All videos
0:00 / 0:00
ai

Building Agents on Databricks with Custom Apps and Omnigent

Databricks7 August 2026Watch on YouTube

Part of series

Ep. 7 · Omnigent: AI Agent Orkestratie

Databricks introduceert Omnigent, het open-source meta-framework dat meerdere AI-agenten combineert in één gecontroleerde, interoperabele workflow.

View the series

What you'll learn

  • Learn how to build agentic AI agents on Databricks' Agent Bricks platform with MCP server integration and the OpenAI agents SDK
  • See a practical example of a store operations agent for a bubble tea company that analyzes training hours and operational workflows
  • Discover intelligent model routing on Databricks to automatically select the best model for different tasks
  • Use MLflow tracing to track and analyze agent interactions in detail for better optimization and insights
  • Apply platform governance features in the Unity AI Gateway to deploy agents safely and in a controlled manner

Frequently asked questions

What is Agent Bricks and how does it work with Omnigent?
Agent Bricks is Databricks' platform for building agents. In the demo, it is used with Omnigent to create a store operations agent that integrates MCP servers to analyze training hours and workflows for a bubble tea company.
What are the benefits of intelligent model routing in this agentic setup?
Intelligent model routing automatically selects the most suitable model for specific tasks. This allows you to efficiently use different models based on the nature of the problem the agent needs to solve.
How does MLflow tracing help monitor agent performance?
MLflow tracing records and visualizes all agent interactions in detail. This enables you to analyze how your agent works, identify bottlenecks, and implement optimizations.
What are governance features and why are they important for agentic AI deployment?
Governance features in the Unity AI Gateway provide security mechanisms and controls for safely deploying agents in production. They help manage risks and ensure compliance.

Topics

agentsdatabricksgenerative aimlflowagentic platforms

Sources

What is known about this topic outside the broadcast, and where it says so.

Description from the channel

Join Databricks' Amber Roberts, our Staff. TME for GenAI, for a new demo featuring the latest agentic capabilities on Agent Bricks. The video demonstrates building a store operations agent using Agent Bricks and Omnigent alongside the OpenAI agents SDK. The custom agent integrates various MCP servers to analyze training hours and operational workflows for a bubble tea company. Additionally, it highlights platform capabilities such as intelligent model routing, MLflow trace tracking, automated weekly reporting, and governance features in the Unity AI Gateway.