Databricks Unity Gateway CLI streamlines coding agent deployment and governance
Databricks has introduced the Unity Gateway CLI to enable centralized deployment and management of coding agents at scale. This new tool allows admins to configure approved models, tools, and spending policies from a single interface, ensuring governance and cost-efficiency. Developers can access any approved agent with a single command, automatically applying organizational settings. It addresses the challenge of rapidly evolving AI models by simplifying updates and providing features like Smart Routing and tracing for spend optimization.
- →Centralized configuration for coding agents
- →Simplified developer access to approved coding agents
- →Dynamic management of models, tools, and skills
- →Smart Routing optimizes model cost-performance
- →Budget-aware defaults and AI spend tracing
Features (5) ›
- Centralized configuration for coding agents
The Unity Gateway CLI allows admins to manage approved models, tools, skills, Smart Routing, and spending policies from a single interface within Unity Gateway. This streamlines the deployment of coding agents across organizations.
- Simplified developer access to approved coding agents
Developers can connect to any approved coding agent with a single command (e.g., ug claude), with the CLI handling authentication and applying published organizational settings. This enables developers to switch between agents easily without individual configuration.
- Dynamic management of models, tools, and skills
Admins can update default models and share approved MCP tools and skills across all supported agents simultaneously, ensuring developers always use the latest, most efficient options. This helps keep pace with the rapidly evolving AI model landscape.
- Smart Routing optimizes model cost-performance
Unity Gateway's Smart Routing feature centrally enables less expensive models for simpler tasks and more capable ones for complex work. This allows developers to stay in their preferred agents while the system automatically matches model cost to task complexity.
- Budget-aware defaults and AI spend tracing
The platform supports budget-aware defaults for agents and models, helping teams manage spending. Centralized tracing captures agent activity, enabling identification and correction of wasted AI spend and lost productivity through detailed analysis.
https://www.databricks.com/blog/deploy-and-manage-coding-agents-scale-unity-gateway-cli
Related releases
- Databricks SDK for Python v0.143.0 Adds ML Feature Fields, Fixes Logging Databricks Python SDK Releases ·
- Horizontal scaling for Databricks Apps is now generally available Databricks Release Notes ·
- Genie Code Builds Intelligent Document Processing Pipelines Databricks Release Notes ·
- Top 5 Databricks System Table Queries for Cost Management Databricks Blog ·
- DeepSeek V4 Pro (0813) Model Scheduled for Retirement Databricks Release Notes ·
- S&P Global Energy details conversational AI for structured data with Databricks Genie Agents Databricks Blog ·