Ever built something in Copilot Studio and thought, “This is great—until it isn’t”? Or coded a Semantic Kernel agent and wondered if you just reinvented what a low-code builder could’ve done faster? In this session, we’ll follow a single use case—a personal “Missed Meeting” agent that summarizes what you missed and what to do next—and build it three different ways: Copilot Studio (low-code), Semantic Kernel + Azure AI (pro-code), and a hybrid approach that combines both.

You’ll see how the same idea flexes across environments: what’s easy, what’s limiting, and where each platform shines. Along the way, we’ll cover the real decision factors—data access, governance, extensibility, cost, and developer velocity—and wrap up with a framework for choosing the right path for your next agent. Whether you live in Power Automate or Visual Studio, you’ll leave knowing how to pick your build battles wisely.