Starting August 25, we’re running a free three-part live series on Microsoft Reactor that takes you from “what is a hosted agent?” to a deployed, orchestrated multi-agent application, all built in VS Code with the Microsoft Foundry Toolkit.
Building agents, without leaving your IDE.
Building an AI agent usually means context-switching between a portal, a terminal, a notebook, and three browser tabs of documentation. You write some instructions, deploy, wait, test in a playground, discover the agent hallucinated a policy that doesn’t exist, and start over. The feedback loop is measured in minutes, not seconds.
The Microsoft Foundry Toolkit for VS Code collapses that loop. You generate an agent from extension using the Command Palette, configure the model and instructions, debug it locally against Agent Inspector, and deploy to Microsoft Foundry Agent Service.
What you will Build
Explain like I am an Executive agent
We’ve all written the perfect post-mortem, root cause, timeline, remediation, only to get back: “So… is the website down or not?”
Session 2 builds a single-purpose agent that takes this:
“The API latency increased due to thread pool exhaustion caused by synchronous calls introduced in v3.2.”
…and returns this:
Executive Summary:
– What happened: After the latest release, the system slowed down.
– Business impact: Some users experienced delays while using the service.
– Next step: The change has been rolled back and a fix is being prepared before redeployment.
The Resume → Job Fit Evaluator
Session 3 steps up to a multi-agent workflow: four agents that collaborate to parse a résumé and a job description, extract the real requirements, score alignment, identify gaps, and generate a personalized learning roadmap backed by Microsoft Learn resources.
This is where you see orchestration patterns, agent-to-agent handoffs, and how to keep a multi-agent system debuggable .
The sessions
|
Title |
Description |
Date and Time |
Speaker |
|
1️⃣ What Is Microsoft Foundry Toolkit for VS Code? What’s New and How to Get Started |
Foundation session touring the toolkit’s workflow: agent creation, model configuration, local debugging with Agent Inspector, and deployment to Microsoft Foundry Agent Service. |
Tuesday, August 25 12:00 PM UTC |
Junjie Li Senior Product Manager, DevDiv, Microsoft |
|
2️⃣ Build Your First Microsoft Foundry Agent: Executive Briefings from Technical Updates |
Hands-on build session creating a Python hosted agent, authoring instructions, testing safety boundaries in Agent Inspector, and deploying to the cloud. |
Tuesday, September 1 2:00 PM UTC |
Bethany Jepchumba Cloud Advocate, Microsoft |
|
3️⃣ Build a Multi-Agent Career Copilot: Resume-to-Job Fit Analysis |
Orchestration session building a 4-agent collaborative team that parses résumés and job descriptions, scores alignment, finds gaps, and generates learning roadmaps. |
Thursday, September 3 3:00 PM UTC |
Shivam Goyal Microsoft MVP (AI) |
Follow along on GitHub….
Every session maps to our workshop in the companion repo with 50+ languages supported, so you can build alongside us or catch up afterward:
Save your seat and see you there
Sessions run on August 25, September 1, and September 3. Register once for the series and you’re in for all three, and you’ll get the recordings even if you can’t make it live.
👉 Register for the full series
Bring your questions and see you there. 🚀