automated_reasoning_policies

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

Overview

Name	automated_reasoning_policies
Type	Resource
Id	aws.bedrock.automated_reasoning_policies

Fields

The following fields are returned by SELECT queries:

get_automated_reasoning_policy

Name	Datatype	Description
name	string	The name of the policy. (pattern: <code>[0-9a-zA-Z-_ ]+</code>)
created_at	string (date-time)	The timestamp when the policy was created.
definition_hash	string	The hash of the policy definition used as a concurrency token. (pattern: <code>[0-9a-z]{128}</code>)
description	string	The description of the policy. (pattern: <code>[\s\S]+</code>)
kms_key_arn	string	The Amazon Resource Name (ARN) of the KMS key used to encrypt the automated reasoning policy and its associated artifacts. If a KMS key is not provided during the initial CreateAutomatedReasoningPolicyRequest, the kmsKeyArn won't be included in the GetAutomatedReasoningPolicyResponse. (pattern: <code>arn:aws(-[^:]+)?:kms:[a-zA-Z0-9-]*:[0-9]{12}:key/[a-zA-Z0-9-]{36}</code>)
policy_arn	string	The Amazon Resource Name (ARN) of the policy. (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>)
policy_id	string	The unique identifier of the policy. (pattern: <code>[a-z0-9]{12}</code>)
updated_at	string (date-time)	The timestamp when the policy was last updated.
version	string	The version of the policy. (pattern: <code>([1-9][0-9]{0,11})</code>)

list_automated_reasoning_policies

Name	Datatype	Description
name	string	The name of the policy. (pattern: <code>[0-9a-zA-Z-_ ]+</code>)
created_at	string (date-time)	The timestamp when the policy was created.
description	string	The description of the policy. (pattern: <code>[\s\S]+</code>)
policy_arn	string	The Amazon Resource Name (ARN) of the policy. (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>)
policy_id	string	The unique identifier of the policy. (pattern: <code>[a-z0-9]{12}</code>)
updated_at	string (date-time)	The timestamp when the policy was last updated.
version	string	The version of the policy. (pattern: <code>([1-9][0-9]{0,11})</code>)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_automated_reasoning_policy	select	policy_arn, region		Retrieves details about an Automated Reasoning policy or policy version. Returns information including the policy definition, metadata, and timestamps.
list_automated_reasoning_policies	select	region	policyArn, nextToken, maxResults	Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN. This helps you manage and discover existing policies.
create_automated_reasoning_policy_version	insert	policy_arn, region, lastUpdatedDefinitionHash		Creates a new version of an existing Automated Reasoning policy. This allows you to iterate on your policy rules while maintaining previous versions for rollback or comparison purposes.
create_automated_reasoning_policy	insert	region, name		Creates an Automated Reasoning policy for Amazon Bedrock Guardrails. Automated Reasoning policies use mathematical techniques to detect hallucinations, suggest corrections, and highlight unstated assumptions in the responses of your GenAI application. To create a policy, you upload a source document that describes the rules that you're encoding. Automated Reasoning extracts important concepts from the source document that will become variables in the policy and infers policy rules.
update_automated_reasoning_policy	update	policy_arn, region, policyDefinition		Updates an existing Automated Reasoning policy with new rules, variables, or configuration. This creates a new version of the policy while preserving the previous version.
delete_automated_reasoning_policy	delete	policy_arn, region	force	Deletes an Automated Reasoning policy or policy version. This operation is idempotent. If you delete a policy more than once, each call succeeds. Deleting a policy removes it permanently and cannot be undone.
cancel_automated_reasoning_policy_build_workflow	exec	policy_arn, build_workflow_id, region		Cancels a running Automated Reasoning policy build workflow. This stops the policy generation process and prevents further processing of the source documents.
export_automated_reasoning_policy_version	exec	policy_arn, region		Exports the policy definition for an Automated Reasoning policy version. Returns the complete policy definition including rules, variables, and custom variable types in a structured format.
start_automated_reasoning_policy_build_workflow	exec	policy_arn, build_workflow_type, region, sourceContent	x-amz-client-token	Starts a new build workflow for an Automated Reasoning policy. This initiates the process of analyzing source documents and generating policy rules, variables, and types.
start_automated_reasoning_policy_test_workflow	exec	policy_arn, build_workflow_id, region		Initiates a test workflow to validate Automated Reasoning policy tests. The workflow executes the specified tests against the policy and generates validation results.

