class Guardrail (construct) 🔹

Language	Type name
.NET	Amazon.CDK.AWS.Bedrock.Alpha.Guardrail
Go	github.com/aws/aws-cdk-go/awsbedrockalpha/v2#Guardrail
Java	software.amazon.awscdk.services.bedrock.alpha.Guardrail
Python	aws_cdk.aws_bedrock_alpha.Guardrail
TypeScript (source)	@aws-cdk/aws-bedrock-alpha » Guardrail

Implements IConstruct, IDependable, IResource, IGuardrail

Class to create a Guardrail with CDK.

Example

const guardrail = new bedrock.Guardrail(this, 'bedrockGuardrails', {
  guardrailName: 'my-BedrockGuardrails',
});
// Add regex filter with input/output actions
guardrail.addRegexFilter({
  name: 'TestRegexFilter',
  pattern: 'test-pattern',
  action: bedrock.GuardrailAction.ANONYMIZE,
  // below props are optional
  description: 'This is a test regex filter',
  inputAction: bedrock.GuardrailAction.BLOCK,
  inputEnabled: true,
  outputAction: bedrock.GuardrailAction.ANONYMIZE,
  outputEnabled: true,
});

Initializer

new Guardrail(scope: Construct, id: string, props: GuardrailProps)

Parameters

• scope Construct
• id string
• props GuardrailProps

Construct Props

Name	Type	Description
guardrailName🔹	string	The name of the guardrail.
blockedInputMessaging?🔹	string	The message to return when the guardrail blocks a prompt.
blockedOutputsMessaging?🔹	string	The message to return when the guardrail blocks a model response.
contentFilters?🔹	ContentFilter[]	The content filters to apply to the guardrail.
contentFiltersTierConfig?🔹	TierConfig	The tier configuration to apply to the guardrail.
contextualGroundingFilters?🔹	ContextualGroundingFilter[]	The contextual grounding filters to apply to the guardrail.
crossRegionConfig?🔹	GuardrailCrossRegionConfigProperty	The cross-region configuration for the guardrail.
deniedTopics?🔹	Topic[]	A list of policies related to topics that the guardrail should deny.
description?🔹	string	The description of the guardrail.
kmsKey?🔹	IKey	A custom KMS key to use for encrypting data.
managedWordListFilters?🔹	ManagedWordFilter[]	The managed word filters to apply to the guardrail.
piiFilters?🔹	PIIFilter[]	The PII filters to apply to the guardrail.
regexFilters?🔹	RegexFilter[]	The regular expression (regex) filters to apply to the guardrail.
topicsTierConfig?🔹	TierConfig	The tier configuration to apply to the guardrail.
wordFilters?🔹	WordFilter[]	The word filters to apply to the guardrail.

---

guardrailName🔹

Type: string

The name of the guardrail.

This will be used as the physical name of the guardrail.

---

blockedInputMessaging?🔹

Type: string (optional, default: "Sorry, your query violates our usage policy.")

The message to return when the guardrail blocks a prompt.

Must be between 1 and 500 characters.

---

blockedOutputsMessaging?🔹

Type: string (optional, default: "Sorry, I am unable to answer your question because of our usage policy.")

The message to return when the guardrail blocks a model response.

Must be between 1 and 500 characters.

---

contentFilters?🔹

Type: ContentFilter[] (optional, default: [])

The content filters to apply to the guardrail.

---

contentFiltersTierConfig?🔹

Type: TierConfig (optional, default: filters.TierConfig.CLASSIC)

The tier configuration to apply to the guardrail.

---

contextualGroundingFilters?🔹

Type: ContextualGroundingFilter[] (optional, default: [])

The contextual grounding filters to apply to the guardrail.

---

crossRegionConfig?🔹

Type: GuardrailCrossRegionConfigProperty (optional, default: No cross-region configuration)

The cross-region configuration for the guardrail.

This is optional and when provided, it should be of type GuardrailCrossRegionConfigProperty.

---

deniedTopics?🔹

Type: Topic[] (optional, default: [])

A list of policies related to topics that the guardrail should deny.

