Gemini Agent
An autonomous agent powered by Google Gemini that can react to events from other components, execute commands, set timers, and maintain working memory. Uses Google ADK for orchestration.
Component Configuration
| Option | Description | Required |
|---|---|---|
id |
A unique identifier for the component instance |
✓ |
displayName |
The name shown in the Studio UI of this component |
✓ |
mission |
The agent's ongoing task/goal for this workflow - what should it accomplish? |
✓ |
systemPrompt |
Base instruction defining the agent's capabilities and how it should behave |
✗ |
model |
Gemini model to use (default: "gemini-2.0-flash") |
✗ |
initialPrompt |
Optional message to send when the agent starts (after mission is set) |
✗ |
maxStepsPerInvocation |
Maximum tool calls per agent invocation (default: 10) (default: 10) |
✗ |
notes |
Notes about this agent |
✗ |
Tags: