Updated June 18, 2026

A Skill or README Isn’t a Semantic Layer

A skill is a static instruction, and a model treats it as a suggestion, not a contract Why not just give the agent a skill? A bunch of people asked this at this week’s Databricks Data + AI Summit. Write…

Posted by: Mark Palmer

Updated June 17, 2026

It’s Got to Be the Semantic Layer, Baby

AtScale'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…

Posted by: Mark Palmer

Updated June 11, 2026

How Anthropic’s AI Accuracy Went from 21% to 95%

The fix wasn't a smarter model. It was a semantic layer. 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%…

Posted by: Dave Mariani

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?"…

Posted by: Mark Palmer

Updated June 18, 2026

A Skill or README Isn’t a Semantic Layer

A skill is a static instruction, and a model treats it as a suggestion, not a contract Why not just give the agent a skill? A bunch of people asked this at this week’s Databricks Data + AI Summit. Write…

Posted by: Mark Palmer

Updated June 17, 2026

It’s Got to Be the Semantic Layer, Baby

AtScale'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…

Posted by: Mark Palmer

Updated June 11, 2026

How Anthropic’s AI Accuracy Went from 21% to 95%

The fix wasn't a smarter model. It was a semantic layer. 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%…

Posted by: Dave Mariani

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?"…

Posted by: Mark Palmer
Guide: How to Choose a Semantic Layer
The Ultimate Guide to Choosing a Semantic Layer