Microsoft Reactor Redmond

In this session, we explore the end-to-end journey of designing and developing AI solutions with Microsoft Foundry models. The session is structured around four key phases of the model development journey.

We begin with Model Understanding, where you discover the Foundry model catalog and build intuition around core model capabilities. Next is Model Selection, focusing on how to choose the right model for a given use case using benchmarks, evaluations, and leaderboards. We then move into Model Customization, covering how models can be adapted through techniques such as context engineering, fine‑tuning, and compression to better meet application needs. Finally, we close with Model Observability, highlighting how evaluations, tracing, and monitoring help ensure models behave safely, reliably, and effectively at scale.

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.

One agent is powerful. Multiple agents working together? That's transformational.

In this session, we explore multi-agent orchestration patterns: how to design agent teams, delegate tasks, and coordinate complex workflows. Using Microsoft Agent Framework and Microsoft Foundry, you'll see how to build agent systems that divide and conquer problems too complex for a single agent.

What you'll learn:
• When single agents aren't enough (and when they are)
• Multi-agent architecture patterns: delegation, collaboration, debate
• Building agent teams with Microsoft Agent Framework
• Coordinating complex workflows across agents
• Real-world use cases: research assistants, code review teams, customer service escalation

Who should attend: Developers who've built their first agent and want to scale up to multi-agent solutions.

-------------------------------------------------------
Explore the Learn paths: