Updated June 25, 2026
The Semantic Layer’s New JobEighteen months ago, Blue Yonder’s analytics engineering team made a decision most data organizations haven’t made yet: they stopped being a BI team. They saw what was coming. AI agents don’t just need access to data. They need to understand…
Updated June 23, 2026
Four AI Pillars and a Wide-Open OpportunityI just got back from the Databricks Data & AI Summit, and I have a lot to unpack. This was the biggest DAIS yet, with 31,309 attendees, and the energy was unmistakable. More importantly, Databricks came in with a sharpened…
Updated June 23, 2026
The Architecture Decision That Lets Carrefour’s Metrics Power Both Google Sheets and AI AgentsImagine if every time you created a document in Microsoft Word you couldn’t read it anywhere else. Not as an email, PDF, or Google Doc. Any time you wanted to collaborate with a new team or adopt a new technology,…
Updated June 22, 2026
Semantic Layer Summit Keynote: What It Takes to Make AI Work in the EnterpriseEvery enterprise AI conversation eventually runs into the same wall. Someone pulls up the output from an agent or a natural language query, and someone else in the room says, “That number doesn't look right.” The AI project doesn't have…
Updated June 18, 2026
A Skill or README Isn’t a Semantic LayerWhy not just give the agent a skill? A bunch of people asked this at this week’s Databricks Data + AI Summit. Write down what “revenue” means, drop the skill next to your data, and skip the semantic layer. I…
Updated June 18, 2026
AtScale’s CPO Luis Maldonado on What It Actually Takes to Make AI TrustworthyAt Snowflake Summit last week, AtScale Chief Product Officer Luis Maldonado sat down with Ravit on The Ravit Show to talk about the announcement everyone at the conference was asking about, and the deeper problem it's designed to solve. The…
Updated June 17, 2026
It’s Got to Be the Semantic Layer, BabyAtScale's Dave Mariani and Snowflake's Carl Perry on why governed semantics, not a smarter LLM, is what makes AI agents trustworthy. For years, business intelligence ran on a human workaround. When two reports disagreed about "revenue," a trained BI analyst…
Updated June 11, 2026
How Anthropic’s AI Accuracy Went from 21% to 95%Anthropic's data science and engineering team runs its internal analytics on Claude, and this week, they published the accuracy figures. Without a semantic layer, the answers were right 21% of the time. With one, accuracy improved to 95%, and some…
Updated June 11, 2026
Power BI Was Built as a Client. Stop Using It as a Foundation.Microsoft wants to own your semantics. We built the universal layer that keeps them yours. Power BI is a strong BI client. It was never an enterprise semantic layer, and the gap between those two jobs is now showing up…
Updated June 10, 2026
Your AI Isn’t Expensive. It’s Guessing.Inside a Tier 1 bank's $9-million-a-year AI rediscovery tax, and the architectural fix that cut compute costs by as much as 21,903x. Every time an analyst at a Tier 1 bank asks, "What was revenue in the Northeast last quarter?"…
