Orchestration modes determine how Surfaces route user requests to Capabilities.
One Capability handles all incoming requests. The Surface acts as a direct channel to a single Flow or Agent.
How it works: All requests are routed to the selected Capability. This is the default mode and works well when your Product has one Capability or when each Surface is dedicated to a single purpose.
Use when:
An AI model reads each incoming request and routes it to the most appropriate Capability. Users do not need to know which Capability to call.
How it works: A router model evaluates each request and selects the best Capability based on the request content and the Capability descriptions. You can choose the router model and optionally add a custom routing prompt.
Example (chat Surface): User types “Where’s my order?” The router recognizes this as an order status query and routes to the order lookup Agent, not the FAQ Flow.
Use when:
A2A Surfaces have their own orchestration model:
Set orchestration mode when creating or editing a Surface:
Default and recommended modes vary by Surface:
Chat Surfaces: Single Orchestrator is the default. Switch to Multi-Capability Router when you want the Product to route each message to the best Capability among several options.
A2A Surfaces: Delegate is the default. Use Managed mode when you want Runtype to coordinate the Agent’s skills instead of letting the calling Agent pick.