2.253.1

interface OnlineEvaluationConfigProps 🔹

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

Implements OnlineEvaluationBaseProps

Properties for creating an OnlineEvaluationConfig.

Example

declare const customEvaluator: agentcore.Evaluator;

const evaluation = new agentcore.OnlineEvaluationConfig(this, 'MixedEvaluation', {
  onlineEvaluationConfigName: 'mixed_evaluation',
  evaluators: [
    // Built-in evaluators
    agentcore.EvaluatorReference.builtin(agentcore.BuiltinEvaluator.HELPFULNESS),
    agentcore.EvaluatorReference.builtin(agentcore.BuiltinEvaluator.CORRECTNESS),
    // Custom evaluator
    agentcore.EvaluatorReference.custom(customEvaluator),
  ],
  dataSource: agentcore.DataSourceConfig.fromCloudWatchLogs({
    logGroupNames: ['/aws/bedrock-agentcore/my-agent'],
    serviceNames: ['my-agent.default'],
  }),
});

Properties

NameTypeDescription
dataSource🔹DataSourceConfigThe data source configuration that specifies where to read agent traces from.
evaluators🔹EvaluatorReference[]The list of evaluators to apply during online evaluation.
onlineEvaluationConfigName🔹stringThe name of the online evaluation configuration.
description?🔹stringThe description of the online evaluation configuration.
executionRole?🔹IRoleThe IAM role that provides permissions for the evaluation to access AWS services.
executionStatus?🔹ExecutionStatusThe execution status of the online evaluation configuration.
filters?🔹FilterConfig[]The list of filters that determine which agent traces should be evaluated.
samplingPercentage?🔹numberThe percentage of agent traces to sample for evaluation.
sessionTimeout?🔹DurationThe duration of inactivity after which an agent session is considered complete and ready for evaluation.

dataSource🔹

Type: DataSourceConfig

The data source configuration that specifies where to read agent traces from.

evaluators🔹

Type: EvaluatorReference[]

The list of evaluators to apply during online evaluation.

Can include both built-in evaluators and custom evaluators.

onlineEvaluationConfigName🔹

Type: string

The name of the online evaluation configuration.

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.

description?🔹

Type: string (optional, default: No description)

The description of the online evaluation configuration.

executionRole?🔹

Type: IRole (optional, default: A new role will be created)

The IAM role that provides permissions for the evaluation to access AWS services.

If not provided, a role will be created automatically with the required permissions including cross-region Bedrock model invocation (to support cross-region inference profiles). For strict cost controls or data residency compliance, provide a custom role with region-scoped permissions.

executionStatus?🔹

Type: ExecutionStatus (optional, default: ExecutionStatus.ENABLED)

The execution status of the online evaluation configuration.

Controls whether the evaluation actively processes agent traces.

filters?🔹

Type: FilterConfig[] (optional, default: No filters (evaluate all sampled traces))

The list of filters that determine which agent traces should be evaluated.

samplingPercentage?🔹

Type: number (optional, default: 10)

The percentage of agent traces to sample for evaluation.

sessionTimeout?🔹

Type: Duration (optional, default: Duration.minutes(15))

The duration of inactivity after which an agent session is considered complete and ready for evaluation.

Must be between 1 minute and 1440 minutes (24 hours).

← PreviousNext →