Skip to content

Bedrock  >  Structures  >  GuardrailAutomatedReasoningPolicy

GuardrailAutomatedReasoningPolicy

Structure Class

GuardrailAutomatedReasoningPolicy dataclass

Represents the configuration of Automated Reasoning policies within a Amazon Bedrock Guardrail, including the policies to apply and confidence thresholds.

Attributes

confidence_threshold class-attribute instance-attribute 
confidence_threshold: float | None = None

The minimum confidence level required for Automated Reasoning policy violations to trigger guardrail actions. Values range from 0.0 to 1.0.

policies instance-attribute 
policies: list[str]

The list of Automated Reasoning policy ARNs that should be applied as part of this guardrail configuration.