---

description?🔹

Type: string (optional, default: No description)

The description of the guardrail.

---

kmsKey?🔹

Type: IKey (optional, default: Data is encrypted by default with a key that AWS owns and manages for you)

A custom KMS key to use for encrypting data.

---

managedWordListFilters?🔹

Type: ManagedWordFilter[] (optional, default: [])

The managed word filters to apply to the guardrail.

---

piiFilters?🔹

Type: PIIFilter[] (optional, default: [])

The PII filters to apply to the guardrail.

---

regexFilters?🔹

Type: RegexFilter[] (optional, default: [])

The regular expression (regex) filters to apply to the guardrail.

---

topicsTierConfig?🔹

Type: TierConfig (optional, default: filters.TierConfig.CLASSIC)

The tier configuration to apply to the guardrail.

---

wordFilters?🔹

Type: WordFilter[] (optional, default: [])

The word filters to apply to the guardrail.

Properties

Name	Type	Description
blockedInputMessaging🔹	string	The message to return when the guardrail blocks a prompt.
blockedOutputsMessaging🔹	string	The message to return when the guardrail blocks a model response.
contentFilters🔹	ContentFilter[]	The content filters applied by the guardrail.
contentFiltersTierConfig🔹	TierConfig	The tier that your guardrail uses for content filters.
contextualGroundingFilters🔹	ContextualGroundingFilter[]	The contextual grounding filters applied by the guardrail.
deniedTopics🔹	Topic[]	The denied topic filters applied by the guardrail.
env🔹	ResourceEnvironment	The environment this resource belongs to.
guardrailArn🔹	string	The ARN of the guardrail.
guardrailId🔹	string	The ID of the guardrail.
guardrailVersion🔹	string	The version of the guardrail.
hash🔹	string	The computed hash of the guardrail properties.
managedWordListFilters🔹	ManagedWordFilter[]	The managed word list filters applied by the guardrail.
name🔹	string	The name of the guardrail.
node🔹	Node	The tree node.
piiFilters🔹	PIIFilter[]	The PII filters applied by the guardrail.
regexFilters🔹	RegexFilter[]	The regex filters applied by the guardrail.
stack🔹	Stack	The stack in which this resource is defined.
topicsTierConfig🔹	TierConfig	The tier that your guardrail uses for denied topic filters.
wordFilters🔹	WordFilter[]	The word filters applied by the guardrail.
crossRegionConfig?🔹	GuardrailCrossRegionConfigProperty	The cross-region configuration for the guardrail.
kmsKey?🔹	IKey	The KMS key used to encrypt data.
lastUpdated?🔹	string	When this guardrail was last updated.
static PROPERTY_INJECTION_ID🔹	string	Uniquely identifies this class.

---

blockedInputMessaging🔹

Type: string

The message to return when the guardrail blocks a prompt.

---

blockedOutputsMessaging🔹

Type: string

The message to return when the guardrail blocks a model response.

---

contentFilters🔹

Type: ContentFilter[]

The content filters applied by the guardrail.

---

contentFiltersTierConfig🔹

Type: TierConfig

The tier that your guardrail uses for content filters.

Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

---

contextualGroundingFilters🔹

Type: ContextualGroundingFilter[]

The contextual grounding filters applied by the guardrail.

---

deniedTopics🔹

Type: Topic[]

The denied topic filters applied by the guardrail.

---

env🔹

Type: ResourceEnvironment

The environment this resource belongs to.

For resources that are created and managed by the CDK (generally, those created by creating new class instances like Role, Bucket, etc.), this is always the same as the environment of the stack they belong to; however, for imported resources (those obtained from static methods like fromRoleArn, fromBucketName, etc.), that might be different than the stack they were imported into.

---

guardrailArn🔹

Type: string

The ARN of the guardrail.

---

guardrailId🔹

Type: string

The ID of the guardrail.

---

guardrailVersion🔹

Type: string

The version of the guardrail.

---

hash🔹

Type: string

The computed hash of the guardrail properties.

---

managedWordListFilters🔹

Type: ManagedWordFilter[]

The managed word list filters applied by the guardrail.

