22-25 April 2026 
Fabric Data Agents
Proposed session for SQLBits 2026TL; DR
Fabric Data Agents allow you to query your data using natural language. Based on the question asked, an LLM constructs the necessary SQL, KQL or DAX queries and interprets the data returned.
Session Details
Wouldn't it be nice if we could just talk to our data?! That is basically what fabric Data Agents try to achieve. By combining your data with large language models that can generate (and interprete the results of) SQL, DAX and kusto queries, data agents provide a way to ask natural language questions on the data stored in fabric lakehouse, semantic models and eventhouses.
In this session you will see how to set up data agents, and consume them from copilot as well as other applications.
In this session you will see how to set up data agents, and consume them from copilot as well as other applications.
3 things you'll get out of this session
Create: Learn how the create a Fabric Data Agent
Configure: how to finetune a Fabric Data agent to get better results
Consume: how to use the Fabric Data Agent in Fabric Copilot and in custom applications
Speakers
Nico Jacobs's other proposed sessions for 2026
The Power of Paginated Reports - 2026
What are Fabric Materialized Lake Views - 2026
When Translytical Task Flow meets Fabric Data Function - 2026