# Call an agent - Workflow node | Docs - nodulz

Source: https://nodulz.com/docs/nodes/call_agent

Language: en

Delegate a task to an AI agent in a published workflow

## Usage and specifics

Select an accessible agent and build its input. Target agent permissions, tools and limits still apply. Tool approval cannot pause a nested agent.

Technical type : `call_agent`. Runtime : `nodulz`.

## Credentials and prerequisites

This node defines no dedicated external credential. Remote sources or execution targets may still need their own access credentials.

See the [credentials guide](/docs/credentials) if a remote source or execution target requires access.

## Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

| Parameter | Type | Default | Values / limits |
| --- | --- | --- | --- |
| `workflowId` | `string` | `""` | - |
| `agentNodeId` | `string` | `""` | - |
| `input` | `string` | `"{{input}}"` | - |
| `name` | `string` | `"call_agent"` | - |
| `description` | `string` | `"Delegate a task to a specialist agent."` | - |

## Configuration help

| Setting | Purpose and guidance |
| --- | --- |
| `workflowId`<br>Agent workflow | Only published workflows you can read and execute are listed. Permissions are checked on every call. |
| `agentNodeId`<br>Agent to call | Choose an enabled AI agent in the workflow. Its answer is available in text, its steps in steps, and its turn count in iterations. |
| `input`<br>Task and context to pass | Accepts text or an expression returning an object. The agent receives this value in input, without the caller’s variables or node outputs. When used as an agent tool, the model’s input argument replaces this field. |
| `name`<br>Tool name | Unique name the orchestrating agent uses to call this tool. Prefer a short name without spaces. |
| `description`<br>When to delegate to this agent | Describe its expertise and the tasks to delegate. The orchestrating agent uses this description to choose the tool. |

## Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

```json
{
  "workflowId": "",
  "agentNodeId": "",
  "input": "{{input}}",
  "name": "call_agent",
  "description": "Delegate a task to a specialist agent."
}
```

## Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.

See also : [Expressions and data](/docs/expressions), [Executions](/docs/executions), [Node catalog](/docs/nodes).

## Explore further

- [Features - nodulz](https://nodulz.com/product/overview)
- [Node catalog - nodulz](https://nodulz.com/product/catalog)
- [MCP server - nodulz](https://nodulz.com/product/mcp)
- [Pricing - nodulz](https://nodulz.com/pricing)
- [Use cases and workflow automation - nodulz](https://nodulz.com/use-cases)
- [Choose what your workflows can do. - nodulz](https://nodulz.com/compare)
- [Documentation - nodulz](https://nodulz.com/docs)