Unlocking semantics for AI: How Mercedes-Benz Korea built trusted “Talk to Data” at scale
Mercedes-Benz Korea built a trusted "Talk to Data" solution at scale by making 500+ KPI definitions available in an AI-ready semantic layer on Unity Catalog metric views, accelerating the transition with an automated DAX-to-Metric-View transpiler. This governed semantic layer supports both existing BI and new "Talk to Data" experiences, with Genie and Agent Bricks providing consistent answers and shaping a playbook for persona-based AI agents across markets.
* One KPI layer: Mercedes-Benz Korea built on its established Lakehouse and Power BI stack by making 500+ KPI definitions available in an open, AI-ready semantic layer on Unity Catalog metric views, using an automated DAX-to-Metric-View transpiler from Databricks to accelerate the transition. * Governed semantics for BI and AI: With Unity Catalog metric views, Mercedes-Benz Korea extended its governed semantic layer for enterprise KPIs. This layer supports both existing BI reports and new “Talk to Data” experiences, with Genie and Agent Bricks providing answers consistent with the existing KPI definitions. * Scaling “Talk to Data” across markets: Building on Unity Catalog metric views, Genie, and Agent Bricks, Mercedes-Benz Korea is shaping a playbook for persona-based AI agents on top of a shared KPI layer, which can serve as a reference for other Mercedes-Benz sales markets in enabling self-service analytics for sales, product, finance, and marketing teams.