class EvaluationLevel

Language	Type name
.NET	Amazon.CDK.AWS.BedrockAgentCore.EvaluationLevel
Go	github.com/aws/aws-cdk-go/awscdk/v2/awsbedrockagentcore#EvaluationLevel
Java	software.amazon.awscdk.services.bedrockagentcore.EvaluationLevel
Python	aws_cdk.aws_bedrockagentcore.EvaluationLevel
TypeScript (source)	aws-cdk-lib » aws_bedrockagentcore » EvaluationLevel

The level at which a custom evaluator assesses agent performance.

Determines what granularity of data the evaluator operates on.

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.EvaluatorSelector.builtin(agentcore.BuiltinEvaluator.HELPFULNESS),
    agentcore.EvaluatorSelector.custom(evaluator),
  ],
  dataSource: agentcore.DataSourceConfig.fromCloudWatchLogs({
    logGroupNames: ['/aws/bedrock-agentcore/my-agent'],
    serviceNames: ['my-agent.default'],
  }),
});

Initializer

new EvaluationLevel(value: string)

Parameters

• value string — - The evaluation level string.

Properties

Name	Type	Description
value	string	The string value of the evaluation level.
static SESSION	EvaluationLevel	Evaluates an entire agent session (multiple traces across a conversation).
static TOOL_CALL	EvaluationLevel	Evaluates individual tool call invocations within a trace.
static TRACE	EvaluationLevel	Evaluates a complete agent trace (a single request-response cycle).

---

value

Type: string

The string value of the evaluation level.

---

static SESSION

Type: EvaluationLevel

Evaluates an entire agent session (multiple traces across a conversation).

---

static TOOL_CALL

Type: EvaluationLevel

Evaluates individual tool call invocations within a trace.

---

static TRACE

Type: EvaluationLevel

Evaluates a complete agent trace (a single request-response cycle).