2.254.0

interface EvaluatorProps 🔹

LanguageType name
.NETAmazon.CDK.AWS.Bedrock.Agentcore.Alpha.EvaluatorProps
Gogithub.com/aws/aws-cdk-go/awsbedrockagentcorealpha/v2#EvaluatorProps
Javasoftware.amazon.awscdk.services.bedrock.agentcore.alpha.EvaluatorProps
Pythonaws_cdk.aws_bedrock_agentcore_alpha.EvaluatorProps
TypeScript (source)@aws-cdk/aws-bedrock-agentcore-alpha » EvaluatorProps

Properties for creating an Evaluator.

Example

// Create a custom LLM-as-a-Judge evaluator
const evaluator = new agentcore.Evaluator(this, 'MyEvaluator', {
  evaluatorName: 'my_custom_evaluator',
  level: agentcore.EvaluationLevel.SESSION,
  evaluatorConfig: agentcore.EvaluatorConfig.llmAsAJudge({
    instructions: 'Evaluate whether the agent response is helpful and accurate.',
    modelId: 'us.anthropic.claude-sonnet-4-6',
    ratingScale: agentcore.EvaluatorRatingScale.categorical([
      { label: 'Good', definition: 'The response is helpful and accurate.' },
      { label: 'Bad', definition: 'The response is not helpful or contains errors.' },
    ]),
  }),
});

// Use the custom evaluator in an online evaluation configuration
new agentcore.OnlineEvaluationConfig(this, 'MyEvaluation', {
  onlineEvaluationConfigName: 'my_evaluation',
  evaluators: [
    agentcore.EvaluatorReference.builtin(agentcore.BuiltinEvaluator.HELPFULNESS),
    agentcore.EvaluatorReference.custom(evaluator),
  ],
  dataSource: agentcore.DataSourceConfig.fromCloudWatchLogs({
    logGroupNames: ['/aws/bedrock-agentcore/my-agent'],
    serviceNames: ['my-agent.default'],
  }),
});

Properties

NameTypeDescription
evaluatorConfig🔹EvaluatorConfigThe configuration that defines how the evaluator assesses agent performance.
evaluatorName🔹stringThe name of the evaluator.
level🔹EvaluationLevelThe level at which the evaluator assesses agent performance.
description?🔹stringThe description of the evaluator.
tags?🔹{ [string]: string }Tags for the evaluator.

evaluatorConfig🔹

Type: EvaluatorConfig

The configuration that defines how the evaluator assesses agent performance.

Use EvaluatorConfig.llmAsAJudge() for model-based evaluation or EvaluatorConfig.codeBased() for Lambda-based evaluation.

evaluatorName🔹

Type: string

The name of the evaluator.

Must be unique within your account. Valid characters are a-z, A-Z, 0-9, _ (underscore). Must start with a letter and can be up to 48 characters long.

level🔹

Type: EvaluationLevel

The level at which the evaluator assesses agent performance.

Determines what granularity of data the evaluator operates on: tool call, trace (single request-response), or session (full conversation).

description?🔹

Type: string (optional, default: No description)

The description of the evaluator.

tags?🔹

Type: { [string]: string } (optional, default: No tags)

Tags for the evaluator.

A list of key:value pairs of tags to apply to this Evaluator resource.

← PreviousNext →