Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy

Published

June 17, 2026

Amazon Bedrock AgentCore Policy Guardrails

AWS announces that Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy, providing enterprises with enhanced safety and security controls as they scale AI agents in production.

Guardrails offer defenses against top security and safety risks with AI agent workloads, including prompt injection attacks and sensitive data exposure. They evaluate outputs of authorized agent actions and inputs of every call to a gateway target in real-time, helping detect and block harmful content and sensitive information exposure.

Guardrail results are evaluated in policy at the AgentCore gateway perimeter, ensuring consistent enforcement regardless of agent autonomy. All policy evaluations are logged for optimization and auditing purposes.

AgentCore policy works with existing AgentCore gateway deployments and requires no new infrastructure. Customers can author policies through natural language or policy-as-code, with consumption-based pricing for policy evaluations.