Aligned on Decisions: How Our Product Lead Builds with Data Agents in MotherDuck

​A product lead's week is full of questions that need data: which feature requests keep coming up, how customers are using compute, what changed since last week. Answering them by hand means reading tickets and pulling queries instead of deciding.

​Sheila Sitaram, MotherDuck's Product Lead for Compute and Agent Workloads, hands much of that work to data agents running on MotherDuck, so the answers are ready before the meeting starts. In conversation with Zoey Weaver, she walks through the agents she relies on:

• ​Sorting customer call notes and support tickets into themes with prompt_jev(), so the same feature requests surface every week

• ​A scheduled agent that pulls context from Slack, support tickets, and Linear to write the weekly business review analysis

• ​Dives that show how customers' agent workloads use compute