Turning Data Requests Into Self-Service: Building an AI-Powered Analytics Product Users Love

Ticketmaster's operations team was drowning in data requests. Every "how many fans showed up to buy tickets last week?" question cost engineering hours. We were spending over 8 weeks/year being human query engines. We needed to give users the power to answer their own questions.We built OMT Wizard: a conversational analytics tool that lets non-technical users ask questions in plain English and get instant answers. Powered by Databricks Genie, it launched to 500+ users and achieved high stickiness. The users who try it keep coming back.

This session shares product lessons from building AI-powered internal tools — how we identified the right problem to solve, designed for trust and transparency, trained the AI on business logic, measured real adoption and turned skeptics into champions. You'll learn what worked — suggested questions, showing your work — what didn't — hiding complexity — and how to build AI products that solve real problems instead of looking for problems to solve.