← All updates Databricks Update One-Pager Light version
databricks Platform · Updated Apr 24, 2026

Manage Supervisor Agent programmatically with the Databricks SDK (Beta)

You can now use the Databricks SDK for Python to create and manage Supervisor Agent and their tools.

Beta Open docs ↗release note ↗
What it does

You can now use the Databricks SDK for Python to create and manage Supervisor Agent and their tools. This page describes how to use Supervisor Agent to create a multi agent supervisor system that orchestrates AI agents and tools to work together on complex tasks. You can improve their coordination based on natural language feedback from your subject matter experts.

Why it matters

You can improve their coordination based on natural language feedback from your subject matter experts.

Key capabilities
Serverless compute available (enabled by
Serverless compute available (enabled by default in workspaces with Unity Catalog in a supported region).
Unity Catalog enabled. See Enable
Unity Catalog enabled. See Enable a workspace for Unity Catalog.
Access to Model Serving
Access to Model Serving.
Access to a serverless usage
Access to a serverless usage policy with a nonzero budget. A workspace in one of the supported regions. You must have agents or…
Recommended use cases
Provide market analysisusage data.
Architecture
Databricks Platform → Platform
In short

You can now use the Databricks SDK for Python to create and manage Supervisor Agent and their tools. This page describes how to use Supervisor Agent to create a multi agent supervisor system that orchestrates AI agents and tools to work together on complex…

Read the full documentation ↗
Key takeaway
You can now use the Databricks SDK for Python to create and manage Supervisor Agent and their tools.
2026-04-24-manage-supervisor-agent-programmatically-with-the-databricks-sdk-beta Generated by the Databricks Updates Agent · browse all updates