Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy

This article announces that Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy, providing enterprises with enhanced safety and security controls for AI agents at scale.

• Guardrails evaluate agent action outputs and gateway target inputs in real-time to detect and block threats
• Defends against prompt injection attacks, harmful content, and sensitive data exposure
• Policy evaluations occur at the AgentCore gateway perimeter, ensuring consistent enforcement
• Works with existing AgentCore gateway deployments without requiring new infrastructure
• Policies authored via natural language or policy-as-code with consumption-based pricing
• Available in US East (N. Virginia), Europe (London), Europe (Stockholm), Asia Pacific (Sydney), and Asia Pacific (Tokyo)

Bedrock Guardrails in policy enable enterprises to secure AI agent workloads with real-time threat detection and consistent policy enforcement across deployments.