The Data Exchange with Ben Lorica How to Make Your Data Truly AI-Ready
16 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
Models Need Business Context
- LLMs can generate SQL but lack business context and will guess which tables or columns to use.
- A semantic layer is required to teach models which tables, columns, and definitions are authoritative.
Semantic Layer As A Rosetta Stone
- The semantic layer translates business meaning into data artifacts so AI can reason about questions.
- It must include what data means, what questions are answerable, and data quality signals.
Start Narrow With Use Cases
- Start semantic layer work from specific domains and clear use cases rather than trying to cover everything.
- Narrow focus speeds deployment and makes human validation manageable.