Databricks releases, every cloud
- Genie Code now supports auto-approve for tool actions
Approves tool actions without prompts, using an AI classifier to block risky ones.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Power BI connections will transition to ADBC Coming soon
Replaces ODBC, requires manual update for existing connections.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Sample Data Explorer is generally available
Lets you ask questions about Unity Catalog tables using natural language, returning SQL queries.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Workspace skills for Genie Code are now available
Workspace admins can create shared skills for machine learning pipelines and domain-specific processes.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Databricks Assistant is now Genie Code
Adds autonomous multi-step data tasks, replaces Databricks Assistant.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Connect Databricks Assistant to MCP servers
Connects to external tools and data sources through MCP servers, requiring permission to use added servers.
- Run the change, do not just read it. Hands-on labs in your own Databricks workspace, graded when you submit. Browse labs
- Partner-powered AI features are now supported in the Canada, Brazil, and United Kingdom Azure Geographies
Uses models hosted in the same Azure Geography as the workspace, requires cross-geo processing for some features.
- Create skills for Databricks Assistant
Extends Databricks Assistant with domain-specific tasks, following the open Agent Skills standard.
- Databricks Assistant Agent mode is now in Public Preview
Automates multiple steps from a single prompt, using Azure OpenAI or Anthropic.
- Add Azure Databricks Genie MCP server to Azure AI Foundry (Public Preview)
Enables AI agents to connect to Genie Agents and query data. Requires Azure AI Foundry setup.
- Connect Genie Agents to Microsoft Copilot Studio (Public Preview)
Requires Managed MCP Servers preview enabled.
- Databricks Assistant Agent mode can now use models served through Anthropic on Databricks
Requires partner-powered AI features to be enabled. Uses endpoints hosted by Databricks.
- Databricks Connector for Google Sheets offers additional features (Public Preview)
Saves queries within a Google Sheet spreadsheet for easy data refresh and reuse.
- Notebook improvements
Cell execution minimap appears in right margin, supports up to 100MB notebooks.
- Databricks Assistant Agent mode: Data Science Agent is in Beta
Orchestrates multi-step workflows from a single prompt, building entire notebooks for tasks like EDA and machine learning.
- Interact with Azure Databricks jobs in a Power Automate flow (Public Preview)
Adds Azure Databricks job action to Power Automate flows. Requires adding the action to a flow.
- Databricks Assistant integrated with compute
Creates compute resources, pools, and policies, and answers questions about them. Available on some compute pages.
- Azure Databricks connector in Microsoft Power Platform is now GA
Replaces beta version, requires Azure Databricks account.
- Get this table by email. One Monday mail covering the week, filtered to the clouds and products you run. Weekly digest
- Databricks-hosted models for Assistant are now GA
Available on all cloud platforms at no extra cost.
- Databricks Assistant: User and workspace instructions now available
Custom instructions can be added by users or admins, applying to all Assistant experiences.
- Power BI Azure Databricks connector supports M2M OAuth
Replaces personal access tokens for service principals with Client credentials authentication.
- Edit mode in Assistant does multi-cell code refactoring and more
Performs reasoning and editing across multiple cells without manual intervention.
Headlines, dates and product areas are Databricks' own, from the release notes published for each cloud, and every item links to the note it came from. The one-line summaries are ours. Not a Databricks product and not affiliated with Databricks, Inc.