1. Registry
  2. Packages
  3. AWS Cloud Control
  4. API Docs
  5. bedrock
  6. getGuardrail

We recommend new projects start with resources from the AWS provider.

Viewing docs for AWS Cloud Control v1.86.0
published on Wednesday, Nov 18, 2026 by Pulumi
aws-native logo aws-native logo AWS Cloud Control

We recommend new projects start with resources from the AWS provider.

Viewing docs for AWS Cloud Control v1.86.0
published on Wednesday, Nov 18, 2026 by Pulumi

    Definition of AWS::Bedrock::Guardrail Resource Type

    Using getGuardrail

    Two invocation forms are available. The direct form accepts plain arguments and either blocks until the result value is available, or returns a Promise-wrapped result. The output form accepts Input-wrapped arguments and returns an Output-wrapped result.

    function getGuardrail(args: GetGuardrailArgs, opts?: InvokeOptions): Promise<GetGuardrailResult>
    function getGuardrailOutput(args: GetGuardrailOutputArgs, opts?: InvokeOutputOptions): Output<GetGuardrailResult>
    def get_guardrail(guardrail_arn: Optional[str] = None,
                      opts: Optional[InvokeOptions] = None) -> GetGuardrailResult
    def get_guardrail_output(guardrail_arn: pulumi.Input[Optional[str]] = None,
                      opts: Optional[InvokeOutputOptions] = None) -> Output[GetGuardrailResult]
    func LookupGuardrail(ctx *Context, args *LookupGuardrailArgs, opts ...InvokeOption) (*LookupGuardrailResult, error)
    func LookupGuardrailOutput(ctx *Context, args *LookupGuardrailOutputArgs, opts ...InvokeOption) LookupGuardrailResultOutput

    > Note: This function is named LookupGuardrail in the Go SDK.

    public static class GetGuardrail 
    {
        public static Task<GetGuardrailResult> InvokeAsync(GetGuardrailArgs args, InvokeOptions? opts = null)
        public static Output<GetGuardrailResult> Invoke(GetGuardrailInvokeArgs args, InvokeOptions? opts = null)
        public static Output<GetGuardrailResult> Invoke(GetGuardrailInvokeArgs args, InvokeOutputOptions opts)
    }
    public static CompletableFuture<GetGuardrailResult> getGuardrail(GetGuardrailArgs args, InvokeOptions options)
    public static Output<GetGuardrailResult> getGuardrail(GetGuardrailArgs args, InvokeOptions options)
    public static Output<GetGuardrailResult> getGuardrail(GetGuardrailArgs args, InvokeOutputOptions options)
    
    fn::invoke:
      function: aws-native:bedrock:getGuardrail
      arguments:
        # arguments dictionary
    data "aws-native_bedrock_get_guardrail" "name" {
        # arguments
    }

    The following arguments are supported:

    GuardrailArn string
    Arn representation for the guardrail
    GuardrailArn string
    Arn representation for the guardrail
    guardrail_arn string
    Arn representation for the guardrail
    guardrailArn String
    Arn representation for the guardrail
    guardrailArn string
    Arn representation for the guardrail
    guardrail_arn str
    Arn representation for the guardrail
    guardrailArn String
    Arn representation for the guardrail

    getGuardrail Result

    The following output properties are available:

    AutomatedReasoningPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailAutomatedReasoningPolicyConfig
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    BlockedInputMessaging string
    Messaging for when violations are detected in text
    BlockedOutputsMessaging string
    Messaging for when violations are detected in text
    ContentPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailContentPolicyConfig
    The content filter policies to configure for the guardrail.
    ContextualGroundingPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailContextualGroundingPolicyConfig
    CreatedAt string
    Time Stamp
    CrossRegionConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailCrossRegionConfig

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    Description string
    Description of the guardrail or its version
    FailureRecommendations List<string>
    List of failure recommendations
    GuardrailArn string
    Arn representation for the guardrail
    GuardrailId string
    Unique id for the guardrail
    KmsKeyArn string
    The KMS key with which the guardrail was encrypted at rest
    Name string
    Name of the guardrail
    SensitiveInformationPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailSensitiveInformationPolicyConfig
    The sensitive information policy to configure for the guardrail.
    Status Pulumi.AwsNative.Bedrock.GuardrailStatus
    The status of the guardrail.
    StatusReasons List<string>
    List of status reasons
    Tags List<Pulumi.AwsNative.Outputs.Tag>
    List of Tags
    TopicPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailTopicPolicyConfig
    The topic policies to configure for the guardrail.
    UpdatedAt string
    Time Stamp
    Version string
    Guardrail version
    WordPolicyConfig Pulumi.AwsNative.Bedrock.Outputs.GuardrailWordPolicyConfig
    The word policy you configure for the guardrail.
    AutomatedReasoningPolicyConfig GuardrailAutomatedReasoningPolicyConfig
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    BlockedInputMessaging string
    Messaging for when violations are detected in text
    BlockedOutputsMessaging string
    Messaging for when violations are detected in text
    ContentPolicyConfig GuardrailContentPolicyConfig
    The content filter policies to configure for the guardrail.
    ContextualGroundingPolicyConfig GuardrailContextualGroundingPolicyConfig
    CreatedAt string
    Time Stamp
    CrossRegionConfig GuardrailCrossRegionConfig

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    Description string
    Description of the guardrail or its version
    FailureRecommendations []string
    List of failure recommendations
    GuardrailArn string
    Arn representation for the guardrail
    GuardrailId string
    Unique id for the guardrail
    KmsKeyArn string
    The KMS key with which the guardrail was encrypted at rest
    Name string
    Name of the guardrail
    SensitiveInformationPolicyConfig GuardrailSensitiveInformationPolicyConfig
    The sensitive information policy to configure for the guardrail.
    Status GuardrailStatus
    The status of the guardrail.
    StatusReasons []string
    List of status reasons
    Tags Tag
    List of Tags
    TopicPolicyConfig GuardrailTopicPolicyConfig
    The topic policies to configure for the guardrail.
    UpdatedAt string
    Time Stamp
    Version string
    Guardrail version
    WordPolicyConfig GuardrailWordPolicyConfig
    The word policy you configure for the guardrail.
    automated_reasoning_policy_config object
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    blocked_input_messaging string
    Messaging for when violations are detected in text
    blocked_outputs_messaging string
    Messaging for when violations are detected in text
    content_policy_config object
    The content filter policies to configure for the guardrail.
    contextual_grounding_policy_config object
    created_at string
    Time Stamp
    cross_region_config object

