The Missing Third Leg of Every Agentic AI Stack
Every architecture diagram I see draws the same three boxes. Sometimes it’s Model + RAG + MCP . Sometimes it’s Model + MCP + Tools. The labels move around, but the shape never changes. The…
Blog
The Multi-Cloud Metrics Problem Snowflake, Databricks, and BigQuery Can't Solve Alone
Enterprises running Snowflake, Databricks, and BigQuery side by side no longer struggle with data movement. Data pipeline tools solved that years ago. Now they have a metrics problem: the same “gross margin” or “active users”…
Inside a Real Benchmark: Measuring the Cost of AI on the Warehouse
Any AI performance conversation runs the same three tracks: token costs, inference latency, and model accuracy, and all three numbers matter. But once an AI system reaches enterprise data, a fourth system starts determining both…
Inside the AtScale and Snowflake Partnership: Why Snowflake Embedded AtScale in Semantic Views
The Snowflake Semantic Views XMLA Endpoint , powered by AtScale, is an integrated product offering. It’s the only semantic solution to have this distinction. It’s not something bolted on the side of Snowflake; it’s the…
Five Questions Every CDO Should Ask About AI and Semantics
The metrics powering your AI agents right now, like margin per square foot or total economic cost, probably don’t belong to you. They belong to whichever platform computes them today. Snowflake, Databricks, the frontier LLM…
Don’t Let Microsoft Be Your Warden
Microsoft just made the case for AtScale by playing Warden Norton, the prison boss from “The Shawshank Redemption.” On Tuesday, Sara Vredevoogd from Microsoft’s Power BI team announced that Microsoft 365 Copilot can now query…
Why I Joined AtScale: The Semantic Layer Inflection Point
Over four and a half years at Snowflake, I watched enterprises run into a problem that’s about to get much worse: every major platform has built its own semantic layer , and none of them…
A Skill or README Isn't a Semantic Layer
Why 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,…
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…
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…