Databricks Launches Genie Code AI Agent to Automate Data Engineering and Analytics Work
The new tool is an extension of Genie, Databricks’ conversational interface that allows business users to query enterprise data using natural language.
Databricks has unveiled Genie Code, an autonomous AI agent designed to automate complex data engineering and data science tasks, marking a shift toward what the company calls “agentic data work.”
The new tool is an extension of Genie, Databricks’ conversational interface that allows business users to query enterprise data using natural language. Genie Code expands the system for technical teams, enabling it to perform tasks such as building data pipelines, debugging failures, shipping dashboards and maintaining production systems.
According to Databricks, internal testing showed Genie Code significantly improves AI performance on real-world data science tasks, increasing the success rate of leading coding agents from 32.1% to 77.1%.
“Software development has shifted from code-assistance to full agentic engineering in the past six months,” said Ali Ghodsi, co-founder and CEO of Databricks. “Genie Code brings this revolution to data teams. We're moving from a world where data professionals are assisted by AI to one where AI agents do the work, guided by humans. We are calling this Agentic Data Work. It will fundamentally change how enterprises make decisions.”
Unlike traditional coding assistants, Genie Code can plan multi-step solutions, write production-grade code and maintain deployed systems while keeping human operators in control of key decisions.
The platform is integrated with Unity Catalog, Databricks’ governance layer, enabling the AI agent to access enterprise context such as data lineage, usage patterns and compliance rules.
The system also continuously monitors data pipelines and machine learning models, identifying anomalies, debugging issues and optimizing resource usage automatically.
Alongside the launch, Databricks announced the acquisition of Quotient AI, a startup specialising in reinforcement learning and evaluation systems for AI agents. The technology will be integrated into Genie to enable continuous performance evaluation.
Early users say the tool can accelerate development workflows. “At SiriusXM, Genie Code supports everything from authoring notebooks and complex SQL to reasoning through table relationships and debugging pipelines,” said Bernie Graham, VP of Data Engineering at SiriusXM.
Last month, Databricks secured more than $7 billion in new investments as it reported strong growth and outlined plans to expand its AI-focused products.
