#pythonsdk

Jul 20, 2026

Ground Truth Before Go-Live: Building Better Fabric Data Agents with Automated Evaluation Datasets

One of the biggest challenges when building a Fabric data agent isn't creating the agent itself, it's knowing whether the answers it provides are consistently accurate. Many teams test a new agent by manually asking a handful of questions and reviewing the responses. While this approach can uncover obvious issues, it doesn't scale and it doesn't provide a reliable way to measure improvements over time. That's where ground truth datasets come in. A ground truth dataset is a collection of questions paired with known-correct answers derived directly from your semantic model. These datasets become the benchmark against which your Fabric data agent can be evaluated.

Data Agent Python SDK Notebooks

Notebooks to evaluate, automate, test data agents

Aug 9, 2025

Extend Fabric Data Agents with Python SDK End to End Tutorial

Let's walk through and End to End tutorial for extending an existing Data Agent with Bradley Ball, aka ‪@SQLBalls‬. In this tutorial we will use the first two links to get and clone the GitHub repo and to use the code to substitute our questions for those hard coded in the tutorial. We also extend the tutorial to make a change to move from hard coded questions to a more interactive Q & A application!