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
build_workflow_id	string	The build workflow identifier. The build workflow must show a COMPLETED status before running tests.
build_workflow_type	string	The type of build workflow to start (e.g., DOCUMENT_INGESTION for processing new documents, POLICY_REPAIR for fixing existing policies).
policy_arn	string	The Amazon Resource Name (ARN) of the Automated Reasoning policy to test.
region	string	AWS region (default: us-east-1)
force	boolean	Specifies whether to force delete the automated reasoning policy even if it has active resources. When false, Amazon Bedrock validates if all artifacts have been deleted (e.g. policy version, test case, test result) for a policy before deletion. When true, Amazon Bedrock will delete the policy and all its artifacts without validation. Default is false.
maxResults	integer	The maximum number of policies to return in a single call.
nextToken	string	The pagination token from a previous request to retrieve the next page of results.
policyArn	string	Optional filter to list only the policy versions with the specified Amazon Resource Name (ARN). If not provided, the DRAFT versions for all policies are listed.
x-amz-client-token	string	A unique, case-sensitive identifier to ensure that the operation completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request but doesn't return an error.

SELECT examples

get_automated_reasoning_policy

Retrieves details about an Automated Reasoning policy or policy version. Returns information including the policy definition, metadata, and timestamps.

SELECT
name,
created_at,
definition_hash,
description,
kms_key_arn,
policy_arn,
policy_id,
updated_at,
version
FROM aws.bedrock.automated_reasoning_policies
WHERE policy_arn = '{{ policy_arn }}' -- required
AND region = '{{ region }}' -- required
;

list_automated_reasoning_policies

Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN. This helps you manage and discover existing policies.

SELECT
name,
created_at,
description,
policy_arn,
policy_id,
updated_at,
version
FROM aws.bedrock.automated_reasoning_policies
WHERE region = '{{ region }}' -- required
AND policyArn = '{{ policyArn }}'
AND nextToken = '{{ nextToken }}'
AND maxResults = '{{ maxResults }}'
;

INSERT examples

create_automated_reasoning_policy_version

Creates a new version of an existing Automated Reasoning policy. This allows you to iterate on your policy rules while maintaining previous versions for rollback or comparison purposes.

INSERT INTO aws.bedrock.automated_reasoning_policies (
clientRequestToken,
lastUpdatedDefinitionHash,
tags,
policy_arn,
region
)
SELECT 
'{{ clientRequestToken }}',
'{{ lastUpdatedDefinitionHash }}' /* required */,
'{{ tags }}',
'{{ policy_arn }}',
'{{ region }}'
RETURNING
name,
created_at,
definition_hash,
description,
policy_arn,
version
;

create_automated_reasoning_policy

Creates an Automated Reasoning policy for Amazon Bedrock Guardrails. Automated Reasoning policies use mathematical techniques to detect hallucinations, suggest corrections, and highlight unstated assumptions in the responses of your GenAI application. To create a policy, you upload a source document that describes the rules that you're encoding. Automated Reasoning extracts important concepts from the source document that will become variables in the policy and infers policy rules.

INSERT INTO aws.bedrock.automated_reasoning_policies (
name,
description,
clientRequestToken,
policyDefinition,
kmsKeyId,
tags,
region
)
SELECT 
'{{ name }}' /* required */,
'{{ description }}',
'{{ clientRequestToken }}',
'{{ policyDefinition }}',
'{{ kmsKeyId }}',
'{{ tags }}',
'{{ region }}'
RETURNING
name,
created_at,
definition_hash,
description,
policy_arn,
updated_at,
version
;

