Amazon Bedrock Guardrails announces policy based enforcement for responsible AI
News
Amazon Bedrock Guardrails has introduced new IAM policy-based enforcement capabilities for responsible AI development:
- Enables customers to apply specific guardrails to model inference calls
- Provides configurable safeguards to detect and filter undesirable content
- Includes topic filters, sensitive information filters, and word blocking
- Can detect model hallucinations and verify factual claims
- Applicable across foundation models, including Amazon Bedrock, self-hosted, and third-party models
- Introduces new IAM condition key bedrock:GuardrailIdentifier to enforce specific guardrails
- Rejects requests that do not comply with configured guardrails
The feature is now available in all AWS regions where Bedrock Guardrails is supported, providing a standardized approach to AI safety and privacy controls.
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
Mar 18
2025
2025
Amazon Bedrock Guardrails announces IAM Policy-based enforcement to deliver safe AI interactions
Apr 8
2025
2025
Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities
Jun 10
2025
2025
Build responsible AI applications with Amazon Bedrock Guardrails
Apr 8
2025
2025
Amazon Bedrock Guardrails announces new capabilities to safely build generative AI applications
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.