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    description string
    Description of the guardrail or its version
    failure_recommendations list(string)
    List of failure recommendations
    guardrail_arn string
    Arn representation for the guardrail
    guardrail_id string
    Unique id for the guardrail
    kms_key_arn string
    The KMS key with which the guardrail was encrypted at rest
    name string
    Name of the guardrail
    sensitive_information_policy_config object
    The sensitive information policy to configure for the guardrail.
    status "CREATING" | "UPDATING" | "VERSIONING" | "READY" | "FAILED" | "DELETING"
    The status of the guardrail.
    status_reasons list(string)
    List of status reasons
    tags list(object)
    List of Tags
    topic_policy_config object
    The topic policies to configure for the guardrail.
    updated_at string
    Time Stamp
    version string
    Guardrail version
    word_policy_config object
    The word policy you configure for the guardrail.
    automatedReasoningPolicyConfig GuardrailAutomatedReasoningPolicyConfig
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    blockedInputMessaging String
    Messaging for when violations are detected in text
    blockedOutputsMessaging String
    Messaging for when violations are detected in text
    contentPolicyConfig GuardrailContentPolicyConfig
    The content filter policies to configure for the guardrail.
    contextualGroundingPolicyConfig GuardrailContextualGroundingPolicyConfig
    createdAt String
    Time Stamp
    crossRegionConfig GuardrailCrossRegionConfig

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    description String
    Description of the guardrail or its version
    failureRecommendations List<String>
    List of failure recommendations
    guardrailArn String
    Arn representation for the guardrail
    guardrailId String
    Unique id for the guardrail
    kmsKeyArn String
    The KMS key with which the guardrail was encrypted at rest
    name String
    Name of the guardrail
    sensitiveInformationPolicyConfig GuardrailSensitiveInformationPolicyConfig
    The sensitive information policy to configure for the guardrail.
    status GuardrailStatus
    The status of the guardrail.
    statusReasons List<String>
    List of status reasons
    tags List<Tag>
    List of Tags
    topicPolicyConfig GuardrailTopicPolicyConfig
    The topic policies to configure for the guardrail.
    updatedAt String
    Time Stamp
    version String
    Guardrail version
    wordPolicyConfig GuardrailWordPolicyConfig
    The word policy you configure for the guardrail.
    automatedReasoningPolicyConfig GuardrailAutomatedReasoningPolicyConfig
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    blockedInputMessaging string
    Messaging for when violations are detected in text
    blockedOutputsMessaging string
    Messaging for when violations are detected in text
    contentPolicyConfig GuardrailContentPolicyConfig
    The content filter policies to configure for the guardrail.
    contextualGroundingPolicyConfig GuardrailContextualGroundingPolicyConfig
    createdAt string
    Time Stamp
    crossRegionConfig GuardrailCrossRegionConfig

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    description string
    Description of the guardrail or its version
    failureRecommendations string[]
    List of failure recommendations
    guardrailArn string
    Arn representation for the guardrail
    guardrailId string
    Unique id for the guardrail
    kmsKeyArn string
    The KMS key with which the guardrail was encrypted at rest
    name string
    Name of the guardrail
    sensitiveInformationPolicyConfig GuardrailSensitiveInformationPolicyConfig
    The sensitive information policy to configure for the guardrail.
    status GuardrailStatus
    The status of the guardrail.
    statusReasons string[]
    List of status reasons
    tags Tag[]
    List of Tags
    topicPolicyConfig GuardrailTopicPolicyConfig
    The topic policies to configure for the guardrail.
    updatedAt string
    Time Stamp
    version string
    Guardrail version
    wordPolicyConfig GuardrailWordPolicyConfig
    The word policy you configure for the guardrail.
    automated_reasoning_policy_config GuardrailAutomatedReasoningPolicyConfig
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    blocked_input_messaging str
    Messaging for when violations are detected in text
    blocked_outputs_messaging str
    Messaging for when violations are detected in text
    content_policy_config GuardrailContentPolicyConfig
    The content filter policies to configure for the guardrail.
    contextual_grounding_policy_config GuardrailContextualGroundingPolicyConfig
    created_at str
    Time Stamp
    cross_region_config GuardrailCrossRegionConfig

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    description str
    Description of the guardrail or its version
    failure_recommendations Sequence[str]
    List of failure recommendations
    guardrail_arn str
    Arn representation for the guardrail
    guardrail_id str
    Unique id for the guardrail
    kms_key_arn str
    The KMS key with which the guardrail was encrypted at rest
    name str
    Name of the guardrail
    sensitive_information_policy_config GuardrailSensitiveInformationPolicyConfig
    The sensitive information policy to configure for the guardrail.
    status GuardrailStatus
    The status of the guardrail.
    status_reasons Sequence[str]
    List of status reasons
    tags Sequence[root_Tag]
    List of Tags
    topic_policy_config GuardrailTopicPolicyConfig
    The topic policies to configure for the guardrail.
    updated_at str
    Time Stamp
    version str
    Guardrail version
    word_policy_config GuardrailWordPolicyConfig
    The word policy you configure for the guardrail.
    automatedReasoningPolicyConfig Property Map
    Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
    blockedInputMessaging String
    Messaging for when violations are detected in text
    blockedOutputsMessaging String
    Messaging for when violations are detected in text
    contentPolicyConfig Property Map
    The content filter policies to configure for the guardrail.
    contextualGroundingPolicyConfig Property Map
    createdAt String
    Time Stamp
    crossRegionConfig Property Map

    The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination AWS Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

    For more information, see the Amazon Bedrock User Guide .

    description String
    Description of the guardrail or its version
    failureRecommendations List<String>
    List of failure recommendations
    guardrailArn String
    Arn representation for the guardrail
    guardrailId String
    Unique id for the guardrail
    kmsKeyArn String
    The KMS key with which the guardrail was encrypted at rest
    name String
    Name of the guardrail
    sensitiveInformationPolicyConfig Property Map
    The sensitive information policy to configure for the guardrail.
    status "CREATING" | "UPDATING" | "VERSIONING" | "READY" | "FAILED" | "DELETING"
    The status of the guardrail.
    statusReasons List<String>
    List of status reasons
    tags List<Property Map>
    List of Tags
    topicPolicyConfig Property Map
    The topic policies to configure for the guardrail.
    updatedAt String
    Time Stamp
    version String
    Guardrail version
    wordPolicyConfig Property Map
    The word policy you configure for the guardrail.

    Supporting Types

    GuardrailAutomatedReasoningPolicyConfig

    Policies List<string>
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    ConfidenceThreshold double
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    Policies []string
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    ConfidenceThreshold float64
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    policies list(string)
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    confidence_threshold number
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    policies List<String>
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    confidenceThreshold Double
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    policies string[]
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    confidenceThreshold number
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    policies Sequence[str]
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    confidence_threshold float
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
    policies List<String>
    The list of Automated Reasoning policy ARNs to include in the guardrail configuration
    confidenceThreshold Number
    The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.

