AI is changing the way we develop data solutions. Instead of writing every line of code ourselves, we can increasingly describe what we want to achieve and let AI agents help us build it. But how far can we take this in Microsoft Fabric, and where do we still need to stay in control?

In this full-day hands-on workshop, we’ll explore agentic development across the Microsoft Fabric ecosystem by building a data platform end-to-end, from source systems and data engineering to semantic models, reporting, and AI-powered Data Agents.

We’ll get our hands dirty with AI coding agents in VS Code, explore PBIP and code-first development workflows, and see how tools like Project Osmos can help turn data engineering requirements into executed and validated solutions. We’ll then build on that foundation to create reporting experiences and Fabric Data Agents, exploring how to prepare semantic models and data sources for reliable answers and how to test and validate their output.

Along the way, we’ll bring these pieces together into a development workflow that is repeatable, maintainable, and ready for real-world use.

Expect plenty of demos, practical examples, and a few moments where we let the agents do the work and see what happens!

By the end of this workshop, you’ll have a better understanding of how to use AI agents throughout the data platform development lifecycle, from raw data to reporting and agentic experiences, while keeping control over the architecture, code, and results.