---

name🔹

Type: string

The name of the guardrail.

---

node🔹

Type: Node

The tree node.

---

piiFilters🔹

Type: PIIFilter[]

The PII filters applied by the guardrail.

---

regexFilters🔹

Type: RegexFilter[]

The regex filters applied by the guardrail.

---

stack🔹

Type: Stack

The stack in which this resource is defined.

---

topicsTierConfig🔹

Type: TierConfig

The tier that your guardrail uses for denied topic filters.

---

wordFilters🔹

Type: WordFilter[]

The word filters applied by the guardrail.

---

crossRegionConfig?🔹

Type: GuardrailCrossRegionConfigProperty (optional)

The cross-region configuration for the guardrail.

---

kmsKey?🔹

Type: IKey (optional, default: undefined - "Data is encrypted by default with a key that AWS owns and manages for you")

The KMS key used to encrypt data.

---

lastUpdated?🔹

Type: string (optional)

When this guardrail was last updated.

---

static PROPERTY_INJECTION_ID🔹

Type: string

Uniquely identifies this class.

Methods

Name	Description
addContentFilter(filter)🔹	Adds a content filter to the guardrail.
addContextualGroundingFilter(filter)🔹	Adds a contextual grounding filter to the guardrail.
addDeniedTopicFilter(filter)🔹	Adds a denied topic filter to the guardrail.
addManagedWordListFilter(filter)🔹	Adds a managed word list filter to the guardrail.
addPIIFilter(filter)🔹	Adds a PII filter to the guardrail.
addRegexFilter(filter)🔹	Adds a regex filter to the guardrail.
addWordFilter(filter)🔹	Adds a word filter to the guardrail.
addWordFilterFromFile(filePath, inputAction?, outputAction?, inputEnabled?, outputEnabled?)🔹	Adds a word filter to the guardrail.
applyRemovalPolicy(policy)🔹	Apply the given removal policy to this resource.
createVersion(description?)🔹	Create a version for the guardrail.
grant(grantee, ...actions)🔹	Grant the given principal identity permissions to perform actions on this guardrail.
grantApply(grantee)🔹	Grant the given identity permissions to apply the guardrail.
metric(metricName, props?)🔹	Return the given named metric for this guardrail.
metricInvocationClientErrors(props?)🔹	Return the invocation client errors metric for this guardrail.
metricInvocationLatency(props?)🔹	Return the invocation latency metric for this guardrail.
metricInvocationServerErrors(props?)🔹	Return the invocation server errors metric for this guardrail.
metricInvocationThrottles(props?)🔹	Return the invocation throttles metric for this guardrail.
metricInvocations(props?)🔹	Return the invocations metric for this guardrail.
metricInvocationsIntervened(props?)🔹	Return the invocations intervened metric for this guardrail.
metricTextUnitCount(props?)🔹	Return the text unit count metric for this guardrail.
toString()🔹	Returns a string representation of this construct.
static fromCfnGuardrail(cfnGuardrail)🔹	Import a low-level L1 Cfn Guardrail.
static fromGuardrailAttributes(scope, id, attrs)🔹	Import a guardrail given its attributes.

---

addContentFilter(filter)🔹

public addContentFilter(filter: ContentFilter): void

Parameters

• filter ContentFilter — The content filter to add.

Adds a content filter to the guardrail.

---

addContextualGroundingFilter(filter)🔹

public addContextualGroundingFilter(filter: ContextualGroundingFilter): void

Parameters

• filter ContextualGroundingFilter — The contextual grounding filter to add.

Adds a contextual grounding filter to the guardrail.

---

addDeniedTopicFilter(filter)🔹

public addDeniedTopicFilter(filter: Topic): void

Parameters

• filter Topic — The denied topic filter to add.

Adds a denied topic filter to the guardrail.

---

addManagedWordListFilter(filter)🔹

public addManagedWordListFilter(filter: ManagedWordFilter): void

Parameters

• filter ManagedWordFilter — The managed word list filter to add.

Adds a managed word list filter to the guardrail.

---

addPIIFilter(filter)🔹

public addPIIFilter(filter: PIIFilter): void

Parameters

• filter PIIFilter — The PII filter to add.

