Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore a 21-minute AWS OnAir video session introducing new capabilities in Amazon Bedrock Guardrails designed to implement responsible AI at enterprise scale. Learn how these integrated safety, privacy, and truthfulness safeguards work across multiple foundation models both on and beyond Amazon Bedrock. Discover how these new features reduce implementation complexity while helping maintain compliance with responsible AI policies through configurable controls tailored to specific use cases and industries. See how customers have used Amazon Bedrock Guardrails to standardize protections across generative AI applications, bridge gaps between native model protections and enterprise requirements, and streamline governance processes. The video includes links to resources for getting started, including blogs on MultiModel Toxicity detection and IAM Policy based enforcement, plus product and technical documentation pages.
