MLOps.community The Semantic Layer and AI Agents // David Jayatillake // #343
70 snips
Oct 24, 2025 David Jayatillake, an experienced AI leader and former VP at Cube.dev, delves into the intricacies of semantic layers and their crucial role in data management. He critiques proprietary BI tools for locking companies into confusing ecosystems, advocating for open-source solutions. The discussion extends to how AI agents can streamline data workflows by automating repetitive tasks and enhancing queryability. Jayatillake also highlights the potential of LLMs in building semantic layers and the significance of company-specific definitions for effective data analysis.
AI Snips
Chapters
Transcript
Episode notes
Vendor Lock-In Hides In Semantic Logic
- Locking semantic logic inside BI vendor platforms creates hidden vendor lock-in and divergent truths across tools.
- Open, external semantic layers let multiple consumers (BI, ML, apps) reuse the same governed definitions.
Abstract The Semantic Layer From Tools
- Deploy the semantic layer as a separate, open component so many tools and teams can consume it.
- Choose open-source hosting to preserve freedom and let teams use the free implementation if needed.
Modeling Drives The Semantic Menu
- Data modeling and the semantic layer are tightly linked but distinct: models structure entities and events while the semantic layer exposes them as metrics and dimensions.
- Good data models make semantic layers easier and enable natural-language–close APIs that compile requests into SQL.