@cdklabs/generative-ai-cdk-constructs • Docs
@cdklabs/generative-ai-cdk-constructs / bedrock / GuardrailAction
Guardrail action when a sensitive entity is detected.
ANONYMIZE:
"ANONYMIZE"
If sensitive information is detected in the model response, the guardrail masks it with an identifier, the sensitive information is masked and replaced with identifier tags (for example: [NAME-1], [NAME-2], [EMAIL-1], etc.).
BLOCK:
"BLOCK"
If sensitive information is detected in the prompt or response, the guardrail blocks all the content and returns a message that you configure.