Databricks’ second-generation Genie adds autonomous workflows, enterprise search and expanded business context tools, with governance controls for agent actions. The new always-on capabilities, Genie Search and Ontology Manager will enter preview and beta programs soon.
Databricks has announced the second generation of Genie, introducing an always-on autonomous agent designed to manage enterprise tasks, coordinate subagents and seek human input when decisions are required.
The new capabilities will allow employees to assign goals and boundaries, with Genie tracking progress, following up on missing inputs and highlighting work requiring attention. The announcement also includes Genie Search, expanded business context management and additional integrations with enterprise applications.
Genie and Genie Ontology are generally available. The new always-on Genie, Genie Search and Ontology Manager are coming soon to preview and beta programs.
Autonomous workflows with governance controls
The new autonomous mode will run in the background using its own compute. Intended uses range from monitoring email and preparing for meetings to tracking quarterly forecasts, customer usage patterns and revenue trends.
Genie will delegate tasks to multiple subagents for parallel execution. A priority inbox will highlight items requiring attention, while email alerts will notify users when they are away. Updates relating to an existing alert will remain in the same email thread.
According to Databricks, actions will remain subject to Unity Catalog permissions and Unity Gateway approval rules and budgets, with auditability across agent activity.
“Genie has made me a 10x more productive CEO, and now it doesn't wait for me to ask,” said Ali Ghodsi, Co-founder and CEO of Databricks. “Every day, Genie keeps up with my inbox, preps me for meetings, and runs in the background, coming back only when it needs a decision. It can do that because it knows how our company works: what we mean by revenue, which numbers are official, and who can see what. That's the power of horizontal context, and Genie delivers it.”
Enterprise search grounded in business context
Genie’s actions are grounded in Genie Ontology, which captures business definitions, metrics, people and processes, and updates that context as organisations change.
Genie Search will provide a governed way for people and agents to find information across lakehouse data and documents, tickets and chats in business applications. It will use the ontology to interpret information within business context, respect existing permissions and provide sources users can inspect.
Databricks said it now offers more than 100 connectors supporting data ingestion, in-place indexing and live application queries through Model Context Protocol (MCP). Supported tools include Google Drive, Jira and Confluence.
The company said agents will be able to search structured and unstructured information across applications in one operation, potentially reducing tool calls and token consumption. Genie MCP will also allow other AI tools and agents to access Genie Ontology and Genie Search.
Expanded context tools and application access
The new Ontology Manager will help teams manage and govern business context, including recommendations identifying frequently asked concepts that need refinement. Additional sources will bring in business logic from external business intelligence tools and organisational reporting relationships.
Genie will also generate dynamic slides, dashboards and interactive reports grounded in governed data. Expanded Genie Agents capabilities cover PDFs, contracts and slides stored in Unity Catalog volumes alongside governed tables, without a separate vector index.
New MCP connectors include Atlassian, Google Drive and GitHub. OpenSharing for Genie Agents is intended to support collaboration with partners without exposing underlying data. Access options also span browsers, mobile, email, and collaboration and AI tools.
“Teams make their best decisions when trusted context shows up in the flow of work. With Genie Agents now connected to Slack, sales, finance, and operations teams can go from question to action without leaving the conversation. We’re thrilled to work alongside Databricks to bring governed, reliable insights to where the work happens,” said Jaime DeLanghe, Chief Product Officer, Slack.
Customers describe analytics and advertising use cases
“AI is only as good as the definitions behind it, so we built our Genie Agents on agreed, governed definitions, and now every answer matches. We expanded self-service analytics by putting plain-language access to our data in the hands of teams across the business, not just analysts, so people can act on numbers they trust,” said Marlissa Wong, Director, Data Engineering, Headspace.
“With Genie constantly analyzing performance signals, we’ve improved programmatic ad ROI and reduced the time to identify ad winners on Meta by 75%. Unity Gateway gives us the flexibility to use the best model for each job without managing separate integrations,” said Alan Khalil, Associate Director, Data Science and Engineering, HelloFresh.
