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
Test the Math in Your AI Answers
Executive summary AI evals test what an answer says and how it says it. They rarely test whether the number inside it is right, and that number is what the business acts on. A wrong…
Semantic Layers Are Still the Missing Piece in Generative Analytics
Ask your AI what churn was last quarter, and it will give you a number. It won’t tell you whether that’s logo churn or revenue churn, or whether it includes voluntary cancellations. A human analyst…
A Wrong Answer Has Never Looked So Good
Executive Summary: An agent doesn’t have a gut check, so it treats a wrong answer as fact and can’t catch it before building the next question on top of it, and accuracy drags down fast…
Microsoft’s About-Face on Semantic Layer Standards
When Snowflake launched the Open Semantic Interchange in September 2025, dozens of companies signed on. Microsoft wasn’t one of them. Power BI’s semantic models stayed in DAX, built for Power BI, while the rest of…
How to Achieve AI Accuracy: Buy the Foundation, Rent the Model
Executive summary AI leaderboard rankings measure a model working alone, on tasks that look little like your warehouse. On the 410 business questions in the BIRD-Interact benchmark, what sat under the model made a bigger…
BIRD-Interact, explained: the conversational text-to-SQL benchmark
What is BIRD-Interact? BIRD-Interact is an independent benchmark that tests how well AI systems complete database tasks through conversation. It evaluates whether a system can clarify a vague request, explore the database schema, write correct…
Stop Writing Your Semantic Model. Start Reviewing It.
Executive summary AI tools, like AtScale’s CoModel, can now draft most of a semantic model, and that will change the data modeler’s job. Claude Sonnet 5, working through a semantic layer that AI generated and…
Every AI Accuracy Fix Your Team Made This Year Reopens at the Next Upgrade
Executive summary Your team makes most AI accuracy fixes for one model. When that model changes, custom training has to be rerun on the new model, and prompts and skills files have to be retested.…
Self-Service Analytics Stalled Once. Will AI Stall It Again?
Executive summary Self-service BI stalled at about 25% of employees for more than a decade because the numbers didn’t agree, not because the tools were hard to use. AI chat makes asking easy again, but…