Amazon Bedrock Guardrails announces general availability of cross-account safeguards

Amazon Bedrock Guardrails now enables centralized enforcement of safety controls across all AWS accounts within an organization through cross-account safeguards. Amazon Bedrock Guardrails offers configurable safeguards that help block up to 88% of harmful multimodal content from both input prompts and model responses, while filtering hallucinated responses from foundation models. Central security teams and administrators can now automatically implement these controls for all foundation model interactions in Amazon Bedrock across their organization, eliminating the operational overhead of manually configuring guardrails for each account.

With cross-account safeguards, you can specify a guardrail ID from your management account in a new Amazon Bedrock policy that automatically enforces configured safeguards across all member entities including organizational units (OUs) and individual accounts for all model invocations with Amazon Bedrock. This enables operational efficiency through automatic enforcement from a single control point in your management account. You can implement organization-level enforcement for uniform baseline protection, account-level controls for specific departmental requirements, and application-specific safeguards that complement organizational policies, with the union of multiple guardrails enforced during model inference calls.

Organizational safeguards in Amazon Bedrock Guardrails is now available in all AWS commercial and GovCloud regions where Bedrock Guardrails is supported. You can access this capability through the AWS management console or using the supported APIs.

To learn more about implementing centralized guardrails enforcement across your organization, read the News blog, visit the Amazon Bedrock Guardrails documentation, and explore the Amazon Bedrock Guardrails service page.