Adds a PII filter to the guardrail.

---

addRegexFilter(filter)🔹

public addRegexFilter(filter: RegexFilter): void

Parameters

• filter RegexFilter — The regex filter to add.

Adds a regex filter to the guardrail.

---

addWordFilter(filter)🔹

public addWordFilter(filter: WordFilter): void

Parameters

• filter WordFilter — The word filter to add.

Adds a word filter to the guardrail.

---

addWordFilterFromFile(filePath, inputAction?, outputAction?, inputEnabled?, outputEnabled?)🔹

public addWordFilterFromFile(filePath: string, inputAction?: GuardrailAction, outputAction?: GuardrailAction, inputEnabled?: boolean, outputEnabled?: boolean): void

Parameters

• filePath string — The location of the word filter file.
• inputAction GuardrailAction
• outputAction GuardrailAction
• inputEnabled boolean
• outputEnabled boolean

Adds a word filter to the guardrail.

---

applyRemovalPolicy(policy)🔹

public applyRemovalPolicy(policy: RemovalPolicy): void

Parameters

• policy RemovalPolicy

Apply the given removal policy to this resource.

The Removal Policy controls what happens to this resource when it stops being managed by CloudFormation, either because you've removed it from the CDK application or because you've made a change that requires the resource to be replaced.

The resource can be deleted (RemovalPolicy.DESTROY), or left in your AWS account for data recovery and cleanup later (RemovalPolicy.RETAIN).

---

createVersion(description?)🔹

public createVersion(description?: string): string

Parameters

• description string — The description of the version.

Returns

• string

Create a version for the guardrail.

---

grant(grantee, ...actions)🔹

public grant(grantee: IGrantable, ...actions: string[]): Grant

Parameters

• grantee IGrantable
• actions string

Returns

• Grant

Grant the given principal identity permissions to perform actions on this guardrail.

---

grantApply(grantee)🔹

public grantApply(grantee: IGrantable): Grant

Parameters

• grantee IGrantable

Returns

• Grant

Grant the given identity permissions to apply the guardrail.

---

metric(metricName, props?)🔹

public metric(metricName: string, props?: MetricOptions): Metric

Parameters

• metricName string
• props MetricOptions

Returns

• Metric

Return the given named metric for this guardrail.

By default, the metric will be calculated as a sum over a period of 5 minutes. You can customize this by using the statistic and period properties.

---

metricInvocationClientErrors(props?)🔹

public metricInvocationClientErrors(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocation client errors metric for this guardrail.

---

metricInvocationLatency(props?)🔹

public metricInvocationLatency(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocation latency metric for this guardrail.

---

metricInvocationServerErrors(props?)🔹

public metricInvocationServerErrors(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocation server errors metric for this guardrail.

---

metricInvocationThrottles(props?)🔹

public metricInvocationThrottles(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocation throttles metric for this guardrail.

---

metricInvocations(props?)🔹

public metricInvocations(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocations metric for this guardrail.

---

metricInvocationsIntervened(props?)🔹

public metricInvocationsIntervened(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the invocations intervened metric for this guardrail.

---

metricTextUnitCount(props?)🔹

public metricTextUnitCount(props?: MetricOptions): Metric

Parameters

• props MetricOptions

Returns

• Metric

Return the text unit count metric for this guardrail.

---

toString()🔹

public toString(): string

Returns

• string

Returns a string representation of this construct.

---

static fromCfnGuardrail(cfnGuardrail)🔹

public static fromCfnGuardrail(cfnGuardrail: CfnGuardrail): IGuardrail

Parameters

• cfnGuardrail CfnGuardrail

Returns

• IGuardrail

Import a low-level L1 Cfn Guardrail.

---

static fromGuardrailAttributes(scope, id, attrs)🔹

public static fromGuardrailAttributes(scope: Construct, id: string, attrs: GuardrailAttributes): IGuardrail

Parameters

• scope Construct
• id string
• attrs GuardrailAttributes

Returns

• IGuardrail

Import a guardrail given its attributes.