — Copilot Cowork missions

How to contribute

Contributions are welcome, with separate guides for different parts of the project:

  • Courses (Recruit, Operative, Commander missions)
  • Special Ops (standalone missions)
  • Cowork Collective (Copilot Cowork missions)
  • A Custom Components Guide documents the custom markdown components used in the files

Legal / process requirements

  • Contributors must agree to a Contributor License Agreement (CLA) — a bot checks this automatically on pull requests.
  • The project follows the Microsoft Open Source Code of Conduct.
  • Microsoft trademarks and logos may appear in the project; their use must follow Microsoft's Trademark & Brand Guidelines.

What the README does not say

It does not explain what the course lessons actually teach, how long the course takes, prerequisites, or any technical setup steps.

Related

  • Project
    wang2122/sprix-sage-router

    A decision layer for Agent-to-Agent networks that optimizes mid-execution task rerouting by evaluating whether to continue, collaborate, or hand off based on current progress and artifact portability.

  • Project
    mnemosyne-oss/mnemosyne

    Mnemosyne is an open‑source, SQLite‑backed memory layer for LLM agents. It offers a local‑first, zero‑cloud solution with a Python SDK, a built‑in MCP server, and optional encrypted sync. The system stores facts, embeddings, and temporal triples using a three‑tier BEAM architecture (working, episodic, triple‑store) and performs hybrid vector‑keyword search inside SQLite. It integrates with many agent platforms (Claude Code, Cursor, OpenWebUI, Hermes, etc.) and runs with a single `pip install` and minimal resources.

  • Project
    onecli/onecli

    OneCLI is an open-source platform that allows teams to deploy and manage secure, sandboxed AI agents for every employee while centralizing credential management and security policies.

  • Project
    Jakeschincariol/instagram-agent-skill

    A set of Claude skills and local Python tools for Instagram content strategy, drafting, and optimization, featuring a humanizer to remove AI-generated patterns.