> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agenticenv.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Sub-agents

> Register specialist sub-agents and configure delegation depth, approval policies, and task queue routing

Sub-agents let a **main agent** delegate work to **specialist agents** — each with its own LLM, tools, prompts, and Temporal task queue. The main agent sees each specialist as a delegation tool the LLM can invoke.

Use sub-agents for domain specialists (math, research, coding) without concentrating every capability into one prompt and tool list.

## Setup

Build each specialist with `NewAgent`, then register it on the main agent:

```go theme={null}
mathAgent, err := agent.NewAgent(
    agent.WithName("MathSpecialist"),
    agent.WithDescription("Arithmetic; uses calculator tools."),
    agent.WithTemporalConfig(&agent.TemporalConfig{
        Host: "localhost", Port: 7233, Namespace: "default",
        TaskQueue: "my-app-math",  // unique task queue for this specialist
    }),
    agent.WithLLMClient(llmClient),
    agent.WithToolRegistry(mathTools),
    agent.WithToolApprovalPolicy(agent.AutoToolApprovalPolicy()),
)
if err != nil {
    return err
}
defer mathAgent.Close()

mainAgent, err := agent.NewAgent(
    agent.WithName("Orchestrator"),
    agent.WithSystemPrompt("You are a helpful assistant."),
    agent.WithTemporalConfig(&agent.TemporalConfig{
        Host: "localhost", Port: 7233, Namespace: "default",
        TaskQueue: "my-app-main",
    }),
    agent.WithLLMClient(llmClient),
    agent.WithSubAgents(mathAgent),
    agent.WithMaxSubAgentDepth(2),
)
if err != nil {
    return err
}
defer mainAgent.Close()

result, err := mainAgent.Run(ctx, "What is 144 divided by 12?", nil)
```

| Option                                                   | Description                                  |
| -------------------------------------------------------- | -------------------------------------------- |
| [`WithSubAgents`](/getting-started/configuration)        | Register specialists at creation             |
| [`WithMaxSubAgentDepth`](/getting-started/configuration) | Max delegation nesting depth — default **2** |

Each specialist needs a **unique** `TaskQueue` when using Temporal. Use clear `WithName` and `WithDescription` values — they appear in the delegation tool schema the LLM sees for routing decisions.

## Behavior

* **Conversation isolation** — sub-agents do not inherit the main agent's conversation ID. They run without session history from the parent.
* **Independent approval policies** — parent and child policies are independent (see [Approvals](/features/approvals)).
* **Worker pairing** — with `DisableLocalWorker`, pair each `NewAgentWorker` with the same options as the `NewAgent` it runs.
* **Validation at build** — sub-agent graphs are validated for cycles and depth violations at `NewAgent`. Errors fail fast.

<Warning>
  Sub-agents do **not** share the parent's conversation history. If you need the specialist to have context from the parent session, include it in the delegation prompt or tool call arguments.
</Warning>

## Streaming

When streaming, events from all delegated sub-agents fan in to the main agent's stream, bracketed by `STEP_STARTED` and `STEP_FINISHED`. See [Streaming](/getting-started/streaming) for the full event reference and approval handling patterns.

## Example

<CardGroup cols={2}>
  <Card title="Sub-agents" icon="play" href="/examples/subagents">
    Orchestrator delegating to a math specialist
  </Card>
</CardGroup>

## Related

<CardGroup cols={2}>
  <Card title="A2A" icon="network-wired" href="/features/a2a">
    Remote agents over the A2A protocol
  </Card>

  <Card title="Approvals" icon="shield-check" href="/features/approvals">
    Parent vs specialist approval policies
  </Card>

  <Card title="Dynamic Capabilities" icon="rotate" href="/advanced/dynamic-capabilities">
    Register sub-agents after NewAgent
  </Card>

  <Card title="Multiple Agents" icon="layer-group" href="/advanced/multiple-agents">
    Instance IDs and task queue patterns
  </Card>
</CardGroup>