Releasesby IbisIn Conversational Analytics, the default question mode is now Fast rather than Thinking
UpdateyesterdayUnverifiedAdded Oct 10, 2026
In Conversational Analytics, the default question mode is now Fast rather than Thinking . Fast mode is intended for answering quickly, and it directly maps your query to underlying LookML definitions without generating reasoning steps.
More Looker releases
Every Looker releaseBeginning October 5, 2026, the following features will be automatically enabled for Looker (original)...
Beginning October 5, 2026, the following features will be automatically enabled for Looker (original) instances running Looker 26.18. Feature enablement for Looker (Google Cloud core) will be announced separately.
Looker now includes built-in support for the Dremio 26.0+ (Arrow Flight SQL) dialect
Looker now includes built-in support for the Dremio 26.0+ (Arrow Flight SQL) dialect. The Dremio 26.0+ (Arrow Flight SQL) uses the bundled Apache Arrow Flight SQL JDBC driver, so that you don't have to install unpackaged custom JDBC driver JAR files. See the Dremio documentation page for more information.
The AI-Assisted Quick Starts feature, called Starter questions in the new Explore experience, is now...
The AI-Assisted Quick Starts feature, called Starter questions in the new Explore experience, is now generally available.
The new Diagnose & Repair tool evaluates your LookML project repository across eight diagnostic test checks...
The new Diagnose & Repair tool evaluates your LookML project repository across eight diagnostic test checks in either your personal development environment or the shared production environment.
Looker Continuous Integration (CI) now includes the Style Validator , which enforces LookML coding standards...
Looker Continuous Integration (CI) now includes the Style Validator , which enforces LookML coding standards, naming conventions, and structural best practices across your LookML project.
Now available in preview , Conversational Analytics agentic workflows support scheduled agentic workflows in...
Now available in preview , Conversational Analytics agentic workflows support scheduled agentic workflows in addition to triggered agentic workflows . You can use scheduled agentic workflows to schedule recurring deliveries of AI-generated insights summaries, data tables, visualizations, and PDF reports to email or Slack by using natural language.
Now available in preview, Looker Data Apps are freeform canvas dashboards that are built by local AI coding...
Now available in preview, Looker Data Apps are freeform canvas dashboards that are built by local AI coding agents, such as Gemini CLI, Claude Code, or Cursor, from natural-language prompts.
The Modern User Interface preview feature toggle now defaults to ON
The Modern User Interface preview feature toggle now defaults to ON .
Also shipped on Oct 9, 2026
Google Cloud in October 2026Google Workspace connector is available in Beta
The managed Google Workspace connector is now available in Beta in Databricks Lakeflow Connect. Use the connector to ingest audit activity from Google Workspace applications and services into Databricks. The connector uses OAuth user authorization and supports incremental ingestion.
Agentic Marketplace Discovery (Public preview)
Agentic Marketplace Discovery is now available in public preview. On the public Snowflake Marketplace Discover page in Snowsight, you can switch between Agentic discovery and Marketplace search . Describe what you need to CoCo to find and compare matching listings, or search for providers and listings directly.
All AI Gateway models with prepaid credits, backend features with your coding agent, and new ways to send feedback release - Oct 09, 2026
All AI Gateway models now available with prepaid credits. You don't need to request access to frontier models in the Neon AI Gateway anymore. If you're on a pai...
Use request tags in Unity Gateway service policies (Beta)
Custom service policies in Unity Gateway can now check caller-supplied request tags, such as requiring a tag before a model request or MCP tool call proceeds. See Request tags .
Use OpenJev as the evaluator for LLM-as-a-judge service policies (Beta)
You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM-as-a-judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator. See Use OpenJev as the evaluator .
Code execution in Genie One (Public Preview)
Genie One can now run code in a secure, isolated sandbox to take on work that goes beyond SQL, such as more advanced analyses. Code runs on your behalf using your existing permissions, so Unity Catalog governance and data access controls continue to apply. See Code execution in Genie One .