We’re excited to introduce Agent mode in Genie areas. Our workforce has developed a strong agentic course of that iteratively plans, explores, and causes over your knowledge to reply your corporation questions. As a part of Databricks’ Week of Brokers, this weblog highlights one other method we’re altering how organizations work together with their knowledge utilizing agentic AI.
This expertise unlocks a way more actionable degree of information evaluation for everybody in your group. Now, anybody can get real-time insights into advanced enterprise questions like:
- Why did our churn charge spike in Q3?
- How can we optimize our marketing campaign spend?
- What income influence ought to I anticipate if these two provide strains are interrupted?
How Agent Mode Works
Once you ask a query in Agent mode, Genie doesn’t simply return a single question. It investigates the issue like an actual knowledge analyst: planning an strategy, testing hypotheses, and iterating towards an evidence.
For instance, think about a Genie area for buyer assist. You discover a spike in reopened instances in December 2025 and ask: “What’s contributing to the spike in reopened assist instances?”
Agent mode first confirms the spike, then explores doable contributors reminiscent of clients, merchandise, classes, or groups. It makes use of the enterprise context in your Genie area, together with Unity Catalog metadata and author-defined semantics, to concentrate on probably the most related potential contributing components.
Agent mode then evaluates these hypotheses by executing a number of queries towards the underlying knowledge. The semantics outlined in Genie’s information retailer train it tips on how to produce correct queries. We additionally made Agent mode’s work clear so customers can all the time confirm its accuracy.
Throughout its evaluation, Genie constantly displays on the outcomes of every question and decides what to discover subsequent. On this instance, after testing a number of potential drivers of the spike, the agent decides that it ought to additional examine if seasonal patterns are contributing to the spike. This iterative cycle of speculation technology, querying, and reflection permits Genie to discover knowledge extra totally and arrive at a well-supported rationalization.
After finishing its evaluation, Genie generates a report of its findings. Following this instance, the report first quantifies the rise in reopened instances after which identifies the first contributors—particularly an increase in bug-related instances and efficiency from the L2 regional workforce. To assist these conclusions, the report additionally contains visualizations and references to the underlying SQL for customers to evaluation.
Relying on the kind of query, Genie additionally gives actionable suggestions on what groups ought to concentrate on to enhance efficiency. Customers can then share these reviews instantly within the platform or obtain them as PDFs to simply distribute insights and collaborate.
Constructed for Questions of Any Complexity
Agent mode not solely unlocks superior enterprise investigations—it improves accuracy throughout all query sorts, from easy analytics to multi-step evaluation.
Even for simple questions, it takes small validation steps to make sure it understands the information earlier than responding. We’ve additionally tuned the agent to dynamically scale its reasoning to the complexity of the duty—transferring shortly for easy prompts, and spending extra time planning and evaluating for deeper investigations.
The result’s quicker solutions for on a regular basis questions and extra rigorous evaluation when tackling advanced issues.
Customers interacting with Genie inside AI/BI Dashboards may also benefit from this new expertise. Once you ask inquiries to Genie from a Dashboard, it leverages Agent mode by default.
Get Began At present
Workspace admins can now verify Agent mode is enabled within the Workspace Previews web page. As soon as enabled, merely activate the Agent toggle in your Genie areas and ask your corporation questions.
Agent mode is now out there, with far more to return together with API assist and unstructured doc evaluation. Give Agent mode a attempt at this time — we are able to’t wait to listen to what you suppose.