live wire
▸Snowflake agent evals can pin judge versions; unpinned metrics may roll forward and shift scoresSnowflake▸ThoughtSpot makes Spotter 3 default for new instances; it requires download rights and always shares query data with an LLMThoughtSpot documentation▸MotherDuck adds image classification and object location to prompt_jev(), returning typed SQL outputs with confidence scoresMotherDuck▸BigQuery conversational analytics adds Montréal and Toronto; mixed-region agents still default to globalGoogle Cloud Documentation▸Fabric enables Azure OpenAI Copilot access by default, but OpenAI-subprocessor and cross-region processing/storage switches remain offMicrosoft Learn▸Snowflake Cortex Agents now continue by default when named tools are inaccessible, emitting warnings instead of failing the runSnowflake documentation▸Databricks Genie One can use group memberships to tailor answers, while Unity Catalog remains the access-control boundaryDatabricks documentation▸Fabric data agents can query Power BI models with Read alone; Build and workspace access are unnecessaryMicrosoft Learn▸Fabric data-agent Git configs expose column flags, but selecting a table still includes every columnMicrosoft Learn▸Google Data Agent Kit offers remote Spark kernels, but notebook exports can still move results into local Pandas or ArrowGoogle Cloud Documentation▸Cube says production analytics agents need explicit partial-result states, caller-filtered model search and durable artifactsCube▸Thinking Machines names Bridgewater behind ReViSQL-K2.6, citing 92.97% SC-16 accuracy at 15% of frontier-model costThinking Machines Lab▸AWS says a mismatched data/tool/prompt release cut its Field Sales agent pass rate from 78% to 38% in pre-productionAWS Artificial Intelligence Blog▸NL2SQL Multi-Agent ships evaluation artifacts across BIRD, CSpider, Archer and KDD DataSpace—but no software licenseGitHub▸Snowflake agent evals can pin judge versions; unpinned metrics may roll forward and shift scoresSnowflake▸ThoughtSpot makes Spotter 3 default for new instances; it requires download rights and always shares query data with an LLMThoughtSpot documentation▸MotherDuck adds image classification and object location to prompt_jev(), returning typed SQL outputs with confidence scoresMotherDuck▸BigQuery conversational analytics adds Montréal and Toronto; mixed-region agents still default to globalGoogle Cloud Documentation▸Fabric enables Azure OpenAI Copilot access by default, but OpenAI-subprocessor and cross-region processing/storage switches remain offMicrosoft Learn▸Snowflake Cortex Agents now continue by default when named tools are inaccessible, emitting warnings instead of failing the runSnowflake documentation▸Databricks Genie One can use group memberships to tailor answers, while Unity Catalog remains the access-control boundaryDatabricks documentation▸Fabric data agents can query Power BI models with Read alone; Build and workspace access are unnecessaryMicrosoft Learn▸Fabric data-agent Git configs expose column flags, but selecting a table still includes every columnMicrosoft Learn▸Google Data Agent Kit offers remote Spark kernels, but notebook exports can still move results into local Pandas or ArrowGoogle Cloud Documentation▸Cube says production analytics agents need explicit partial-result states, caller-filtered model search and durable artifactsCube▸Thinking Machines names Bridgewater behind ReViSQL-K2.6, citing 92.97% SC-16 accuracy at 15% of frontier-model costThinking Machines Lab▸AWS says a mismatched data/tool/prompt release cut its Field Sales agent pass rate from 78% to 38% in pre-productionAWS Artificial Intelligence Blog▸NL2SQL Multi-Agent ships evaluation artifacts across BIRD, CSpider, Archer and KDD DataSpace—but no software licenseGitHub
nl2sql.ai
newsLAUNCH

Welcome to nl2sql.ai

A trade publication for one technical beat: systems that turn natural language into SQL. Continuous coverage, evidence-diffed rankings, public corrections.

By The Editorial Desk· Aug 10, 2026the quick take — two AI hosts go live when you do

nl2sql.ai covers one beat, relentlessly: natural language to SQL. New model releases, benchmark movements, open-source projects, enterprise platform features, research papers, and the occasional post-mortem when things go wrong.

What we publish

  • The wire — a continuously updated feed of short, sourced items: releases, papers, leaderboard moves, announcements.
  • Stories — reported pieces when events deserve more than a headline.
  • The leaderboard — a monthly, evidence-diffed ranking of the systems that matter.
  • The directory — reference entries for every serious system on the beat, kept current.
  • The benchmark tracker — BIRD, Spider 2.0, and whatever credible evaluation comes next, with every number linked to its source.

The rules we publish under

  1. Every claim cites a source. Wire items and stories link to the primary artifact — the release notes, the paper, the leaderboard entry.
  2. Rankings are evidence-diffed. Score changes name the evidence that moved them. No pay-for-placement, ever.
  3. Corrections are public. Corrected or retracted stories stay visible with a note explaining what changed.

Why this beat

Text-to-SQL sits at the exact pressure point of enterprise AI: it is the interface between "everyone can ask questions of data" and "the SQL was subtly wrong and nobody noticed." Benchmarks like Spider 2.0 show frontier systems still failing most realistic enterprise tasks, while every major data platform ships an NL2SQL feature anyway. That gap — between demo and dependable — is a news beat. We intend to cover it relentlessly.

Tips, corrections, and challenges: desk@nl2sql.ai. The wire is live.

Filed by The Editorial Desk. Corrections: desk@nl2sql.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.

    more from the desk