    GuardrailContentFilterAction

    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    GuardrailContentFilterActionBlockBLOCK
    GuardrailContentFilterActionNoneNONE
    Value
    BLOCK
    NONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BLOCKBLOCK
    NONENONE
    Value
    BLOCK
    NONE

    GuardrailContentFilterConfig

    InputStrength Pulumi.AwsNative.Bedrock.GuardrailFilterStrength
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    OutputStrength Pulumi.AwsNative.Bedrock.GuardrailFilterStrength
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    Type Pulumi.AwsNative.Bedrock.GuardrailContentFilterType
    The harmful category that the content filter is applied to.
    InputAction Pulumi.AwsNative.Bedrock.GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    InputModalities List<Pulumi.AwsNative.Bedrock.GuardrailModality>
    List of modalities
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputModalities List<Pulumi.AwsNative.Bedrock.GuardrailModality>
    List of modalities
    InputStrength GuardrailFilterStrength
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    OutputStrength GuardrailFilterStrength
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    Type GuardrailContentFilterType
    The harmful category that the content filter is applied to.
    InputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    InputModalities []GuardrailModality
    List of modalities
    OutputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputModalities []GuardrailModality
    List of modalities
    input_strength "NONE" | "LOW" | "MEDIUM" | "HIGH"
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    output_strength "NONE" | "LOW" | "MEDIUM" | "HIGH"
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    type "SEXUAL" | "VIOLENCE" | "HATE" | "INSULTS" | "MISCONDUCT" | "PROMPT_ATTACK"
    The harmful category that the content filter is applied to.
    input_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    input_modalities list("TEXT" | "IMAGE")
    List of modalities
    output_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_modalities list("TEXT" | "IMAGE")
    List of modalities
    inputStrength GuardrailFilterStrength
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    outputStrength GuardrailFilterStrength
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    type GuardrailContentFilterType
    The harmful category that the content filter is applied to.
    inputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    inputModalities List<GuardrailModality>
    List of modalities
    outputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputModalities List<GuardrailModality>
    List of modalities
    inputStrength GuardrailFilterStrength
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    outputStrength GuardrailFilterStrength
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    type GuardrailContentFilterType
    The harmful category that the content filter is applied to.
    inputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    inputModalities GuardrailModality[]
    List of modalities
    outputAction GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputModalities GuardrailModality[]
    List of modalities
    input_strength GuardrailFilterStrength
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    output_strength GuardrailFilterStrength
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    type GuardrailContentFilterType
    The harmful category that the content filter is applied to.
    input_action GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    input_modalities Sequence[GuardrailModality]
    List of modalities
    output_action GuardrailContentFilterAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_modalities Sequence[GuardrailModality]
    List of modalities
    inputStrength "NONE" | "LOW" | "MEDIUM" | "HIGH"
    The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    outputStrength "NONE" | "LOW" | "MEDIUM" | "HIGH"
    The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
    type "SEXUAL" | "VIOLENCE" | "HATE" | "INSULTS" | "MISCONDUCT" | "PROMPT_ATTACK"
    The harmful category that the content filter is applied to.
    inputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    inputModalities List<"TEXT" | "IMAGE">
    List of modalities
    outputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputModalities List<"TEXT" | "IMAGE">
    List of modalities

    GuardrailContentFilterType

    NameValue
    SexualSEXUAL
    ViolenceVIOLENCE
    HateHATE
    InsultsINSULTS
    MisconductMISCONDUCT
    PromptAttackPROMPT_ATTACK
    NameValue
    GuardrailContentFilterTypeSexualSEXUAL
    GuardrailContentFilterTypeViolenceVIOLENCE
    GuardrailContentFilterTypeHateHATE
    GuardrailContentFilterTypeInsultsINSULTS
    GuardrailContentFilterTypeMisconductMISCONDUCT
    GuardrailContentFilterTypePromptAttackPROMPT_ATTACK
    Value
    SEXUAL
    VIOLENCE
    HATE
    INSULTS
    MISCONDUCT
    PROMPT_ATTACK
    NameValue
    SexualSEXUAL
    ViolenceVIOLENCE
    HateHATE
    InsultsINSULTS
    MisconductMISCONDUCT
    PromptAttackPROMPT_ATTACK
    NameValue
    SexualSEXUAL
    ViolenceVIOLENCE
    HateHATE
    InsultsINSULTS
    MisconductMISCONDUCT
    PromptAttackPROMPT_ATTACK
    NameValue
    SEXUALSEXUAL
    VIOLENCEVIOLENCE
    HATEHATE
    INSULTSINSULTS
    MISCONDUCTMISCONDUCT
    PROMPT_ATTACKPROMPT_ATTACK
    Value
    SEXUAL
    VIOLENCE
    HATE
    INSULTS
    MISCONDUCT
    PROMPT_ATTACK

    GuardrailContentFiltersTierName

    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    GuardrailContentFiltersTierNameClassicCLASSIC
    GuardrailContentFiltersTierNameStandardSTANDARD
    Value
    CLASSIC
    STANDARD
    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    CLASSICCLASSIC
    STANDARDSTANDARD
    Value
    CLASSIC
    STANDARD

    GuardrailContentPolicyConfig

    FiltersConfig []GuardrailContentFilterConfig
    List of content filter configs in content policy.
    ContentFiltersTierConfig GuardrailContentPolicyConfigContentFiltersTierConfigProperties
    Guardrail tier config for content policy
    filters_config list(object)
    List of content filter configs in content policy.
    content_filters_tier_config object
    Guardrail tier config for content policy
    filtersConfig List<GuardrailContentFilterConfig>
    List of content filter configs in content policy.
    contentFiltersTierConfig GuardrailContentPolicyConfigContentFiltersTierConfigProperties
    Guardrail tier config for content policy
    filtersConfig GuardrailContentFilterConfig[]
    List of content filter configs in content policy.
    contentFiltersTierConfig GuardrailContentPolicyConfigContentFiltersTierConfigProperties
    Guardrail tier config for content policy
    filtersConfig List<Property Map>
    List of content filter configs in content policy.
    contentFiltersTierConfig Property Map
    Guardrail tier config for content policy

    GuardrailContentPolicyConfigContentFiltersTierConfigProperties

    GuardrailContextualGroundingAction

    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    GuardrailContextualGroundingActionBlockBLOCK
    GuardrailContextualGroundingActionNoneNONE
    Value
    BLOCK
    NONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BLOCKBLOCK
    NONENONE
    Value
    BLOCK
    NONE

