AI over governed enterprise data

MCP servers and a Databricks Genie semantic layer over governed data, with access control and audit owned by engineering.

Problem

Business users wanted natural-language access to governed data. A chatbot on top would have bypassed existing access groups, lineage and curated marts.

Work

Designed the Genie semantic layer: business metadata, join criteria and metric views, so queries resolve to the same definitions as dashboards.
Built Databricks-backed MCP servers for Claude, scoped to curated data.
Enforced per-user permissions on every agent call and logged each one.

Result

Higher natural-language query accuracy on governed data, with no ungoverned copy.