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

# Send Policy Protocol • AI Agent SDK

> SendPolicyProtocol: Protocol for authorising agent-initiated proactive sends.

# SendPolicyProtocol

> Defined in the [**protocols**](../modules/protocols) module.

<Badge color="blue">AI Agent</Badge>

Protocol for authorising agent-initiated proactive sends.

Implementations decide whether an agent may deliver to a model-chosen
`target`. The hook is evaluated inside the `send_message` path before
the messenger dispatches, so a denied send returns a clean, model-readable
:class:`DeliveryResult` (`ok=False`) rather than delivering.

A concrete, config-driven implementation (:class:`SendPolicy`) is provided
for the common allow/deny case; richer back-ends may live in plugins.

## Methods

<CardGroup cols={2}>
  <Card title="evaluate()" icon="function" href="../functions/SendPolicyProtocol-evaluate">
    Return a :class:`SendDecision` for the requested `target`.
  </Card>
</CardGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/gateway/protocols.py#L2814">
  `praisonaiagents/gateway/protocols.py` at line 2814
</Card>