The Data Exchange with Ben Lorica How to Make Your Data Truly AI-Ready
32 snips
Oct 2, 2025 Yoni Leitersdorf, the CEO and co-founder of Solid, dives into the world of AI and data access. He explains why simply using LLMs for text-to-SQL can lead to errors without adequate business context. Yoni highlights the importance of a semantic layer, which acts as a Rosetta Stone for AI, providing essential data quality and query context. He discusses how organizations can start building this layer, the role of human oversight in AI accuracy, and the challenges in creating cross-system semantic layers. Plus, he shares his vision for the future of AI in enterprise.
AI Snips
Chapters
Transcript
Episode notes
Chat For Simple Answers, Analysts For Deep Work
- Users want direct answers more than discovery; chat solves simple queries while analysts handle deep analysis.
- Semantic layers support both quick chat answers and deeper discovery workflows.
Populate Native Semantic Formats
- Generate semantic artifacts in the formats your AI platform expects (Spaces, Unity Catalog, semantic models, YAML).
- Push and auto-update those artifacts to prevent drift after schema or model changes.
Cross-Platform Layer Remains Hard
- Access control and trust boundaries often prevent a single cross-platform semantic layer today.
- Platform-native interfaces (Databricks, Snowflake) handle user-level filtering and permissions.