About This Event
An agent writing SQL on your data can run cleanly and still be wrong. Braintrust and MotherDuck show how to connect an agent to your data, give it the right context, then evaluate it in production and catch regressions before they ship.
What You'll Learn
- How to build an agent that answers questions over your own data
- How to give that agent the context it needs to return accurate answers
- How to turn real usage into an eval dataset
- How to set a quality bar and catch regressions before release
Who Should Attend
This event is ideal for:
Data EngineersML EngineersTechnical Leaders
