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
analysisRelease analysis

Tableau is closing the agentic-feature gap between cloud and self-managed deployments

Server 2026.3 restores a four-month major-release cycle, but companion Desktop and Bridge builds can have a much shorter maintenance window.

Tableau release trains compared: aligned major versions versus shorter maintenance builds.
AI-generated illustration
By The News Desk· Oct 14, 2026the quick take — two AI hosts go live when you do

Tableau is changing a deployment constraint that matters to enterprises adopting agentic analytics: beginning with Tableau Server 2026.3 in October, the self-managed product will again receive a major release every four months, aligned with Tableau Cloud and Tableau Desktop. The company says the goal is to reduce the delay before Server customers can adopt new capabilities, including its agentic features, and to simplify planning for organizations that run mixed deployments. Tableau

The important change is alignment, not just speed

A shared four-month cadence means Tableau’s three main delivery surfaces are meant to move through major versions together. For a team deciding whether an analytics agent can be deployed outside the vendor’s cloud, that alignment narrows a familiar gap: a capability may still arrive with product-specific requirements, but Server customers should no longer wait through an additional major-release cycle simply because their deployment is self-managed. Tableau

This does not mean feature parity is guaranteed. Tableau promises aligned release timing, not that every cloud capability will ship unchanged on Server. The practical test for each agentic feature remains its own availability matrix, identity model and data-access boundary. What changes is the planning baseline: mixed Cloud, Desktop and Server estates can now evaluate a new major version on the same cycle. Tableau

Maintenance policy still creates two classes of desktop build

The cadence note also draws an operational distinction that administrators could easily miss. Desktop versions aligned with a Tableau Server release retain the same 24-month maintenance-release support as that Server release. By contrast, Desktop and Tableau Bridge versions shipped only as companions to Tableau Cloud stop receiving maintenance releases after the next Cloud version, a four-month window. Tableau

That makes the Server-aligned Desktop build the more predictable choice for long-lived managed estates, while Cloud-companion builds may require faster turnover. Teams piloting agentic analytics should therefore track not only whether a feature exists, but which release train delivers the client and bridge components around it.

What practitioners should verify

For the October 2026.3 rollout, deployment owners should check three things before treating cadence alignment as deployability: whether the desired agentic capability is explicitly listed for Server, whether its authentication and governance behavior matches Cloud, and whether every required Desktop or Bridge component is on the 24-month Server-aligned support track. Tableau’s announcement makes new functionality reachable sooner; it does not remove the need for release-by-release compatibility review. Tableau

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