AutomatedReasoningPolicyTestCase - Amazon Bedrock
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.

AutomatedReasoningPolicyTestCase

Represents a test for validating an Automated Reasoning policy. tests contain sample inputs and expected outcomes to verify policy behavior.

Contents

createdAt

The timestamp when the test was created.

Type: Timestamp

Required: Yes

guardContent

The output content to be validated by the policy, typically representing a foundation model response.

Type: String

Length Constraints: Minimum length of 0. Maximum length of 2048.

Required: Yes

testCaseId

The unique identifier of the test.

Type: String

Length Constraints: Minimum length of 0. Maximum length of 12.

Pattern: [0-9A-Z]{12}

Required: Yes

updatedAt

The timestamp when the test was last updated.

Type: Timestamp

Required: Yes

confidenceThreshold

The minimum confidence level for logic validation. Content meeting this threshold is considered high-confidence and can be validated.

Type: Double

Valid Range: Minimum value of 0. Maximum value of 1.

Required: No

expectedAggregatedFindingsResult

The expected result of the Automated Reasoning check for this test.

Type: String

Valid Values: VALID | INVALID | SATISFIABLE | IMPOSSIBLE | TRANSLATION_AMBIGUOUS | TOO_COMPLEX | NO_TRANSLATION

Required: No

queryContent

The input query or prompt that generated the content. This provides context for the validation.

Type: String

Length Constraints: Minimum length of 0. Maximum length of 1024.

Required: No

See Also

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