Agent Executor
Category: Agent
Node id: agent-executor
Orchestrates an LLM agent with iterative tool-use capabilities
What it does
- Iterative LLM reasoning with tool-use loop
- Configurable maximum iteration count
- Tool call detection and delegation to pipeline orchestrator
- Full message history tracking across iterations
- System prompt customization for agent persona
- Automatic stop detection on completion
Use cases
- Building ReAct-style agents that reason and act iteratively
- Autonomous task execution with tool augmentation
- Multi-step clinical workflows requiring external tool calls
- Complex question answering with intermediate reasoning steps
Runtime
- Performance tier:
slow
Input ports
| Name | Type | Required | Description |
|---|---|---|---|
task | text | Yes | The task for the agent to execute |
context | text | No | Additional context for the agent |
Output ports
| Name | Type | Required | Description |
|---|---|---|---|
result | json | No | Execution result with answer, steps, iterations, status, and optionally tool_calls and messages |
success | boolean | No | Whether the execution completed without error |
Settings
Basic
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| LLM Endpoint | llm_endpoint | string | Yes | Base URL of the LLM API | ||
| Model | model | string | No | gpt-4o | Model name to use | |
| System Prompt | system_prompt | text | No | You are a helpful AI assistant. | System prompt for the agent |
Auth
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| API Key | api_key | secret | No | API key for the LLM provider |
Advanced
| Setting | Name | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|---|
| Max Iterations | max_iterations | number | No | 10 | min 1; max 100 | Maximum number of reasoning iterations |
| Temperature | temperature | number | No | 0.7 | min 0; max 2 | Sampling temperature |
| Max Tokens | max_tokens | number | No | 4096 | Maximum tokens per LLM call | |
| Tools | tools | json | No | Tool definitions for the agent to use |
Errors
| Code | Description |
|---|---|
ENDPOINT_REQUIRED | llm_endpoint is not configured |
TASK_REQUIRED | No task input was provided |
LLM_REQUEST_FAILED | LLM API call failed during an iteration |
HTTP_ERROR | LLM endpoint returned an HTTP error status |
Runtime notes
- When tool_calls are pending, status is 'tool_calls_pending' and the messages array contains the full conversation history for resumption
- result.steps is an ordered array — each entry records one LLM round-trip with its finish_reason
- The node stops iterating on finish_reason 'stop' or when max_iterations is reached
- Wire the success output to a branch node to handle LLM errors vs tool-call delegation
See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.
Something unclear? Send documentation feedback by email.