Agent Bricks Supervisor Agent is Now GA: Orchestrate Enterprise Agents

Enterprises are quickly ramping up agent development for financial analysis copilots, customer service assistants, and internal knowledge retrieval. But this rapid growth brings a new challenge: how to find and manage them all. Teams are left playing agent roulette, toggling between dozens of niche bots and trying to remember if the “Travel Policy” lives in the HR agent or Finance Agent. This cognitive load is slowing down productivity, causing teams to search around aimlessly, create agents that have already been built, or reference out-of-date information. Enterprises need a single entry point that can reason about intent, coordinate specialized agents, and act securely on a user’s behalf.

Agent Bricks Supervisor Agent, now Generally Available (GA), is a managed orchestration layer that lets you tie together agents and tools, fully governed by Unity Catalog. It uses a dynamic supervisor pattern to analyze the user’s question and orchestrate between Genie Spaces for structured data, Knowledge Assistant agents for unstructured data, and MCP servers for tools to answer complex questions and provide deep analysis. This lets teams own and iterate on the quality of their agents independently, and gives users a single place to get their work done.

Governance-by-Design: Secured by Unity Catalog

For IT and Security teams, agentic AI often operates outside enterprise security. Most tools require duplicating permissions or using broad service accounts, creating a compliance gap where the agent might access data the end-user is unauthorized to see.

Agent Bricks uses Unity Catalog as the control and governance layer for agents, along with your models, data, and tools. Supervisor Agent natively supports On-Behalf-Of (OBO) authentication, acting as a transparent proxy for the human user. Every data fetch or tool execution is validated against the user’s existing permissions in Unity Catalog: whether they can query a table, or they have access to a specific tool via the MCP Catalog. This ensures the agent stays in sync with your governance policies without additional work.

For Franklin Templeton, scaling AI means making regulated fund documentation usable without compromising compliance. Using Agent Bricks, with governance built in through Unity Catalog, the team combined public fund documents with performance data to power a governed fund analysis agent grounded in approved enterprise sources.

"Agent Bricks lets us scale reliable, compliant fund analysis. What would take days now takes seconds, and we trust that every insight is grounded in our data and business logic." — Colin Zimmerman, CFA, Lead Data Scientist, Franklin Templeton

Continuous Improvement Through Research-Backed Learning

A production-grade agent is never "finished"; it must evolve based on real-world performance. You need to evaluate its response, incorporate new information, and continuously improve for the agent to remain useful.

Supervisor Agent has a built-in quality loop with Agent Learning on Human Feedback (ALHF). Add questions and guidelines that the Supervisor can incorporate to improve its answers, how it routes between sub-agents, and provide context to the system. This makes collaboration with subject matter experts (SMEs) easier, too: for example, your marketing team can provide guidelines about brand and style for agent responses, and the Supervisor can learn from it directly. With a built-in MLflow experiment and integration, every interaction is tracked and measurable, allowing you to see and address gaps quickly.

Customers like Zapier have used Agent Learning on Human Feedback to quickly iterate and improve their agents. Zapier is using the Supervisor Agent to democratize access to data, and has leveraged ALHF to improve the Supervisor’s orchestration between different Genie spaces and tools.

“Agent Bricks Supervisor Agent gives us a structured way to coordinate multiple data intelligence endpoints in a single system. Instead of hard-coding routing logic, we can guide how the agent prioritizes Genie and governed data in Unity Catalog through clear instructions. That makes it much easier to build an internal ‘ask data’ experience that’s flexible and reliable as it evolves.” —  Alvaro Martin, Sr. Data Engineer, Zapier 

Use the Supervisor Agent Today

With General Availability, Supervisor Agent provides a managed foundation for orchestrating AI agents at enterprise scale. Teams can now route intent, govern access through Unity Catalog, and continuously improve agent quality, all from a single control plane.

Get started with Supervisor Agent today by creating your first agent and connecting it to your existing agents and tools. Explore the documentation to see how Supervisor Agent fits into your production workflows.

Build your first Supervisor Agent today →