Python + Agents: Orchestrating advanced multi-agent workflows
In Session 5 of our Python + Agents series, we’ll go beyond workflow fundamentals and explore how to orchestrate *advanced, multi‑agent workflows* using the Microsoft Agent Framework. This session focuses on patterns that coordinate multiple steps or multiple agents at once, enabling more powerful and flexible AI‑driven systems. We’ll begin by comparing **sequential vs. concurrent execution**, then dive into techniques for running workflow steps in parallel. You’ll learn how fan‑out and fan‑in edges enable multiple branches to run at the same time, how to aggregate their results, and how concurrency allows workflows to scale across tasks efficiently. From there, we’ll introduce two multi‑agent orchestration approaches that are built into the framework. We’ll start with **handoff**, where control moves entirely from one agent to another based on workflow logic, which is useful for routing tasks to the right agent as the workflow progresses. We’ll then look at **Magentic**, a planning‑oriented supervisor that generates a high‑level plan for completing a task and delegates portions of that plan to other agents. Finally, we'll wrap up with a demo of an E2E application that showcases a concurrent multi-agent workflow in action. Prerequisites: To follow along with the live examples, sign up for a free GitHub account. If you are brand new to generative AI with Python, start with [our 9-part Python + AI series](https://aka.ms/pythonai/rewatch), which covers LLMs, embedding models, RAG, tool calling, MCP, and more. 📌 This event is a part of a series, learn more here: https://aka.ms/PythonAgents/YT Microsoft Agent Framework: https://learn.microsoft.com/agent-fra... Chapters: 0:00 Introduction to Advanced Multi-Agent Workflows 4:05 Recap: Agentic Workflows 7:36 Concurrency and Fan-Out/Fan-In Patterns 11:43 Aggregation Patterns 25:56 Conditional Routing with Concurrency 30:09 Built-in Workflow Orchestrations: Concurrent Builder 33:12 Magentic Builder: Planning and Progress Management 46:39 Handoff Orchestration: Dynamic Routing 57:18 Full-Stack Application Demo 1:01:32 Conclusion and Next Steps #microsoftreactor #learnconnectbuild [eventID:26692]

Python + Agents: Building your first AI-driven workflows

Python + Agents: Building your first agent in Python

Python + Agents: Adding a human in the loop to agentic workflows

The Agent Development Lifecycle: Build, Test, Deploy, Monitor | Interrupt 26

Microsoft Agent Framework Explained| Foundation & Hands-On Lab (Part 1)
![GitHub Copilot - Understanding Budgets [APAC]](https://i.ytimg.com/vi/F2rJ55VVf44/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4JgALQBYoCDAgAEAEYZSBlKGUwDw==&rs=AOn4CLBV0_dtAeVYbLZ_8d4MOBHs68EoKg)
GitHub Copilot - Understanding Budgets [APAC]

Model Context Protocol (MCP) Explained for Beginners: AI Flight Booking Demo!

Microsoft Agent Framework Tutorial 2025 - Build AI Agents with Python from Scratch | Complete Course

MCP vs ADK: How Modern AI Agents Connect and Work Together

Pi is INCREDIBLE - Building a Custom Coding Agent Live
![GitHub Copilot - Token Optimization [APAC]](https://i.ytimg.com/vi/0IOcPqubpMc/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4JgALQBYoCDAgAEAEYGCBcKH8wDw==&rs=AOn4CLDSgjO4d85qrAws5XH1g2yXi8Q5PQ)
GitHub Copilot - Token Optimization [APAC]

No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan
![GitHub Copilot - Understanding Budgets [AMER/EMEA]](https://i.ytimg.com/vi/YfMAtF0sMS8/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLA2prrUOs9X-QnHpcnm5YrDZ3ZUoQ)
GitHub Copilot - Understanding Budgets [AMER/EMEA]

Don't learn AI Agents without Learning these Fundamentals

The Agentic AI Developer: Deep Dive into the GitHub GH-600 Certification

RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source

EP 8 | AI Agents That Don’t Break Under Pressure

Moderne: DevTools or AgentTools? The Changing Target of Engineering Productivity
![GitHub Copilot - Token Optimization [AMER/EMEA]](https://i.ytimg.com/vi/LeALSSsbzHU/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLASGQaaaCCtNLUcWw1G8jyeATAPaA)
