We’re excited to introduce Agent mode in Genie areas. Our crew has developed a strong agentic course of that iteratively plans, explores, and causes over your knowledge to reply what you are promoting questions. As a part of Databricks’ Week of Brokers, this weblog highlights one other approach 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 fee spike in Q3?
- How can we optimize our marketing campaign spend?
- What income influence ought to I anticipate if these two provide traces are interrupted?
How Agent Mode Works
While 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 method, testing hypotheses, and iterating towards a proof.
For instance, think about a Genie house 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 attainable contributors corresponding to prospects, merchandise, classes, or groups. It makes use of the enterprise context in your Genie house, together with Unity Catalog metadata and author-defined semantics, to give attention to essentially the most related potential contributing elements.
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 the right way to produce correct queries. We additionally made Agent mode’s work clear so customers can at all times 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 completely 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 crew. To assist these conclusions, the report additionally consists of visualizations and references to the underlying SQL for customers to evaluate.
Relying on the kind of query, Genie additionally supplies actionable suggestions on what groups ought to give attention to to enhance efficiency. Customers can then share these stories immediately 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—shifting rapidly for easy prompts, and spending extra time planning and evaluating for deeper investigations.
The result’s sooner solutions for on a regular basis questions and extra rigorous evaluation when tackling advanced issues.
Customers interacting with Genie inside AI/BI Dashboards can even make the most of this new expertise. While you ask inquiries to Genie from a Dashboard, it leverages Agent mode by default.
Get Began Right now
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 what you are promoting questions.
Agent mode is now obtainable, with way more to come back together with API assist and unstructured doc evaluation. Give Agent mode a attempt at the moment — we are able to’t wait to listen to what you assume.
