Amazon Bedrock Guardrails announces new capabilities to safely build generative AI applications
News
Amazon Bedrock Guardrails has announced new capabilities to enhance the safety and control of generative AI applications:
- Detect mode allows preview of policy results before deployment
- More granular policy configuration options for input prompts and model responses
- Sensitive information filters with two modes: Block and Mask
- Ability to apply PII detection to both input prompts and model responses
- New features available in all AWS regions supporting Bedrock Guardrails
These enhancements provide developers with greater flexibility and control in building responsible and safe generative AI applications, enabling faster iteration and more precise policy implementation.
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
Apr 8
2025
2025
Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities
Jan 15
2026
2026
Safeguard generative AI applications with Amazon Bedrock Guardrails
Mar 2
2026
2026
Build safe generative AI applications like a Pro: Best Practices with Amazon Bedrock Guardrails
Jun 10
2025
2025
Build responsible 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.