Build actions

Actions are what the agent can do: call your APIs, submit forms, navigate your UI, or render a component. Each action has two halves — you define it in Agent Studio (name, description, input schema) and implement it in your code (a handler registered under the action’s key). The agent decides when to call an action from the user’s request; your handler runs it and returns data or renders UI.

What are Actions The model: text-driven capabilities the agent routes requests to.

Connect actions Register a handler in your code under the action's key.

Execute actions What runs at call time, and how to return data or render UI.

Where to start

Read What are Actions for the model, then Connect actions to wire a handler, then Execute actions for the runtime.

Related

• Authoring actions: define actions in the Agent Studio dashboard.
• Agentic UI: render UI components from an action.