Fabric Data Agents

Fabric data agents are now generally available in Microsoft Fabric, and they give teams a way to build conversational Q&A experiences over data sources like Power BI semantic models.

But the real work is not just creating the agent. It is shaping the semantic model, instructions, examples, and feedback loop so the answers are robust.

Which is why our next Wellington Power BI & Fabric User Group session is on Fabric data agents: what they are, where they fit, and how to get better results from them.

We are privileged to have Sandeep Pawar joining us for the session from Vancouver. Sandeep is a Principal Program Manager on the Microsoft Fabric Customer Advisory Team, where he focuses primarily on data agents, and writes regularly about them at fabric.guru.

He'll cover:

• How Fabric data agents work, and how they differ from Copilot in Fabric
• How to build a data agent over a Power BI semantic model, including instructions and example queries that improve accuracy on real data
• Patterns for evaluating responses and refining the agent over time

45 minutes of content, 15 minutes for Q&A.

📅 Friday 26 June, 12:00 PM NZST
💻 Online