    GuardrailContextualGroundingFilterConfig

    Threshold double
    The threshold for this filter.
    Type Pulumi.AwsNative.Bedrock.GuardrailContextualGroundingFilterType
    The filter details for the guardrails contextual grounding filter.
    Action Pulumi.AwsNative.Bedrock.GuardrailContextualGroundingAction
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    Enabled bool
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Threshold float64
    The threshold for this filter.
    Type GuardrailContextualGroundingFilterType
    The filter details for the guardrails contextual grounding filter.
    Action GuardrailContextualGroundingAction
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    Enabled bool
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    threshold number
    The threshold for this filter.
    type "GROUNDING" | "RELEVANCE"
    The filter details for the guardrails contextual grounding filter.
    action "BLOCK" | "NONE"
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    enabled bool
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    threshold Double
    The threshold for this filter.
    type GuardrailContextualGroundingFilterType
    The filter details for the guardrails contextual grounding filter.
    action GuardrailContextualGroundingAction
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    enabled Boolean
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    threshold number
    The threshold for this filter.
    type GuardrailContextualGroundingFilterType
    The filter details for the guardrails contextual grounding filter.
    action GuardrailContextualGroundingAction
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    enabled boolean
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    threshold float
    The threshold for this filter.
    type GuardrailContextualGroundingFilterType
    The filter details for the guardrails contextual grounding filter.
    action GuardrailContextualGroundingAction
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    enabled bool
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    threshold Number
    The threshold for this filter.
    type "GROUNDING" | "RELEVANCE"
    The filter details for the guardrails contextual grounding filter.
    action "BLOCK" | "NONE"
    Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    enabled Boolean
    Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailContextualGroundingFilterType

    NameValue
    GroundingGROUNDING
    RelevanceRELEVANCE
    NameValue
    GuardrailContextualGroundingFilterTypeGroundingGROUNDING
    GuardrailContextualGroundingFilterTypeRelevanceRELEVANCE
    Value
    GROUNDING
    RELEVANCE
    NameValue
    GroundingGROUNDING
    RelevanceRELEVANCE
    NameValue
    GroundingGROUNDING
    RelevanceRELEVANCE
    NameValue
    GROUNDINGGROUNDING
    RELEVANCERELEVANCE
    Value
    GROUNDING
    RELEVANCE

    GuardrailContextualGroundingPolicyConfig

    FiltersConfig []GuardrailContextualGroundingFilterConfig
    List of contextual grounding filter configs.
    filters_config list(object)
    List of contextual grounding filter configs.
    filtersConfig List<GuardrailContextualGroundingFilterConfig>
    List of contextual grounding filter configs.
    filtersConfig GuardrailContextualGroundingFilterConfig[]
    List of contextual grounding filter configs.
    filters_config Sequence[GuardrailContextualGroundingFilterConfig]
    List of contextual grounding filter configs.
    filtersConfig List<Property Map>
    List of contextual grounding filter configs.

    GuardrailCrossRegionConfig

    GuardrailProfileArn string
    The Amazon Resource Name (ARN) of the guardrail profile
    GuardrailProfileArn string
    The Amazon Resource Name (ARN) of the guardrail profile
    guardrail_profile_arn string
    The Amazon Resource Name (ARN) of the guardrail profile
    guardrailProfileArn String
    The Amazon Resource Name (ARN) of the guardrail profile
    guardrailProfileArn string
    The Amazon Resource Name (ARN) of the guardrail profile
    guardrail_profile_arn str
    The Amazon Resource Name (ARN) of the guardrail profile
    guardrailProfileArn String
    The Amazon Resource Name (ARN) of the guardrail profile

    GuardrailFilterStrength

    NameValue
    NoneNONE
    LowLOW
    MediumMEDIUM
    HighHIGH
    NameValue
    GuardrailFilterStrengthNoneNONE
    GuardrailFilterStrengthLowLOW
    GuardrailFilterStrengthMediumMEDIUM
    GuardrailFilterStrengthHighHIGH
    Value
    NONE
    LOW
    MEDIUM
    HIGH
    NameValue
    NoneNONE
    LowLOW
    MediumMEDIUM
    HighHIGH
    NameValue
    NoneNONE
    LowLOW
    MediumMEDIUM
    HighHIGH
    NameValue
    NONENONE
    LOWLOW
    MEDIUMMEDIUM
    HIGHHIGH
    Value
    NONE
    LOW
    MEDIUM
    HIGH

    GuardrailManagedWordsConfig

    Type Pulumi.AwsNative.Bedrock.GuardrailManagedWordsType
    The managed word type to configure for the guardrail.
    InputAction Pulumi.AwsNative.Bedrock.GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Type GuardrailManagedWordsType
    The managed word type to configure for the guardrail.
    InputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    type "PROFANITY"
    The managed word type to configure for the guardrail.
    input_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    type GuardrailManagedWordsType
    The managed word type to configure for the guardrail.
    inputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    type GuardrailManagedWordsType
    The managed word type to configure for the guardrail.
    inputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    type GuardrailManagedWordsType
    The managed word type to configure for the guardrail.
    input_action GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    type "PROFANITY"
    The managed word type to configure for the guardrail.
    inputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailManagedWordsType

    NameValue
    ProfanityPROFANITY
    NameValue
    GuardrailManagedWordsTypeProfanityPROFANITY
    Value
    PROFANITY
    NameValue
    ProfanityPROFANITY
    NameValue
    ProfanityPROFANITY
    NameValue
    PROFANITYPROFANITY
    Value
    PROFANITY

    GuardrailModality

    NameValue
    TextTEXT
    ImageIMAGE
    NameValue
    GuardrailModalityTextTEXT
    GuardrailModalityImageIMAGE
    Value
    TEXT
    IMAGE
    NameValue
    TextTEXT
    ImageIMAGE
    NameValue
    TextTEXT
    ImageIMAGE
    NameValue
    TEXTTEXT
    IMAGEIMAGE
    Value
    TEXT
    IMAGE

    GuardrailPiiEntityConfig

    Action Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    Configure guardrail action when the PII entity is detected.
    Type Pulumi.AwsNative.Bedrock.GuardrailPiiEntityType

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    InputAction Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Action GuardrailSensitiveInformationAction
    Configure guardrail action when the PII entity is detected.
    Type GuardrailPiiEntityType

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    InputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action "BLOCK" | "ANONYMIZE" | "NONE"
    Configure guardrail action when the PII entity is detected.
    type "ADDRESS" | "AGE" | "AWS_ACCESS_KEY" | "AWS_SECRET_KEY" | "CA_HEALTH_NUMBER" | "CA_SOCIAL_INSURANCE_NUMBER" | "CREDIT_DEBIT_CARD_CVV" | "CREDIT_DEBIT_CARD_EXPIRY" | "CREDIT_DEBIT_CARD_NUMBER" | "DRIVER_ID" | "EMAIL" | "INTERNATIONAL_BANK_ACCOUNT_NUMBER" | "IP_ADDRESS" | "LICENSE_PLATE" | "MAC_ADDRESS" | "NAME" | "PASSWORD" | "PHONE" | "PIN" | "SWIFT_CODE" | "UK_NATIONAL_HEALTH_SERVICE_NUMBER" | "UK_NATIONAL_INSURANCE_NUMBER" | "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER" | "URL" | "USERNAME" | "US_BANK_ACCOUNT_NUMBER" | "US_BANK_ROUTING_NUMBER" | "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER" | "US_PASSPORT_NUMBER" | "US_SOCIAL_SECURITY_NUMBER" | "VEHICLE_IDENTIFICATION_NUMBER"

