Policy: AWS > Bedrock > Guardrail > Settings > Automated Reasoning Policy > Confidence Threshold

Minimum confidence (0-1) required for automated-reasoning policy violations to trigger guardrail actions. Leave unset to skip; the field is included in the enforced automatedReasoningPolicyConfig only when set and only when Automated Reasoning Policy Policies is also non-empty.

Targets

This policy targets the following resource types:

AWS > Bedrock > Guardrail

Primary Policy

This policy is used with the following primary policy:

AWS > Bedrock > Guardrail > Settings > Automated Reasoning Policy

Controls

Setting this policy configures this control:

AWS > Bedrock > Guardrail > Settings

Policy Specification

Examples [YAML]	`0.75` `0.5`

In Your Workspace

Policy Settings by Type report

Developers

Category URI

tmod:@turbot/turbot#/control/categories/security

Policy Type URI

tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold

GraphQL

query policyType(id: "tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold") { … }

query policySettings(filter: "policyTypeId:'tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold'") { … }

query policyValues(filter: "policyTypeId:'tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold'") { … }

CLI

Get Policy Type

turbot graphql policy-type --id "tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold"

Get Policy Settings

turbot graphql policy-settings --filter "policyTypeId:tmod:@turbot/aws-bedrock#/policy/types/bedrockGuardrailSettingsAutomatedReasoningPolicyConfidenceThreshold"