Manifest

# Description fields are for documentation purposes
- name: automated_reasoning_policies
props:
  - name: policy_arn
    value: "{{ policy_arn }}"
    description: Required parameter for the automated_reasoning_policies resource.
  - name: region
    value: "{{ region }}"
    description: Required parameter for the automated_reasoning_policies resource.
  - name: clientRequestToken
    value: "{{ clientRequestToken }}"
  - name: lastUpdatedDefinitionHash
    value: "{{ lastUpdatedDefinitionHash }}"
  - name: tags
    value:
      - key: "{{ key }}"
        value: "{{ value }}"
  - name: name
    value: "{{ name }}"
  - name: description
    value: "{{ description }}"
  - name: policyDefinition
    description: |
      Contains the formal logic rules, variables, and custom variable types that define an Automated Reasoning policy. The policy definition specifies the constraints used to validate foundation model responses for accuracy and logical consistency.
    value:
      version: "{{ version }}"
      types:
        - name: "{{ name }}"
          description: "{{ description }}"
          values: "{{ values }}"
      rules:
        - id: "{{ id }}"
          expression: "{{ expression }}"
          alternateExpression: "{{ alternateExpression }}"
      variables:
        - name: "{{ name }}"
          type_: "{{ type_ }}"
          description: "{{ description }}"
  - name: kmsKeyId
    value: "{{ kmsKeyId }}"

UPDATE examples

update_automated_reasoning_policy

Updates an existing Automated Reasoning policy with new rules, variables, or configuration. This creates a new version of the policy while preserving the previous version.

UPDATE aws.bedrock.automated_reasoning_policies
SET 
policyDefinition = '{{ policyDefinition }}',
name = '{{ name }}',
description = '{{ description }}'
WHERE 
policy_arn = '{{ policy_arn }}' --required
AND region = '{{ region }}' --required
AND policyDefinition = '{{ policyDefinition }}' --required
RETURNING
name,
definition_hash,
policy_arn,
updated_at;

DELETE examples

delete_automated_reasoning_policy

Deletes an Automated Reasoning policy or policy version. This operation is idempotent. If you delete a policy more than once, each call succeeds. Deleting a policy removes it permanently and cannot be undone.

DELETE FROM aws.bedrock.automated_reasoning_policies
WHERE policy_arn = '{{ policy_arn }}' --required
AND region = '{{ region }}' --required
AND force = '{{ force }}'
;

Lifecycle Methods

cancel_automated_reasoning_policy_build_workflow

Cancels a running Automated Reasoning policy build workflow. This stops the policy generation process and prevents further processing of the source documents.

EXEC aws.bedrock.automated_reasoning_policies.cancel_automated_reasoning_policy_build_workflow 
@policy_arn='{{ policy_arn }}' --required, 
@build_workflow_id='{{ build_workflow_id }}' --required, 
@region='{{ region }}' --required
;

export_automated_reasoning_policy_version

Exports the policy definition for an Automated Reasoning policy version. Returns the complete policy definition including rules, variables, and custom variable types in a structured format.

EXEC aws.bedrock.automated_reasoning_policies.export_automated_reasoning_policy_version 
@policy_arn='{{ policy_arn }}' --required, 
@region='{{ region }}' --required
;

start_automated_reasoning_policy_build_workflow

Starts a new build workflow for an Automated Reasoning policy. This initiates the process of analyzing source documents and generating policy rules, variables, and types.

EXEC aws.bedrock.automated_reasoning_policies.start_automated_reasoning_policy_build_workflow 
@policy_arn='{{ policy_arn }}' --required, 
@build_workflow_type='{{ build_workflow_type }}' --required, 
@region='{{ region }}' --required, 
@x-amz-client-token='{{ x-amz-client-token }}' 
@@json=
'{
"sourceContent": "{{ sourceContent }}"
}'
;

start_automated_reasoning_policy_test_workflow

Initiates a test workflow to validate Automated Reasoning policy tests. The workflow executes the specified tests against the policy and generates validation results.

EXEC aws.bedrock.automated_reasoning_policies.start_automated_reasoning_policy_test_workflow 
@policy_arn='{{ policy_arn }}' --required, 
@build_workflow_id='{{ build_workflow_id }}' --required, 
@region='{{ region }}' --required 
@@json=
'{
"testCaseIds": "{{ testCaseIds }}", 
"clientRequestToken": "{{ clientRequestToken }}"
}'
;