live wire
▸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▸Graph-repair retrieval cut F1 by 0.126 on one suite; a learned router used fewer tokens than always-on retrieval in all sixLin et al. / arXiv▸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▸Graph-repair retrieval cut F1 by 0.126 on one suite; a learned router used fewer tokens than always-on retrieval in all sixLin et al. / arXiv
nl2sql.ai
guideOperations guide

ThoughtSpot lets teams build their own AI analysts—but the connector boundary is where governance lives

Cloud 26.10 makes custom Spotter Analysts generally available while adding user- and group-level connector sharing. Those controls solve different problems, and teams should test both.

By The News Desk· Nov 6, 2026the quick take — two AI hosts go live when you do

ThoughtSpot Cloud 26.10 turns “build an analyst” into a chat workflow. A user describes the analyst they want, and Spotter translates that request into agent instructions. The same release makes Spotter Analysts generally available, according to the October release notes.

That changes the bottleneck. Creating a tailored analytics agent is no longer the hard part; deciding which models and external tools it may use is.

The analyst and the connector are separate controls

ThoughtSpot’s release notes describe a connector marketplace with more than 100 third-party integrations. Everyone can browse the catalog, but adding and configuring a connector requires an administrator or a user with the CanManageSpotter privilege. Administrators can also add an MCP-compliant server manually when it is not listed in the catalog.

The same release adds a narrower sharing model. Previously, a connector enabled by an administrator was shared with all users across all Orgs. In 26.10, a connector added in the primary Org can be shared with selected users and groups and is hidden from everyone else by default. Connectors can still only be added or edited from the primary Org.

Those are distinct governance layers:

  • Analyst instructions define the job: which data models, business context and behavior the agent should use.
  • Connector configuration defines the available external capability.
  • Connector sharing defines who can discover and invoke that capability.

A carefully scoped analyst can still be overpowered if its assigned users can reach a broadly shared connector. Conversely, a correctly restricted connector does not ensure that an analyst’s instructions select the right model or interpret the business question correctly.

What to test before rollout

Start with a matrix, not a demo. For each custom analyst, record its owners, models, instructions, connectors and intended user groups. Then test with identities from every permitted and denied group.

Verify at least four cases: an authorized user can invoke the connector; an unauthorized user cannot discover it; a copied or modified analyst does not acquire extra connector access; and removing a user from a group removes the effective capability. Because connector creation and editing remain centralized in the primary Org, include that administrative path in change review.

Status also matters. Spotter Analysts and user/group connector sharing are GA in the release notes, while Databricks Metric Views integration is Early Access and must be enabled by an administrator. Do not treat all components visible in the same release as having the same support or rollout state.

The practical lesson is simple: custom analytics agents should be reviewed as a bundle of instructions, semantic models, connectors and identities. Reviewing only the prompt leaves the most consequential permission boundary out of frame.

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