This product is not supported for your selected Datadog site. ().

aws_bedrock_guardrail

account_id

Type: STRING

blocked_input_messaging

Type: STRING
Provider name: blockedInputMessaging
Description: The message that the guardrail returns when it blocks a prompt.

blocked_outputs_messaging

Type: STRING
Provider name: blockedOutputsMessaging
Description: The message that the guardrail returns when it blocks a model response.

content_policy

Type: STRUCT
Provider name: contentPolicy
Description: The content policy that was configured for the guardrail.

  • filters
    Type: UNORDERED_LIST_STRUCT
    Provider name: filters
    Description: Contains the type of the content filter and how strongly it should apply to prompts and model responses.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • input_modalities
      Type: UNORDERED_LIST_STRING
      Provider name: inputModalities
      Description: The input modalities selected for the guardrail content filter.
    • input_strength
      Type: STRING
      Provider name: inputStrength
      Description: 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_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • output_modalities
      Type: UNORDERED_LIST_STRING
      Provider name: outputModalities
      Description: The output modalities selected for the guardrail content filter.
    • output_strength
      Type: STRING
      Provider name: outputStrength
      Description: 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
      Type: STRING
      Provider name: type
      Description: The harmful category that the content filter is applied to.
  • tier
    Type: STRUCT
    Provider name: tier
    Description: The tier that your guardrail uses for content filters.
    • tier_name
      Type: STRING
      Provider name: tierName
      Description: The tier that your guardrail uses for content filters. Valid values include:
      • CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
      • STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.

contextual_grounding_policy

Type: STRUCT
Provider name: contextualGroundingPolicy
Description: The contextual grounding policy used in the guardrail.

  • filters
    Type: UNORDERED_LIST_STRUCT
    Provider name: filters
    Description: The filter details for the guardrails contextual grounding policy.
    • action
      Type: STRING
      Provider name: action
      Description: 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
      Type: BOOLEAN
      Provider name: enabled
      Description: Indicates whether contextual grounding is enabled for evaluation. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • threshold
      Type: DOUBLE
      Provider name: threshold
      Description: The threshold details for the guardrails contextual grounding filter.
    • type
      Type: STRING
      Provider name: type
      Description: The filter type details for the guardrails contextual grounding filter.

created_at

Type: TIMESTAMP
Provider name: createdAt
Description: The date and time at which the guardrail was created.

cross_region_details

Type: STRUCT
Provider name: crossRegionDetails
Description: Details about the system-defined guardrail profile that you’re using with your guardrail, including the guardrail profile ID and Amazon Resource Name (ARN).

  • guardrail_profile_arn
    Type: STRING
    Provider name: guardrailProfileArn
    Description: The Amazon Resource Name (ARN) of the guardrail profile that you’re using with your guardrail.
  • guardrail_profile_id
    Type: STRING
    Provider name: guardrailProfileId
    Description: The ID of the guardrail profile that your guardrail is using. Profile availability depends on your current Amazon Web Services Region. For more information, see the Amazon Bedrock User Guide.

description

Type: STRING
Provider name: description
Description: The description of the guardrail.

failure_recommendations

Type: UNORDERED_LIST_STRING
Provider name: failureRecommendations
Description: Appears if the status of the guardrail is FAILED. A list of recommendations to carry out before retrying the request.

guardrail_arn

Type: STRING
Provider name: guardrailArn
Description: The ARN of the guardrail.

guardrail_id

Type: STRING
Provider name: guardrailId
Description: The unique identifier of the guardrail.

kms_key_arn

Type: STRING
Provider name: kmsKeyArn
Description: The ARN of the KMS key that encrypts the guardrail.

name

Type: STRING
Provider name: name
Description: The name of the guardrail.

sensitive_information_policy

Type: STRUCT
Provider name: sensitiveInformationPolicy
Description: The sensitive information policy that was configured for the guardrail.

  • pii_entities
    Type: UNORDERED_LIST_STRUCT
    Provider name: piiEntities
    Description: The list of PII entities configured for the guardrail.
    • action
      Type: STRING
      Provider name: action
      Description: The configured guardrail action when PII entity is detected.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • output_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • type
      Type: STRING
      Provider name: type
      Description: The type of PII entity. For example, Social Security Number.
  • regexes
    Type: UNORDERED_LIST_STRUCT
    Provider name: regexes
    Description: The list of regular expressions configured for the guardrail.
    • action
      Type: STRING
      Provider name: action
      Description: The action taken when a match to the regular expression is detected.
    • description
      Type: STRING
      Provider name: description
      Description: The description of the regular expression for the guardrail.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • name
      Type: STRING
      Provider name: name
      Description: The name of the regular expression for the guardrail.
    • output_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • pattern
      Type: STRING
      Provider name: pattern
      Description: The pattern of the regular expression configured for the guardrail.

status

Type: STRING
Provider name: status
Description: The status of the guardrail.

status_reasons

Type: UNORDERED_LIST_STRING
Provider name: statusReasons
Description: Appears if the status is FAILED. A list of reasons for why the guardrail failed to be created, updated, versioned, or deleted.

tags

Type: UNORDERED_LIST_STRING

topic_policy

Type: STRUCT
Provider name: topicPolicy
Description: The topic policy that was configured for the guardrail.

  • tier
    Type: STRUCT
    Provider name: tier
    Description: The tier that your guardrail uses for denied topic filters.
    • tier_name
      Type: STRING
      Provider name: tierName
      Description: The tier that your guardrail uses for denied topic filters. Valid values include:
      • CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
      • STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.
  • topics
    Type: UNORDERED_LIST_STRUCT
    Provider name: topics
    Description: A list of policies related to topics that the guardrail should deny.
    • definition
      Type: STRING
      Provider name: definition
      Description: A definition of the topic to deny.
    • examples
      Type: UNORDERED_LIST_STRING
      Provider name: examples
      Description: A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • name
      Type: STRING
      Provider name: name
      Description: The name of the topic to deny.
    • output_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • type
      Type: STRING
      Provider name: type
      Description: Specifies to deny the topic.

updated_at

Type: TIMESTAMP
Provider name: updatedAt
Description: The date and time at which the guardrail was updated.

version

Type: STRING
Provider name: version
Description: The version of the guardrail.

word_policy

Type: STRUCT
Provider name: wordPolicy
Description: The word policy that was configured for the guardrail.

  • managed_word_lists
    Type: UNORDERED_LIST_STRUCT
    Provider name: managedWordLists
    Description: A list of managed words configured for the guardrail.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • output_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • type
      Type: STRING
      Provider name: type
      Description: ManagedWords$type The managed word type that was configured for the guardrail. (For now, we only offer profanity word list)
  • words
    Type: UNORDERED_LIST_STRUCT
    Provider name: words
    Description: A list of words configured for the guardrail.
    • input_action
      Type: STRING
      Provider name: inputAction
      Description: 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
      Type: BOOLEAN
      Provider name: inputEnabled
      Description: Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.
    • output_action
      Type: STRING
      Provider name: outputAction
      Description: 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
      Type: BOOLEAN
      Provider name: outputEnabled
      Description: 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.
    • text
      Type: STRING
      Provider name: text
      Description: Text of the word configured for the guardrail to block.
PREVIEWING: may/embedded-workflows