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    input_action "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    Configure guardrail action when the PII entity is detected.
    type GuardrailPiiEntityType

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    inputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    Configure guardrail action when the PII entity is detected.
    type GuardrailPiiEntityType

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    inputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    Configure guardrail action when the PII entity is detected.
    type GuardrailPiiEntityType

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    input_action GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action "BLOCK" | "ANONYMIZE" | "NONE"
    Configure guardrail action when the PII entity is detected.
    type "ADDRESS" | "AGE" | "AWS_ACCESS_KEY" | "AWS_SECRET_KEY" | "CA_HEALTH_NUMBER" | "CA_SOCIAL_INSURANCE_NUMBER" | "CREDIT_DEBIT_CARD_CVV" | "CREDIT_DEBIT_CARD_EXPIRY" | "CREDIT_DEBIT_CARD_NUMBER" | "DRIVER_ID" | "EMAIL" | "INTERNATIONAL_BANK_ACCOUNT_NUMBER" | "IP_ADDRESS" | "LICENSE_PLATE" | "MAC_ADDRESS" | "NAME" | "PASSWORD" | "PHONE" | "PIN" | "SWIFT_CODE" | "UK_NATIONAL_HEALTH_SERVICE_NUMBER" | "UK_NATIONAL_INSURANCE_NUMBER" | "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER" | "URL" | "USERNAME" | "US_BANK_ACCOUNT_NUMBER" | "US_BANK_ROUTING_NUMBER" | "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER" | "US_PASSPORT_NUMBER" | "US_SOCIAL_SECURITY_NUMBER" | "VEHICLE_IDENTIFICATION_NUMBER"

    Configure guardrail type when the PII entity is detected.

    The following PIIs are used to block or mask sensitive information:

    • General

    • ADDRESS

    A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.

    • AGE

    An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.

    • NAME

    An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.

    • EMAIL

    An email address, such as marymajor@email.com .

    • PHONE

    A phone number. This entity type also includes fax and pager numbers.

    • USERNAME

    A user name that identifies an account, such as a login name, screen name, nick name, or handle.

    • PASSWORD

    An alphanumeric string that is used as a password, such as "* *very20special#pass** ".

    • DRIVER_ID

    The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.

    • LICENSE_PLATE

    A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.

    • VEHICLE_IDENTIFICATION_NUMBER

    A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.

    • Finance

    • CREDIT_DEBIT_CARD_CVV

    A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.

    • CREDIT_DEBIT_CARD_EXPIRY

    The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY . Guardrails recognizes expiration dates such as 01/21 , 01/2021 , and Jan 2021 .

    • CREDIT_DEBIT_CARD_NUMBER

    The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.

    • PIN

    A four-digit personal identification number (PIN) with which you can access your bank account.

    • INTERNATIONAL_BANK_ACCOUNT_NUMBER

    An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure .

    • SWIFT_CODE

    A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.

    SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.

    • IT

    • IP_ADDRESS

    An IPv4 address, such as 198.51.100.0 .

    • MAC_ADDRESS

    A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).

    • URL

    A web address, such as www.example.com .

    • AWS_ACCESS_KEY

    A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • AWS_SECRET_KEY

    A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic AWS requests cryptographically.

    • USA specific

    • US_BANK_ACCOUNT_NUMBER

    A US bank account number, which is typically 10 to 12 digits long.

    • US_BANK_ROUTING_NUMBER

    A US bank account routing number. These are typically nine digits long,

    • US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER

    A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.

    • US_PASSPORT_NUMBER

    A US passport number. Passport numbers range from six to nine alphanumeric characters.

    • US_SOCIAL_SECURITY_NUMBER

    A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.

    • Canada specific

    • CA_HEALTH_NUMBER

    A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.

    • CA_SOCIAL_INSURANCE_NUMBER

    A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.

    The SIN is formatted as three groups of three digits, such as 123-456-789 . A SIN can be validated through a simple check-digit process called the Luhn algorithm .

    • UK Specific

    • UK_NATIONAL_HEALTH_SERVICE_NUMBER

    A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456 . The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.

    • UK_NATIONAL_INSURANCE_NUMBER

    A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.

    The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.

    • UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER

    A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.

    • Custom

    • Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..

    inputAction "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • ANONYMIZE – Mask the content and replace it with identifier tags.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailPiiEntityType

