Unlocking semantics for AI: How Mercedes-Benz Korea built trusted “Talk to Data” at scale

Summary

Mercedes-Benz Korea piloted a “Talk to Data” architecture that extends its Databricks analytics foundation with a governed semantic layer for enterprise AI, rather than treating the effort as a chatbot project. The design moves Power BI DAX KPI logic into Unity Catalog Business Semantics and Metric Views, keeping sources, joins, measures, dimensions, comments, and synonyms alongside governed Lakehouse data. Genie spaces use curated metric views for domain questions, while Agent Bricks composes persona-based agents, with Unity Catalog enforcing row- and column-level access. An automated DAX-to-Metric-View transpiler parses semantic models, maps tables, generates draft definitions, flags non-automatable measures, and reports conversion gaps. The documented playbook combines gold-layer curation, KPI validation, regression testing, Genie optimization, persona agents, and Databricks Apps; the pilot reports AI answers aligned with established KPI definitions and BI reporting logic.

Context

The existing setup distributed semantic context across Power BI reports and other components, making it harder for AI to capture business semantics consistently across users and workloads. Persona-based access control on KPIs was also not yet available.

Approach / What changed

Mercedes-Benz Korea extended its Databricks data foundation with Unity Catalog Business Semantics and Metric Views, then connected curated Genie spaces, Agent Bricks persona agents, Unity Catalog governance, Databricks Apps, and Lakebase. An automated DAX-to-Metric-View transpiler accelerated conversion of more than 500 KPI definitions, with validation and manual review for non-automatable measures.

Takeaways

• Mercedes-Benz Korea’s foundation covers more than 500 KPIs across sales, product, marketing, customer service, and finance, with shared definitions in the Lakehouse and Unity Catalog.
• The DAX-to-Metric-View transpiler extracts measures and metadata, maps Power BI tables to Unity Catalog, generates draft metric views and SQL, and flags complex measures for manual review.
• Agent Bricks routes questions to persona agents that use multiple Genie spaces, while Unity Catalog applies row- and column-level permissions to natural-language queries.

Related reading