EvaluatorConfig
The configuration that defines how an evaluator assesses agent performance, including the evaluation method and parameters.
Inheritors
Types
Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.
The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.
The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.
Functions
Casts this EvaluatorConfig as a CodeBased and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.CodeBasedEvaluatorConfig value. Throws an exception if the EvaluatorConfig is not a CodeBased.
Casts this EvaluatorConfig as a CodeBased and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.CodeBasedEvaluatorConfig value. Returns null if the EvaluatorConfig is not a CodeBased.
Casts this EvaluatorConfig as a Derived and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.DerivedEvaluatorConfig value. Throws an exception if the EvaluatorConfig is not a Derived.
Casts this EvaluatorConfig as a Derived and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.DerivedEvaluatorConfig value. Returns null if the EvaluatorConfig is not a Derived.
Casts this EvaluatorConfig as a LlmAsAJudge and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.LlmAsAJudgeEvaluatorConfig value. Throws an exception if the EvaluatorConfig is not a LlmAsAJudge.
Casts this EvaluatorConfig as a LlmAsAJudge and retrieves its aws.sdk.kotlin.services.bedrockagentcorecontrol.model.LlmAsAJudgeEvaluatorConfig value. Returns null if the EvaluatorConfig is not a LlmAsAJudge.