How Semantic Layers Future-Proof Data Strategies with David P. Mariani of AtScale

The semantic layer is becoming the backbone of trusted, AI-ready data. We’re joined by David P. Mariani, Chief Technology Officer and Co-Founder of AtScale, to explore why defining a shared business language is critical for scalable analytics and AI innovation. David explains how the semantic layer enables teams to align on metrics, eliminate silos and create flexibility across BI tools, data platforms and emerging AI interfaces. He also shares how open standards and large language models are reshaping how businesses interact with their data.

Key Takeaways:

00:00 Introduction.

02:22 Semantic layers began in BI tools, tightly linked to the presentation layer.

08:02 Combining a semantic layer with LLMs unlocks powerful insights.

12:57 Relying on one BI tool creates inconsistent metrics as AI adds new consumption layers.

17:29 Open-sourcing SML prevents lock-in and standardizes semantic models.

22:38 Semantic layers with GenAI reshape strategy through language and a strong query engine.

25:45 Without a semantic layer, LLMs were wrong 80% of the time.

30:33 Data engineers should build base semantic objects as part of their pipeline.

38:53 MCP with semantic layers and knowledge graphs gives LLMs a richer context.

Resources Mentioned:

David P. Mariani

https://www.linkedin.com/in/davidpmariani/

AtScale | LinkeIn

https://www.linkedin.com/company/atscale-inc-/

AtScale | Website

https://www.atscale.com/

SML

https://www.atscale.com/blog/introduction-to-sml-a-standard-semantic-modeling-language/

Model Context Protocol (MCP)

https://modelcontextprotocol.io/docs/getting-started/intro

Thanks for listening to the “Data Masters Podcast.” If you enjoyed this episode, be sure to subscribe so you never miss our latest discussions and insights into the ever-changing world of data.

#DataStrategy #DataManagement #DataMastersPodcast