    NameValue
    AddressADDRESS
    AgeAGE
    AwsAccessKeyAWS_ACCESS_KEY
    AwsSecretKeyAWS_SECRET_KEY
    CaHealthNumberCA_HEALTH_NUMBER
    CaSocialInsuranceNumberCA_SOCIAL_INSURANCE_NUMBER
    CreditDebitCardCvvCREDIT_DEBIT_CARD_CVV
    CreditDebitCardExpiryCREDIT_DEBIT_CARD_EXPIRY
    CreditDebitCardNumberCREDIT_DEBIT_CARD_NUMBER
    DriverIdDRIVER_ID
    EmailEMAIL
    InternationalBankAccountNumberINTERNATIONAL_BANK_ACCOUNT_NUMBER
    IpAddressIP_ADDRESS
    LicensePlateLICENSE_PLATE
    MacAddressMAC_ADDRESS
    NameNAME
    PasswordPASSWORD
    PhonePHONE
    PinPIN
    SwiftCodeSWIFT_CODE
    UkNationalHealthServiceNumberUK_NATIONAL_HEALTH_SERVICE_NUMBER
    UkNationalInsuranceNumberUK_NATIONAL_INSURANCE_NUMBER
    UkUniqueTaxpayerReferenceNumberUK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    UrlURL
    UsernameUSERNAME
    UsBankAccountNumberUS_BANK_ACCOUNT_NUMBER
    UsBankRoutingNumberUS_BANK_ROUTING_NUMBER
    UsIndividualTaxIdentificationNumberUS_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    UsPassportNumberUS_PASSPORT_NUMBER
    UsSocialSecurityNumberUS_SOCIAL_SECURITY_NUMBER
    VehicleIdentificationNumberVEHICLE_IDENTIFICATION_NUMBER
    NameValue
    GuardrailPiiEntityTypeAddressADDRESS
    GuardrailPiiEntityTypeAgeAGE
    GuardrailPiiEntityTypeAwsAccessKeyAWS_ACCESS_KEY
    GuardrailPiiEntityTypeAwsSecretKeyAWS_SECRET_KEY
    GuardrailPiiEntityTypeCaHealthNumberCA_HEALTH_NUMBER
    GuardrailPiiEntityTypeCaSocialInsuranceNumberCA_SOCIAL_INSURANCE_NUMBER
    GuardrailPiiEntityTypeCreditDebitCardCvvCREDIT_DEBIT_CARD_CVV
    GuardrailPiiEntityTypeCreditDebitCardExpiryCREDIT_DEBIT_CARD_EXPIRY
    GuardrailPiiEntityTypeCreditDebitCardNumberCREDIT_DEBIT_CARD_NUMBER
    GuardrailPiiEntityTypeDriverIdDRIVER_ID
    GuardrailPiiEntityTypeEmailEMAIL
    GuardrailPiiEntityTypeInternationalBankAccountNumberINTERNATIONAL_BANK_ACCOUNT_NUMBER
    GuardrailPiiEntityTypeIpAddressIP_ADDRESS
    GuardrailPiiEntityTypeLicensePlateLICENSE_PLATE
    GuardrailPiiEntityTypeMacAddressMAC_ADDRESS
    GuardrailPiiEntityTypeNameNAME
    GuardrailPiiEntityTypePasswordPASSWORD
    GuardrailPiiEntityTypePhonePHONE
    GuardrailPiiEntityTypePinPIN
    GuardrailPiiEntityTypeSwiftCodeSWIFT_CODE
    GuardrailPiiEntityTypeUkNationalHealthServiceNumberUK_NATIONAL_HEALTH_SERVICE_NUMBER
    GuardrailPiiEntityTypeUkNationalInsuranceNumberUK_NATIONAL_INSURANCE_NUMBER
    GuardrailPiiEntityTypeUkUniqueTaxpayerReferenceNumberUK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    GuardrailPiiEntityTypeUrlURL
    GuardrailPiiEntityTypeUsernameUSERNAME
    GuardrailPiiEntityTypeUsBankAccountNumberUS_BANK_ACCOUNT_NUMBER
    GuardrailPiiEntityTypeUsBankRoutingNumberUS_BANK_ROUTING_NUMBER
    GuardrailPiiEntityTypeUsIndividualTaxIdentificationNumberUS_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    GuardrailPiiEntityTypeUsPassportNumberUS_PASSPORT_NUMBER
    GuardrailPiiEntityTypeUsSocialSecurityNumberUS_SOCIAL_SECURITY_NUMBER
    GuardrailPiiEntityTypeVehicleIdentificationNumberVEHICLE_IDENTIFICATION_NUMBER
    Value
    ADDRESS
    AGE
    AWS_ACCESS_KEY
    AWS_SECRET_KEY
    CA_HEALTH_NUMBER
    CA_SOCIAL_INSURANCE_NUMBER
    CREDIT_DEBIT_CARD_CVV
    CREDIT_DEBIT_CARD_EXPIRY
    CREDIT_DEBIT_CARD_NUMBER
    DRIVER_ID
    EMAIL
    INTERNATIONAL_BANK_ACCOUNT_NUMBER
    IP_ADDRESS
    LICENSE_PLATE
    MAC_ADDRESS
    NAME
    PASSWORD
    PHONE
    PIN
    SWIFT_CODE
    UK_NATIONAL_HEALTH_SERVICE_NUMBER
    UK_NATIONAL_INSURANCE_NUMBER
    UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    URL
    USERNAME
    US_BANK_ACCOUNT_NUMBER
    US_BANK_ROUTING_NUMBER
    US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    US_PASSPORT_NUMBER
    US_SOCIAL_SECURITY_NUMBER
    VEHICLE_IDENTIFICATION_NUMBER
    NameValue
    AddressADDRESS
    AgeAGE
    AwsAccessKeyAWS_ACCESS_KEY
    AwsSecretKeyAWS_SECRET_KEY
    CaHealthNumberCA_HEALTH_NUMBER
    CaSocialInsuranceNumberCA_SOCIAL_INSURANCE_NUMBER
    CreditDebitCardCvvCREDIT_DEBIT_CARD_CVV
    CreditDebitCardExpiryCREDIT_DEBIT_CARD_EXPIRY
    CreditDebitCardNumberCREDIT_DEBIT_CARD_NUMBER
    DriverIdDRIVER_ID
    EmailEMAIL
    InternationalBankAccountNumberINTERNATIONAL_BANK_ACCOUNT_NUMBER
    IpAddressIP_ADDRESS
    LicensePlateLICENSE_PLATE
    MacAddressMAC_ADDRESS
    NameNAME
    PasswordPASSWORD
    PhonePHONE
    PinPIN
    SwiftCodeSWIFT_CODE
    UkNationalHealthServiceNumberUK_NATIONAL_HEALTH_SERVICE_NUMBER
    UkNationalInsuranceNumberUK_NATIONAL_INSURANCE_NUMBER
    UkUniqueTaxpayerReferenceNumberUK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    UrlURL
    UsernameUSERNAME
    UsBankAccountNumberUS_BANK_ACCOUNT_NUMBER
    UsBankRoutingNumberUS_BANK_ROUTING_NUMBER
    UsIndividualTaxIdentificationNumberUS_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    UsPassportNumberUS_PASSPORT_NUMBER
    UsSocialSecurityNumberUS_SOCIAL_SECURITY_NUMBER
    VehicleIdentificationNumberVEHICLE_IDENTIFICATION_NUMBER
    NameValue
    AddressADDRESS
    AgeAGE
    AwsAccessKeyAWS_ACCESS_KEY
    AwsSecretKeyAWS_SECRET_KEY
    CaHealthNumberCA_HEALTH_NUMBER
    CaSocialInsuranceNumberCA_SOCIAL_INSURANCE_NUMBER
    CreditDebitCardCvvCREDIT_DEBIT_CARD_CVV
    CreditDebitCardExpiryCREDIT_DEBIT_CARD_EXPIRY
    CreditDebitCardNumberCREDIT_DEBIT_CARD_NUMBER
    DriverIdDRIVER_ID
    EmailEMAIL
    InternationalBankAccountNumberINTERNATIONAL_BANK_ACCOUNT_NUMBER
    IpAddressIP_ADDRESS
    LicensePlateLICENSE_PLATE
    MacAddressMAC_ADDRESS
    NameNAME
    PasswordPASSWORD
    PhonePHONE
    PinPIN
    SwiftCodeSWIFT_CODE
    UkNationalHealthServiceNumberUK_NATIONAL_HEALTH_SERVICE_NUMBER
    UkNationalInsuranceNumberUK_NATIONAL_INSURANCE_NUMBER
    UkUniqueTaxpayerReferenceNumberUK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    UrlURL
    UsernameUSERNAME
    UsBankAccountNumberUS_BANK_ACCOUNT_NUMBER
    UsBankRoutingNumberUS_BANK_ROUTING_NUMBER
    UsIndividualTaxIdentificationNumberUS_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    UsPassportNumberUS_PASSPORT_NUMBER
    UsSocialSecurityNumberUS_SOCIAL_SECURITY_NUMBER
    VehicleIdentificationNumberVEHICLE_IDENTIFICATION_NUMBER
    NameValue
    ADDRESSADDRESS
    AGEAGE
    AWS_ACCESS_KEYAWS_ACCESS_KEY
    AWS_SECRET_KEYAWS_SECRET_KEY
    CA_HEALTH_NUMBERCA_HEALTH_NUMBER
    CA_SOCIAL_INSURANCE_NUMBERCA_SOCIAL_INSURANCE_NUMBER
    CREDIT_DEBIT_CARD_CVVCREDIT_DEBIT_CARD_CVV
    CREDIT_DEBIT_CARD_EXPIRYCREDIT_DEBIT_CARD_EXPIRY
    CREDIT_DEBIT_CARD_NUMBERCREDIT_DEBIT_CARD_NUMBER
    DRIVER_IDDRIVER_ID
    EMAILEMAIL
    INTERNATIONAL_BANK_ACCOUNT_NUMBERINTERNATIONAL_BANK_ACCOUNT_NUMBER
    IP_ADDRESSIP_ADDRESS
    LICENSE_PLATELICENSE_PLATE
    MAC_ADDRESSMAC_ADDRESS
    NAMENAME
    PASSWORDPASSWORD
    PHONEPHONE
    PINPIN
    SWIFT_CODESWIFT_CODE
    UK_NATIONAL_HEALTH_SERVICE_NUMBERUK_NATIONAL_HEALTH_SERVICE_NUMBER
    UK_NATIONAL_INSURANCE_NUMBERUK_NATIONAL_INSURANCE_NUMBER
    UK_UNIQUE_TAXPAYER_REFERENCE_NUMBERUK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    URLURL
    USERNAMEUSERNAME
    US_BANK_ACCOUNT_NUMBERUS_BANK_ACCOUNT_NUMBER
    US_BANK_ROUTING_NUMBERUS_BANK_ROUTING_NUMBER
    US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBERUS_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    US_PASSPORT_NUMBERUS_PASSPORT_NUMBER
    US_SOCIAL_SECURITY_NUMBERUS_SOCIAL_SECURITY_NUMBER
    VEHICLE_IDENTIFICATION_NUMBERVEHICLE_IDENTIFICATION_NUMBER
    Value
    ADDRESS
    AGE
    AWS_ACCESS_KEY
    AWS_SECRET_KEY
    CA_HEALTH_NUMBER
    CA_SOCIAL_INSURANCE_NUMBER
    CREDIT_DEBIT_CARD_CVV
    CREDIT_DEBIT_CARD_EXPIRY
    CREDIT_DEBIT_CARD_NUMBER
    DRIVER_ID
    EMAIL
    INTERNATIONAL_BANK_ACCOUNT_NUMBER
    IP_ADDRESS
    LICENSE_PLATE
    MAC_ADDRESS
    NAME
    PASSWORD
    PHONE
    PIN
    SWIFT_CODE
    UK_NATIONAL_HEALTH_SERVICE_NUMBER
    UK_NATIONAL_INSURANCE_NUMBER
    UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
    URL
    USERNAME
    US_BANK_ACCOUNT_NUMBER
    US_BANK_ROUTING_NUMBER
    US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
    US_PASSPORT_NUMBER
    US_SOCIAL_SECURITY_NUMBER
    VEHICLE_IDENTIFICATION_NUMBER

