BI Locked Semantic Models are Dead! Open Semantics Just Entered the Chat

The biggest blocker in fully adopting Unity Catalog (UC) isn’t data access; it’s the business logic that never makes it there. KPIs, measures, and dimensions live inside proprietary semantic models, hand-crafted by analysts over years. In an AI-era open semantics are crucial to go the next mile beyond static and manual data analytics, but rebuilding them manually is expensive, fragile, and doesn’t scale. We bring this vision of a scalable, automated & governed solution to life using our open-source agentic framework, Kasal. In this demo, we feature Coca-Cola HBC, a pioneer in big data processing & innovation, with whom we leveraged Kasal for one of their most complex Power BI reports to automatically generate over 25+ UC Metric Views, encompassing over 200 measures from a single semantic model and powering a fully optimized Genie Space on top of it. This real-world example shows how Kasal accelerates migrations and enables next-level AI-driven insights to generate real business value, as demonstrated through their IDOR (Insights Discovery On Report) initiative. Talk By: David Schwarzenbacher, Senior Solutions Engineer, Databricks ; Maximilian Kohnen, Sr. Data Quality Scientist, Coca-Cola HBC ; Nehmé Tohmé, Lead Data &AI Strategist, Databricks ; Connect with us: Website: https://databricks.com X: / databricks LinkedIn: / databricks Instagram: / databricksinc Facebook: / databricksinc