Releasesby GlyphDashboard enhancements and bug fixes
- Import from Power BI and Tableau : Importing reports and data models from Power BI and Tableau with Genie Code ( /importBI ) is now generally available. See Import BI files using Genie Code . Larger Excel downloads : You can now download up to 1 million rows from a dashboard widget to Excel ( .xlsx ), up from 100,000. See Download results .
Also shipped Aug 20, 2026Databricks in August 2026 →
BigQuery adds ML.TREND, ML.SEASONALITY and ML.DETECT_CHANGE_POINTS in preview
New table-valued functions in the query editor and conversational analytics identify trends, repeating seasonal patterns and structural change points in time series data.
BigQuery Graph core processing limited to Enterprise editions from April 26, 2027
Standard edition and on-demand billing support for BigQuery Graph core graph processing is deprecated, with processing restricted to Enterprise and Enterprise Plus from April 26, 2027. Graph measures remain available except in Standard edition.
The run_bq_command tool exposes the bq command-line tool within the Cloud CLI remote MCP server
The run_bq_command tool exposes the bq command-line tool within the Cloud CLI remote MCP server. AI agents can now execute advanced BigQuery operations, such as job scheduling, job management, and reservation management, through a managed MCP endpoint. For more information, see Use the Cloud CLI remote MCP server . This feature is in Preview .
AI_EXTRACT and AI_PARSE_DOCUMENT support for client-side encrypted stages and network-restricted accounts (General availability)
AI_EXTRACT and AI_PARSE_DOCUMENT now support documents stored on stages that use client-side or server-side encryption, including in accounts that use PrivateLink or other network policies that restrict public network access to stages. For more information, see the following topics:
Cortex Agent code execution tool (Preview)
The Cortex Agent code execution tool is now in public preview. When you enable the tool on an agent, the agent can generate and run Python in a secure, isolated sandbox to process data, perform calculations, and produce visualizations.
Gemini Enterprise and Gemini Notebook Enterprise: Autocomplete for sharing notebooks and agents with Okta
If you use Okta as your external identity provider (IdP) with Workforce Identity Federation, you can configure System for Cross-domain Identity Management (SCIM). Configuring SCIM enables autocomplete when sharing Gemini Notebook Enterprise notebooks and when sharing agents in Gemini Enterprise.
More from AI/BI and GenieEvery AI/BI and Genie release →
Genie One enhancements
- Scheduled task consistency : Scheduled tasks now look up past runs to keep run-to-run outputs consistent. See Scheduled tasks . Export documents to PDF : You can now export Genie One documents to PDF. See Documents in Genie One .
Choose an effort level in Genie Code
You can now set the effort level for Genie Code to balance response quality and cost. Auto (default) gives you the highest quality responses. For simpler tasks, select Low to use a faster, lower-cost model. See Select a level of effort .
Connect to the Databricks Genie app in Microsoft Teams with your workspace URL (Public Preview)
When you sign in to the Databricks Genie app in Microsoft Teams, you can now enter your workspace URL instead of a server hostname to connect to your Databricks account. See Databricks Genie app in Microsoft Teams .
The Genie One desktop app for macOS is in Beta
The Genie One desktop app is now in Beta . The native macOS app opens Genie One on your desktop instead of in a browser tab, so business users can chat with data in natural language, work with their threads and documents, and use Genie Agents without a browser. See Use Genie One on desktop .
Genie Agents enhancements
- Chat mode in Genie One : You can now submit prompts to a Genie Agent in Chat mode from Genie One. Cancel Agent mode responses through the API : You can now cancel in-progress Agent mode responses through the API. See the Cancel Genie agent response API .
Genie Code supports file uploads
You can now upload files to Genie Code to use as context for the current chat. See Attach files .
Genie Code is now available as a Lakeflow Jobs task (Beta)
You can now run prompts with Genie Code as a task in a Lakeflow Job. Genie Code runs your prompt autonomously. It can read upstream task outputs and call tools as needed. The task returns a link to the resulting Genie Code conversation with its response. See Genie Code task for jobs .
Genie Code for AI Runtime (Public Preview)
Use Genie Code to develop and troubleshoot deep learning workloads in notebooks connected to AI Runtime. Now in Public Preview , it generates distributed training code, resolves environment and dependency issues, and debugs GPU and distributed workload failures. See Use Genie Code with AI Runtime .