Home icon

Tailor responsible AI with new safeguard tiers in Amazon Bedrock Guardrails

Machine Learning Blog



AWS has introduced new safeguard tiers in Amazon Bedrock Guardrails to help organizations implement responsible AI with more flexible protection strategies for generative AI applications.

  • Two new tiers introduced: Classic (default) and Standard
  • Standard tier offers multilingual support for over 60 languages
  • Improved protection against prompt attacks and manipulated inputs
  • Enhanced topic detection with better understanding of complex topics
  • Organizations can independently configure tiers for content filters and denied topics

Key benefits include independent policy evolution, controlled adoption, resource efficiency, and a simplified migration path for implementing AI safety controls across different applications and use cases.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jun 10
2025
Build responsible AI applications with Amazon Bedrock Guardrails
Apr 8
2025
Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities
Mar 18
2025
Amazon Bedrock Guardrails announces policy based enforcement for responsible AI
Jan 15
2026
Safeguard generative AI applications with Amazon Bedrock Guardrails

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.