Sapien is a new policy engine that enforces stateful contextual policies for AI agents, allowing for more dynamic and flexible security defenses in multi-step tasks.
> Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls.
Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a policy engine for enforcing stateful contextual policies.
