Agent Executor
Category: Agent Standards: HIPAA (with BAA) · AI governance
Execute multi-step agentic workflows with tool calls and reasoning
What this node does
- Multi-step reasoning
- Tool calling
- Iterative execution
- Context management
How to use
- In the Hydra Builder, open or create a workflow
- In the node palette on the left, find Agent Executor under the Agent category (or use the search bar)
- Drag the node onto the canvas
- Double-click the node to open its configuration dialog
- Fill in the required parameters (see Configuration below)
- Connect the Agent Task input port from an upstream node
- Optionally connect the Available Tools port if needed
- Connect the Execution Result and Reasoning Trace output to the next node downstream
Inputs
| Port | Type | Required | Description |
|---|---|---|---|
| Agent Task | text | ✓ | Plain text string |
| Available Tools | array | Optional | A list of items |
Outputs
| Port | Type | Description |
|---|---|---|
| Execution Result | json | JSON data object |
| Reasoning Trace | array | A list of items |
Configuration
Open the configuration dialog by double-clicking the Agent Executor node on the canvas.
| Parameter | What to enter |
|---|---|
maxIterations | Configure maxIterations in the node settings |
tools | List of tools the agent is allowed to call during its run |
llmConfig | Configure llmConfig in the node settings |
temperature | Creativity of the output: 0.0 for deterministic, 1.0 for creative (default: 0.3) |
When to use this node
- Complex clinical queries
- Multi-step analysis
- Autonomous workflows
Need help configuring this node?
Go to Settings → Connectors to set up the connection this node depends on, then reference the connector ID in the node configuration dialog.