automated_reasoning_policy_test_cases

Creates, updates, deletes, gets or lists an automated_reasoning_policy_test_cases resource.

Overview

Name	automated_reasoning_policy_test_cases
Type	Resource
Id	aws.bedrock.automated_reasoning_policy_test_cases

Fields

The following fields are returned by SELECT queries:

get_automated_reasoning_policy_test_case

Name	Datatype	Description
policy_arn	string	The Amazon Resource Name (ARN) of the policy that contains the test. (pattern: <code>arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:automated-reasoning-policy/[a-z0-9]{12}(:([1-9][0-9]{0,11}))?</code>)
test_case	object	Represents a test for validating an Automated Reasoning policy. tests contain sample inputs and expected outcomes to verify policy behavior.

list_automated_reasoning_policy_test_cases

Name	Datatype	Description
confidence_threshold	number (double)	The minimum confidence level for logic validation. Content meeting this threshold is considered high-confidence and can be validated.
created_at	string (date-time)	The timestamp when the test was created.
expected_aggregated_findings_result	string	The expected result of the Automated Reasoning check for this test. (VALID, INVALID, SATISFIABLE, IMPOSSIBLE, TRANSLATION_AMBIGUOUS, TOO_COMPLEX, NO_TRANSLATION)
guard_content	string	The output content to be validated by the policy, typically representing a foundation model response.
query_content	string	The input query or prompt that generated the content. This provides context for the validation.
test_case_id	string	The unique identifier of the test. (pattern: <code>[0-9A-Z]{12}</code>)
updated_at	string (date-time)	The timestamp when the test was last updated.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_automated_reasoning_policy_test_case	select	policy_arn, test_case_id, region		Retrieves details about a specific Automated Reasoning policy test.
list_automated_reasoning_policy_test_cases	select	policy_arn, region	nextToken, maxResults	Lists tests for an Automated Reasoning policy. We recommend using pagination to ensure that the operation returns quickly and successfully.
create_automated_reasoning_policy_test_case	insert	policy_arn, region, guardContent, expectedAggregatedFindingsResult		Creates a test for an Automated Reasoning policy. Tests validate that your policy works as expected by providing sample inputs and expected outcomes. Use tests to verify policy behavior before deploying to production.
update_automated_reasoning_policy_test_case	update	policy_arn, test_case_id, region, guardContent, lastUpdatedAt, expectedAggregatedFindingsResult		Updates an existing Automated Reasoning policy test. You can modify the content, query, expected result, and confidence threshold.
delete_automated_reasoning_policy_test_case	delete	policy_arn, test_case_id, updatedAt, region		Deletes an Automated Reasoning policy test. This operation is idempotent; if you delete a test more than once, each call succeeds.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
policy_arn	string	The Amazon Resource Name (ARN) of the Automated Reasoning policy that contains the test.
region	string	AWS region (default: us-east-1)
test_case_id	string	The unique identifier of the test to delete.
updatedAt	string (date-time)	The timestamp when the test was last updated. This is used as a concurrency token to prevent conflicting modifications.
maxResults	integer	The maximum number of tests to return in a single call.
nextToken	string	The pagination token from a previous request to retrieve the next page of results.

SELECT examples

get_automated_reasoning_policy_test_case

Retrieves details about a specific Automated Reasoning policy test.

SELECT
policy_arn,
test_case
FROM aws.bedrock.automated_reasoning_policy_test_cases
WHERE policy_arn = '{{ policy_arn }}' -- required
AND test_case_id = '{{ test_case_id }}' -- required
AND region = '{{ region }}' -- required
;

list_automated_reasoning_policy_test_cases

Lists tests for an Automated Reasoning policy. We recommend using pagination to ensure that the operation returns quickly and successfully.

SELECT
confidence_threshold,
created_at,
expected_aggregated_findings_result,
guard_content,
query_content,
test_case_id,
updated_at
FROM aws.bedrock.automated_reasoning_policy_test_cases
WHERE policy_arn = '{{ policy_arn }}' -- required
AND region = '{{ region }}' -- required
AND nextToken = '{{ nextToken }}'
AND maxResults = '{{ maxResults }}'
;

INSERT examples

create_automated_reasoning_policy_test_case

Creates a test for an Automated Reasoning policy. Tests validate that your policy works as expected by providing sample inputs and expected outcomes. Use tests to verify policy behavior before deploying to production.

INSERT INTO aws.bedrock.automated_reasoning_policy_test_cases (
guardContent,
queryContent,
expectedAggregatedFindingsResult,
clientRequestToken,
confidenceThreshold,
policy_arn,
region
)
SELECT 
'{{ guardContent }}' /* required */,
'{{ queryContent }}',
'{{ expectedAggregatedFindingsResult }}' /* required */,
'{{ clientRequestToken }}',
{{ confidenceThreshold }},
'{{ policy_arn }}',
'{{ region }}'
RETURNING
policy_arn,
test_case_id
;

Manifest

# Description fields are for documentation purposes
- name: automated_reasoning_policy_test_cases
props:
  - name: policy_arn
    value: "{{ policy_arn }}"
    description: Required parameter for the automated_reasoning_policy_test_cases resource.
  - name: region
    value: "{{ region }}"
    description: Required parameter for the automated_reasoning_policy_test_cases resource.
  - name: guardContent
    value: "{{ guardContent }}"
  - name: queryContent
    value: "{{ queryContent }}"
  - name: expectedAggregatedFindingsResult
    value: "{{ expectedAggregatedFindingsResult }}"
    valid_values: ['VALID', 'INVALID', 'SATISFIABLE', 'IMPOSSIBLE', 'TRANSLATION_AMBIGUOUS', 'TOO_COMPLEX', 'NO_TRANSLATION']
  - name: clientRequestToken
    value: "{{ clientRequestToken }}"
  - name: confidenceThreshold
    value: {{ confidenceThreshold }}

UPDATE examples

update_automated_reasoning_policy_test_case

Updates an existing Automated Reasoning policy test. You can modify the content, query, expected result, and confidence threshold.

UPDATE aws.bedrock.automated_reasoning_policy_test_cases
SET 
guardContent = '{{ guardContent }}',
queryContent = '{{ queryContent }}',
lastUpdatedAt = '{{ lastUpdatedAt }}',
expectedAggregatedFindingsResult = '{{ expectedAggregatedFindingsResult }}',
confidenceThreshold = {{ confidenceThreshold }},
clientRequestToken = '{{ clientRequestToken }}'
WHERE 
policy_arn = '{{ policy_arn }}' --required
AND test_case_id = '{{ test_case_id }}' --required
AND region = '{{ region }}' --required
AND guardContent = '{{ guardContent }}' --required
AND lastUpdatedAt = '{{ lastUpdatedAt }}' --required
AND expectedAggregatedFindingsResult = '{{ expectedAggregatedFindingsResult }}' --required
RETURNING
policy_arn,
test_case_id;

DELETE examples

delete_automated_reasoning_policy_test_case

Deletes an Automated Reasoning policy test. This operation is idempotent; if you delete a test more than once, each call succeeds.

DELETE FROM aws.bedrock.automated_reasoning_policy_test_cases
WHERE policy_arn = '{{ policy_arn }}' --required
AND test_case_id = '{{ test_case_id }}' --required
AND updatedAt = '{{ updatedAt }}' --required
AND region = '{{ region }}' --required
;