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
newsProduction data agents

The UN turns official statistics into a natural-language and MCP data service

The UN System Data Commons joins official datasets behind one searchable graph—and gives AI agents a route to the same governed source material.

Before-and-after view of siloed data turning into a unified governed graph.
AI-generated illustration
By The News Desk· Sep 17, 2026the quick take — two AI hosts go live when you do

The United Nations system has launched a new version of data.un.org built for both human questions and machine agents. The UN System Data Commons presents official statistics through natural-language search, interactive exploration and an open-source Data Commons foundation. Google’s launch post says the platform replaces months of manual reconciliation across separately formatted datasets with one interconnected, AI-ready knowledge graph.

The interface is conversational; the product is a shared data layer

A user can ask questions such as how rural clean-water access relates to school attendance and receive relevant data plus visualizations. The live portal also supports structured browsing by geography and themes including health and education. Google describes the service as a unified environment that aligns metrics, timelines and geographic boundaries across previously siloed datasets.

That distinction matters for practitioners. This is not a chatbot laid over one warehouse table. The difficult work is upstream: aligning metrics, timelines and geographic boundaries from multiple institutions so that a natural-language layer has consistent objects to retrieve. Google says UN statisticians and technical experts validate every dataset made available through the system.

MCP extends the same source to research agents

The launch also exposes the data for agentic workflows through open standards including the Model Context Protocol. According to Google, agents can fetch authoritative figures from the Commons, connect information across domains, and assemble charts, infographics or draft reports. Google explicitly cautions users to inspect underlying sources before citing critical figures, even when the retrieved data is grounded and verified.

For data-agent teams, that combination is more instructive than the search box alone. The platform pairs a public conversational interface with a reusable machine-access layer rather than forcing every assistant to scrape pages or rebuild statistical mappings. It also keeps provenance visible: the goal is to accelerate research assembly, not erase the review step.

The graph is still expanding

Google says the UN system plans to add more datasets over the coming year and aims to include 80% of UN system statistical datasets by 2027. The launch was supported by Google.org through the UN Foundation, while the underlying Data Commons technology is open source.

The immediate lesson for enterprise analytics teams is architectural: reliable natural-language access begins with a shared, governed representation of the data. MCP can distribute that context to multiple assistants, but it does not replace semantic alignment, provenance or human verification.

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