    GuardrailRegexConfig

    Action Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    The guardrail action to configure when matching regular expression is detected.
    Name string
    The regex name.
    Pattern string
    The regex pattern.
    Description string
    The regex description.
    InputAction Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Action GuardrailSensitiveInformationAction
    The guardrail action to configure when matching regular expression is detected.
    Name string
    The regex name.
    Pattern string
    The regex pattern.
    Description string
    The regex description.
    InputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action "BLOCK" | "ANONYMIZE" | "NONE"
    The guardrail action to configure when matching regular expression is detected.
    name string
    The regex name.
    pattern string
    The regex pattern.
    description string
    The regex description.
    input_action "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    The guardrail action to configure when matching regular expression is detected.
    name String
    The regex name.
    pattern String
    The regex pattern.
    description String
    The regex description.
    inputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    The guardrail action to configure when matching regular expression is detected.
    name string
    The regex name.
    pattern string
    The regex pattern.
    description string
    The regex description.
    inputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action GuardrailSensitiveInformationAction
    The guardrail action to configure when matching regular expression is detected.
    name str
    The regex name.
    pattern str
    The regex pattern.
    description str
    The regex description.
    input_action GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action GuardrailSensitiveInformationAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    action "BLOCK" | "ANONYMIZE" | "NONE"
    The guardrail action to configure when matching regular expression is detected.
    name String
    The regex name.
    pattern String
    The regex pattern.
    description String
    The regex description.
    inputAction "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction "BLOCK" | "ANONYMIZE" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailSensitiveInformationAction

    NameValue
    BlockBLOCK
    AnonymizeANONYMIZE
    NoneNONE
    NameValue
    GuardrailSensitiveInformationActionBlockBLOCK
    GuardrailSensitiveInformationActionAnonymizeANONYMIZE
    GuardrailSensitiveInformationActionNoneNONE
    Value
    BLOCK
    ANONYMIZE
    NONE
    NameValue
    BlockBLOCK
    AnonymizeANONYMIZE
    NoneNONE
    NameValue
    BlockBLOCK
    AnonymizeANONYMIZE
    NoneNONE
    NameValue
    BLOCKBLOCK
    ANONYMIZEANONYMIZE
    NONENONE
    Value
    BLOCK
    ANONYMIZE
    NONE

    GuardrailSensitiveInformationPolicyConfig

    GuardrailStatus

    NameValue
    CreatingCREATING
    UpdatingUPDATING
    VersioningVERSIONING
    ReadyREADY
    FailedFAILED
    DeletingDELETING
    NameValue
    GuardrailStatusCreatingCREATING
    GuardrailStatusUpdatingUPDATING
    GuardrailStatusVersioningVERSIONING
    GuardrailStatusReadyREADY
    GuardrailStatusFailedFAILED
    GuardrailStatusDeletingDELETING
    Value
    CREATING
    UPDATING
    VERSIONING
    READY
    FAILED
    DELETING
    NameValue
    CreatingCREATING
    UpdatingUPDATING
    VersioningVERSIONING
    ReadyREADY
    FailedFAILED
    DeletingDELETING
    NameValue
    CreatingCREATING
    UpdatingUPDATING
    VersioningVERSIONING
    ReadyREADY
    FailedFAILED
    DeletingDELETING
    NameValue
    CREATINGCREATING
    UPDATINGUPDATING
    VERSIONINGVERSIONING
    READYREADY
    FAILEDFAILED
    DELETINGDELETING
    Value
    CREATING
    UPDATING
    VERSIONING
    READY
    FAILED
    DELETING

