GuardrailTraceAssessment - Amazon Bedrock
ContentsSee Also
Services or capabilities described in AWS documentation might vary by Region. To see the differences applicable to the AWS European Sovereign Cloud Region, see the AWS European Sovereign Cloud User Guide.

GuardrailTraceAssessment

A Top level guardrail trace object. For more information, see ConverseTrace.

Contents

actionReason

Provides the reason for the action taken when harmful content is detected.

Type: String

Required: No

inputAssessment

The input assessment.

Type: String to GuardrailAssessment object map

Required: No

modelOutput

The output from the model.

Type: Array of strings

Required: No

outputAssessments

the output assessments.

Type: String to array of GuardrailAssessment objects map

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: