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
analysisSAP TechEd

SAP is building an ontology layer for Joule—and wiring Databricks Genie into it

The TechEd roadmap joins ontology authoring, federated Iceberg access and governed agent interoperability, but most of the data-agent pieces are still promises rather than GA features.

By The News Desk· Oct 28, 2026the quick take — two AI hosts go live when you do

SAP’s latest TechEd announcement puts a clearer architecture behind its “autonomous enterprise” pitch: an ontology layer to describe business data, a federated query layer to reach it, and governed gateways through which agents can act on it. The most relevant addition for analytics teams is a planned integration between Joule and Databricks Genie inside SAP Business Data Cloud. SAP announced the package on October 27.

The ontology becomes the grounding contract

SAP says Business Data Cloud Ontology Manager will provide an AI-native authoring experience for ontologies spanning SAP and third-party data. The company’s stated goal is to encode how records from different systems relate, giving agents a shared business model for reasoning and decisions. SAP Knowledge Graph remains the context layer for SAP data, while the new authoring surface is intended to extend that model across customer-specific sources. The launch describes both components but does not provide availability dates or accuracy measurements.

That distinction matters for natural-language analytics. A model can generate syntactically valid SQL and still choose the wrong measure, join path or business definition. SAP is positioning the ontology—not the prompt—as the place where those relationships are made explicit.

Genie reaches SAP through a broader data plane

The announcement also expands SAP’s Databricks partnership. SAP says SAP Databricks will bring Lakeflow, Agent Bricks, Unity Gateway and Lakebase into Business Data Cloud, alongside a new Application Data Foundation and an integration between Joule and Genie. Separately, a Dremio partnership is set to add native Apache Iceberg and Apache Polaris support plus federated querying without moving or copying data. SAP presents these as parts of one Business Data Cloud foundation.

For practitioners, the deployment question is therefore broader than “Can Joule ask Genie a question?” Teams will need to decide which semantic definitions live in SAP’s ontology, which governance boundary Unity Gateway enforces, and how identities and policies survive a federated query across SAP and non-SAP systems. SAP’s release does not yet document that end-to-end authorization path.

Governance is expanding with the data surface

SAP says third-party agents will be able to invoke Joule Agents through a governed agent gateway, while a new Enterprise AI Gateway is intended to centralize authentication, policy enforcement, routing, monitoring, usage tracking and auditing. Joule Studio is also gaining observability for agent behavior, model usage and spend. Those controls were announced alongside MCP and A2A interoperability.

The practical takeaway is promising but cautious: SAP has named the layers an enterprise analytics agent needs—semantics, data access, interoperability and audit—but has not yet published availability, pricing, supported query paths or evaluation results for the combined Joule-Genie workflow. Teams should treat this as an architectural roadmap and demand those contracts before planning production migration.

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