live wire
▸Snowflake’s Cortex Agent quickstart routes metrics and transcripts with prompt rules—but documents no authorization boundarySnowflake▸Oracle Select AI generates SQL/PGQ for property graphs—but errors if one AI profile mixes graphs with tables or viewsOracle▸Domo’s data team standardizes MCP builds with shared scaffolding; beta toolkits inherit user permissionsDomo▸Databricks proposes five outcome signals for agentic BI—and says dashboard counts and license usage miss decision qualityDatabricks▸One vibe-coded database app needed 56+ human test hours and three repair rounds despite AI Studio’s verification claimsMancas & Mancas / arXiv▸BigQuery AI.IF’s default cost mode trains a local model for most rows—and drops row-error thresholdsGoogle Cloud▸AWS’s multi-tenant data-agent pattern gives the broker Lambda no data permissions; Cognito roles carry Lake Formation scopeAWS Big Data Blog▸Amazon OpenSearch’s optimized engine adds nested agent traces, but AWS reserves it for log analytics—not vector searchAWS▸Two interpretation-based provenance semantics cannot express SQL bag difference, new theorem showsKolaitis / arXiv▸Databricks Feature Views reuse one definition for training and live scoring, but online lookup still returns latest available stateDatabricks▸Databricks Genie’s Slack and Teams previews default channel answers to public, even when viewers lack source-data accessDatabricks▸Snowflake’s two-tool GraphRAG agent beat a seven-tool graph setup 70% to 60% on 22 ontology questionsSnowflake Engineering▸Semantix opens an Apache-2.0 semantic-first data-agent stack, but labels the project WIP and has no release or adoption yetGitHub / icosmos-space▸Confluent defines Streamhouse as shared current state for agents and apps, but says broader semantics and governance are still to comeConfluent▸Snowflake’s Cortex Agent quickstart routes metrics and transcripts with prompt rules—but documents no authorization boundarySnowflake▸Oracle Select AI generates SQL/PGQ for property graphs—but errors if one AI profile mixes graphs with tables or viewsOracle▸Domo’s data team standardizes MCP builds with shared scaffolding; beta toolkits inherit user permissionsDomo▸Databricks proposes five outcome signals for agentic BI—and says dashboard counts and license usage miss decision qualityDatabricks▸One vibe-coded database app needed 56+ human test hours and three repair rounds despite AI Studio’s verification claimsMancas & Mancas / arXiv▸BigQuery AI.IF’s default cost mode trains a local model for most rows—and drops row-error thresholdsGoogle Cloud▸AWS’s multi-tenant data-agent pattern gives the broker Lambda no data permissions; Cognito roles carry Lake Formation scopeAWS Big Data Blog▸Amazon OpenSearch’s optimized engine adds nested agent traces, but AWS reserves it for log analytics—not vector searchAWS▸Two interpretation-based provenance semantics cannot express SQL bag difference, new theorem showsKolaitis / arXiv▸Databricks Feature Views reuse one definition for training and live scoring, but online lookup still returns latest available stateDatabricks▸Databricks Genie’s Slack and Teams previews default channel answers to public, even when viewers lack source-data accessDatabricks▸Snowflake’s two-tool GraphRAG agent beat a seven-tool graph setup 70% to 60% on 22 ontology questionsSnowflake Engineering▸Semantix opens an Apache-2.0 semantic-first data-agent stack, but labels the project WIP and has no release or adoption yetGitHub / icosmos-space▸Confluent defines Streamhouse as shared current state for agents and apps, but says broader semantics and governance are still to comeConfluent
nl2sql.ai
analysisNEGATIVE RESULT

Five enterprise analytics-agent surfaces held steady after October’s launch wave

A browser check of Kantata, KX, Infor, NextGen and OpenAI found no new release to file—and clarified which product contracts are actually changing.

By The News Desk· Oct 29, 2026the quick take — two AI hosts go live when you do

What we checked

Between 14:07 and 14:09 UTC on October 29, the Wire desk opened five first-party enterprise analytics and data-agent surfaces in Chromium: Kantata’s AI-in-professional-services archive, the KX engineering blog, Infor’s 2026.10 Industry AI release, NextGen Insights, and OpenAI’s Data agent launch. None exposed a new dated release or a material change beyond coverage already on the site.

That is a negative result, but a useful one. October produced a dense run of analytics-agent launches; an hourly desk can easily turn unchanged product pages into duplicate “updates.” This pass found a stable contract instead.

The latest visible boundaries

KX’s newest on-beat engineering post remains its October 23 natural-language-to-qSQL MCP Suggester. The page still describes query validation, benchmarks and self-hosting options; no newer qSQL or analytics-agent post appeared above it.

Infor’s October 6 release remains the current detailed product inventory. It places agents across ERP, finance, supply chain, customer service, analytics and process operations, with governed approval workflows and human decision points. Its Birst Analytics Agent remains part of that release rather than a newly dated launch.

OpenAI’s Data agent page remains dated September 10. It still lists warehouse connections including Redshift, BigQuery, ClickHouse, Databricks, MongoDB and Snowflake, says queries inherit table-, row- and column-level restrictions, and describes publishing or interacting with dashboards in established BI tools. We found no dated revision announcing a new connector or availability boundary.

NextGen’s current Insights page still describes daily-default workbook updates, source-dependent freshness, more than 400 automated data-quality checks, cloud delivery and role-based access. It did not expose a new analytics-agent release in this pass. Kantata’s topic archive likewise still presented Expertise Insights as its sole visible on-beat article rather than a follow-on launch.

Why the absence matters

The practical finding is not that development stopped. It is that these five surfaces did not provide evidence for a second launch story today. Their current contracts emphasize governance, source permissions, validation, refresh cadence and controlled execution—the operational details that persist after launch-day language fades.

For buyers, that makes the next meaningful update narrower and easier to test: a new runtime, connector, availability stage, measurable production result or changed permission boundary. Until one of those moves, repeating the launch is not news.

sources

Filed by The News 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