Package software.amazon.awscdk.services.bedrockagentcore

Class LlmAsAJudgeOptions.Jsii$Proxy

java.lang.Object

software.amazon.jsii.JsiiObject

software.amazon.awscdk.services.bedrockagentcore.LlmAsAJudgeOptions.Jsii$Proxy

All Implemented Interfaces:

LlmAsAJudgeOptions, software.amazon.jsii.JsiiSerializable

Enclosing interface:

LlmAsAJudgeOptions

@Stability(Stable)
@Internal
public static final class LlmAsAJudgeOptions.Jsii$Proxy
extends software.amazon.jsii.JsiiObject
implements LlmAsAJudgeOptions

An implementation for LlmAsAJudgeOptions

Nested Class Summary

Nested classes/interfaces inherited from class software.amazon.jsii.JsiiObject

software.amazon.jsii.JsiiObject.InitializationMode

Nested classes/interfaces inherited from interface software.amazon.awscdk.services.bedrockagentcore.LlmAsAJudgeOptions

LlmAsAJudgeOptions.Builder, LlmAsAJudgeOptions.Jsii$Proxy

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	Jsii$Proxy(LlmAsAJudgeOptions.Builder builder)	Constructor that initializes the object based on literal property values passed by the LlmAsAJudgeOptions.Builder.
protected	Jsii$Proxy(software.amazon.jsii.JsiiObjectRef objRef)	Constructor that initializes the object based on values retrieved from the JsiiObject.

Method Summary

Modifier and Type	Method	Description
com.fasterxml.jackson.databind.JsonNode	$jsii$toJson()
final boolean	equals(Object o)
final Map<String,Object>	getAdditionalModelRequestFields()	Additional model-specific request fields.
final EvaluatorInferenceConfig	getInferenceConfig()	Optional inference configuration parameters that control model behavior during evaluation.
final String	getInstructions()	The evaluation instructions that guide the language model in assessing agent performance.
final String	getModelId()	The identifier of the Amazon Bedrock model to use for evaluation.
final EvaluatorRatingScale	getRatingScale()	The rating scale that defines how the evaluator should score agent performance.
final int	hashCode()

Methods inherited from class software.amazon.jsii.JsiiObject

jsiiAsyncCall, jsiiAsyncCall, jsiiCall, jsiiCall, jsiiGet, jsiiGet, jsiiSet, jsiiStaticCall, jsiiStaticCall, jsiiStaticGet, jsiiStaticGet, jsiiStaticSet, jsiiStaticSet

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Jsii$Proxy

protected Jsii$Proxy(software.amazon.jsii.JsiiObjectRef objRef)

Constructor that initializes the object based on values retrieved from the JsiiObject.

Parameters:

objRef - Reference to the JSII managed object.

Jsii$Proxy

protected Jsii$Proxy(LlmAsAJudgeOptions.Builder builder)

Constructor that initializes the object based on literal property values passed by the LlmAsAJudgeOptions.Builder.

Method Details

getInstructions

public final String getInstructions()

Description copied from interface: LlmAsAJudgeOptions

The evaluation instructions that guide the language model in assessing agent performance.

These instructions define the evaluation criteria, context, and expected behavior. Instructions must contain placeholders appropriate for the evaluation level (e.g., {context}, {available_tools} for SESSION level).

Note: Evaluators using reference-input placeholders (e.g., {expected_tool_trajectory}, {assertions}, {expected_response}) are only compatible with on-demand evaluation, not online evaluation.

Specified by:

getInstructions in interface LlmAsAJudgeOptions

See Also:

• https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/custom-evaluators.html

getModelId

public final String getModelId()

Description copied from interface: LlmAsAJudgeOptions

The identifier of the Amazon Bedrock model to use for evaluation.

Accepts standard model IDs (e.g., 'anthropic.claude-sonnet-4-6') and cross-region inference profile IDs with region prefixes (e.g., 'us.anthropic.claude-sonnet-4-6', 'eu.anthropic.claude-sonnet-4-6').

Specified by:

getModelId in interface LlmAsAJudgeOptions

getRatingScale

public final EvaluatorRatingScale getRatingScale()

Description copied from interface: LlmAsAJudgeOptions

The rating scale that defines how the evaluator should score agent performance.

Specified by:

getRatingScale in interface LlmAsAJudgeOptions

getAdditionalModelRequestFields

public final Map<String,Object> getAdditionalModelRequestFields()

Description copied from interface: LlmAsAJudgeOptions

Additional model-specific request fields.

Default: - No additional fields

Specified by:

getAdditionalModelRequestFields in interface LlmAsAJudgeOptions

getInferenceConfig

public final EvaluatorInferenceConfig getInferenceConfig()

Description copied from interface: LlmAsAJudgeOptions

Optional inference configuration parameters that control model behavior during evaluation.

When not specified, the foundation model uses its own default values for maxTokens, temperature, and topP.

Default: - The foundation model's default inference parameters are used

Specified by:

getInferenceConfig in interface LlmAsAJudgeOptions

See Also:

• https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/custom-evaluators.html

$jsii$toJson

@Internal
public com.fasterxml.jackson.databind.JsonNode $jsii$toJson()

Specified by:

$jsii$toJson in interface software.amazon.jsii.JsiiSerializable

equals

public final boolean equals(Object o)

Overrides:

equals in class Object

hashCode

public final int hashCode()

Overrides:

hashCode in class Object