Book a demo

Blog

A better LLM isn’t the biggest upgrade for Text-to-SQL

Across Seven LLMs, a Semantic Layer Improved Accuracy More Than Switching Models

Executive Summary Seven LLMs answered the same 410 business questions from the BIRD-Interact benchmark , once against PostgreSQL with full documentation and once through an AtScale semantic layer. Their tool-call logs show seven working styles.…
Estimated Reading Time: 11 minutes
Read Article
Topics
Topics
Platforms / Tools
Platforms / Tools
Industries
Industries
Content Type
Content Type
Clear all

/ 6 MIN READ

AtScale and OpenAI: The Comprehensive Guide

OpenAI has changed how people work. Enterprise teams use ChatGPT every day to draft, summarize, research, and write code. Building enterprise applications on business data is a harder row to hoe. Ask Codex to build…

Posted By: Mark Palmer

/ 10 MIN READ

Will the real semantic layer please stand up?

Executive Summary: A semantic layer defines business metrics and computes them on request. A universal semantic layer makes those definitions available across AI agents, BI tools, and spreadsheets, reducing duplicated logic. An AtScale customer-count example…

Posted By: Ryan Siegler

/ 9 MIN READ

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…

Posted By: Ryan Siegler

/ 7 MIN READ

You Defined Your Metric Once. So Why Don't Your AI Tools Agree?

Executive summary AI tools don’t agree because each one writes its own query, and the query is where a metric gets computed. A shared definition tells a tool what retention means, but the tool still…

Posted By: Naveen Hariprasad

/ 7 MIN READ

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…

Posted By: Naveen Hariprasad

/ 7 MIN READ

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…

Posted By: Naveen Hariprasad

/ 8 MIN READ

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…

Posted By: Sarah Mulcahy

/ 4 MIN READ

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…

Posted By: Chris Lynch

/ 10 MIN READ

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…

Posted By: Dave Mariani