Skip to main content
Last updated on

Genie Code

note

Starting July 8, 2026 at 00:00 UTC, Genie Code is billed following a pay-as-you-go pricing model that includes a per-user free monthly allowance. Account administrators can manage budgets and cost controls for Genie. For more information about pricing, see Databricks pricing.

Genie One and Genie Agents usage by users is free through January 31, 2027. Service principals are excluded from the promotion, and their usage is billed.

Genie Code is the AI coding and data assistant for developers and technical practitioners in the Databricks workspace. It generates and runs code, builds pipelines and AI/BI dashboards, debugs errors, and works directly with Unity Catalog tables, columns, and lineage to accelerate multi-step data work. It runs in notebooks, the SQL editor, the Lakeflow Pipelines Editor, AI/BI dashboards, and MLflow, and chats persist as you navigate between pages.

Genie Code is an autonomous agent. It plans solutions, retrieves relevant context, runs code, uses cell outputs to improve results, and fixes errors automatically. By default, an AI classifier approves the tool actions that carry out your request and is designed to block actions that go beyond it. To approve each action yourself, see Approve tool actions. If you want a direct conversational response without autonomous task execution, say so in your prompt, for example, "Just explain this to me, don't run any code."

Genie Code is governed by your Unity Catalog permissions, so it can only access data and perform operations that you have permissions for. Fair usage limits prevent abuse but do not affect most users.

To complete tasks, Genie Code sends your prompt and relevant context to the model, including table and column names, descriptions, the code you are working with, data samples from tables, and cell outputs, all within your Unity Catalog permissions. For details, see Data sent to the models.

Genie Code is part of the Genie family of AI experiences. Business users who want a simplified chat interface to ask data questions, explore dashboards, and run apps should use Genie One. Data teams configuring trusted data, metrics, and business rules for domain-specific environments should see Genie Agents. For privacy, trust, and security details, see Databricks AI assistive features trust and safety.

Requirements​

To use Genie Code's agentic capabilities, your workspace needs the following:

If partner-powered AI features are disabled, Genie Code is still available but without its agentic capabilities, using a Databricks-hosted model.

tip

Genie Code has a full page command center experience, where the active chat is shown prominently, surfacing notebooks and files alongside it as tabs when needed. Start work directly from Genie Code rather than from an asset like a notebook, run multiple chats in parallel, and personalize Genie Code with skills, instructions, and MCP servers. See Full page Genie Code.

Demo video​

See Genie Code in action in this demo video.

Explore Genie Code​

    • Navigate Genie Code
    • Open Genie Code and work in the chat pane, the full page command center, settings, and chats.
    • Features and capabilities
    • See how Genie Code helps with code, answers questions from documentation, and works across notebooks, pipelines, dashboards, and MLflow.

Customize and improve Genie Code​

Geo availability of Genie Code features​

Genie Code is a Designated Service that uses Geos to manage data residency when processing customer content. To learn more about the availability of Genie Code features in different geographic areas, see Databricks Designated Services.

tip

If you can't enable Genie Code, you might need to disable Enforce data processing within workspace Geography for AI features. See Enable cross-Geo processing.

On this page