    GuardrailTopicAction

    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    GuardrailTopicActionBlockBLOCK
    GuardrailTopicActionNoneNONE
    Value
    BLOCK
    NONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BLOCKBLOCK
    NONENONE
    Value
    BLOCK
    NONE

    GuardrailTopicConfig

    Definition string
    Definition of topic in topic policy
    Name string
    Name of topic in topic policy
    Type Pulumi.AwsNative.Bedrock.GuardrailTopicType
    Specifies to deny the topic.
    Examples List<string>
    List of text examples
    InputAction Pulumi.AwsNative.Bedrock.GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Definition string
    Definition of topic in topic policy
    Name string
    Name of topic in topic policy
    Type GuardrailTopicType
    Specifies to deny the topic.
    Examples []string
    List of text examples
    InputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    definition string
    Definition of topic in topic policy
    name string
    Name of topic in topic policy
    type "DENY"
    Specifies to deny the topic.
    examples list(string)
    List of text examples
    input_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    definition String
    Definition of topic in topic policy
    name String
    Name of topic in topic policy
    type GuardrailTopicType
    Specifies to deny the topic.
    examples List<String>
    List of text examples
    inputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    definition string
    Definition of topic in topic policy
    name string
    Name of topic in topic policy
    type GuardrailTopicType
    Specifies to deny the topic.
    examples string[]
    List of text examples
    inputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    definition str
    Definition of topic in topic policy
    name str
    Name of topic in topic policy
    type GuardrailTopicType
    Specifies to deny the topic.
    examples Sequence[str]
    List of text examples
    input_action GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action GuardrailTopicAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    definition String
    Definition of topic in topic policy
    name String
    Name of topic in topic policy
    type "DENY"
    Specifies to deny the topic.
    examples List<String>
    List of text examples
    inputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailTopicPolicyConfig

    TopicsConfig []GuardrailTopicConfig
    List of topic configs in topic policy.
    TopicsTierConfig GuardrailTopicPolicyConfigTopicsTierConfigProperties
    Guardrail tier config for topic policy
    topics_config list(object)
    List of topic configs in topic policy.
    topics_tier_config object
    Guardrail tier config for topic policy
    topicsConfig List<GuardrailTopicConfig>
    List of topic configs in topic policy.
    topicsTierConfig GuardrailTopicPolicyConfigTopicsTierConfigProperties
    Guardrail tier config for topic policy
    topicsConfig GuardrailTopicConfig[]
    List of topic configs in topic policy.
    topicsTierConfig GuardrailTopicPolicyConfigTopicsTierConfigProperties
    Guardrail tier config for topic policy
    topics_config Sequence[GuardrailTopicConfig]
    List of topic configs in topic policy.
    topics_tier_config GuardrailTopicPolicyConfigTopicsTierConfigProperties
    Guardrail tier config for topic policy
    topicsConfig List<Property Map>
    List of topic configs in topic policy.
    topicsTierConfig Property Map
    Guardrail tier config for topic policy

    GuardrailTopicPolicyConfigTopicsTierConfigProperties

    GuardrailTopicType

    NameValue
    DenyDENY
    NameValue
    GuardrailTopicTypeDenyDENY
    Value
    DENY
    NameValue
    DenyDENY
    NameValue
    DenyDENY
    NameValue
    DENYDENY
    Value
    DENY

    GuardrailTopicsTierName

    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    GuardrailTopicsTierNameClassicCLASSIC
    GuardrailTopicsTierNameStandardSTANDARD
    Value
    CLASSIC
    STANDARD
    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    ClassicCLASSIC
    StandardSTANDARD
    NameValue
    CLASSICCLASSIC
    STANDARDSTANDARD
    Value
    CLASSIC
    STANDARD

    GuardrailWordAction

    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    GuardrailWordActionBlockBLOCK
    GuardrailWordActionNoneNONE
    Value
    BLOCK
    NONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BlockBLOCK
    NoneNONE
    NameValue
    BLOCKBLOCK
    NONENONE
    Value
    BLOCK
    NONE

    GuardrailWordConfig

    Text string
    The custom word text.
    InputAction Pulumi.AwsNative.Bedrock.GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction Pulumi.AwsNative.Bedrock.GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    Text string
    The custom word text.
    InputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    InputEnabled bool
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    OutputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    OutputEnabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    text string
    The custom word text.
    input_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    text String
    The custom word text.
    inputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    text string
    The custom word text.
    inputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled boolean
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    text str
    The custom word text.
    input_action GuardrailWordAction
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    input_enabled bool
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    output_action GuardrailWordAction
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    output_enabled bool
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    text String
    The custom word text.
    inputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the input. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    inputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
    outputAction "BLOCK" | "NONE"
    Specifies the action to take when harmful content is detected in the output. Supported values include:

    • BLOCK – Block the content and replace it with blocked messaging.
    • NONE – Take no action but return detection information in the trace response.
    outputEnabled Boolean
    Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

    GuardrailWordPolicyConfig

    ManagedWordListsConfig []GuardrailManagedWordsConfig
    A config for the list of managed words.
    WordsConfig []GuardrailWordConfig
    List of custom word configs.
    managed_word_lists_config list(object)
    A config for the list of managed words.
    words_config list(object)
    List of custom word configs.
    managedWordListsConfig List<GuardrailManagedWordsConfig>
    A config for the list of managed words.
    wordsConfig List<GuardrailWordConfig>
    List of custom word configs.
    managedWordListsConfig GuardrailManagedWordsConfig[]
    A config for the list of managed words.
    wordsConfig GuardrailWordConfig[]
    List of custom word configs.
    managed_word_lists_config Sequence[GuardrailManagedWordsConfig]
    A config for the list of managed words.
    words_config Sequence[GuardrailWordConfig]
    List of custom word configs.
    managedWordListsConfig List<Property Map>
    A config for the list of managed words.
    wordsConfig List<Property Map>
    List of custom word configs.

    Tag

    Key string
    The key name of the tag
    Value string
    The value of the tag
    Key string
    The key name of the tag
    Value string
    The value of the tag
    key string
    The key name of the tag
    value string
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag
    key string
    The key name of the tag
    value string
    The value of the tag
    key str
    The key name of the tag
    value str
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag

    Package Details

    Repository
    AWS Native pulumi/pulumi-aws-native
    License
    Apache-2.0
    aws-native logo aws-native logo AWS Cloud Control

    We recommend new projects start with resources from the AWS provider.

    Viewing docs for AWS Cloud Control v1.86.0
    published on Wednesday, Nov 18, 2026 by Pulumi

      Try Pulumi Cloud free.
      Your team will thank you.

      Start free trial