class EvaluatorRatingScale 🔹

Language	Type name
.NET	Amazon.CDK.AWS.Bedrock.Agentcore.Alpha.EvaluatorRatingScale
Go	github.com/aws/aws-cdk-go/awsbedrockagentcorealpha/v2#EvaluatorRatingScale
Java	software.amazon.awscdk.services.bedrock.agentcore.alpha.EvaluatorRatingScale
Python	aws_cdk.aws_bedrock_agentcore_alpha.EvaluatorRatingScale
TypeScript (source)	@aws-cdk/aws-bedrock-agentcore-alpha » EvaluatorRatingScale

Represents a rating scale for custom LLM-as-a-Judge evaluators.

Rating scales define how the evaluator scores agent performance. Use either categorical (discrete labels) or numerical (labeled numeric values) scales.

Example

// Categorical rating scale
const categorical = agentcore.EvaluatorRatingScale.categorical([
  { label: 'Good', definition: 'The response fully addresses the query.' },
  { label: 'Bad', definition: 'The response fails to address the query.' },
]);

// Numerical rating scale
const numerical = agentcore.EvaluatorRatingScale.numerical([
  { label: 'Poor', definition: 'Inadequate response.', value: 1 },
  { label: 'Good', definition: 'Adequate response.', value: 3 },
  { label: 'Excellent', definition: 'Outstanding response.', value: 5 },
]);

Methods

Name	Description
static categorical(options)🔹	Creates a categorical rating scale.
static numerical(options)🔹	Creates a numerical rating scale.

---

static categorical(options)🔹

public static categorical(options: CategoricalRatingOption[]): EvaluatorRatingScale

Parameters

• options CategoricalRatingOption[] — - The categorical rating options (at least 1 required).

Returns

• EvaluatorRatingScale

Creates a categorical rating scale.

Categorical scales define discrete labels for scoring, such as "Good" / "Bad" or "Pass" / "Fail".

---

static numerical(options)🔹

public static numerical(options: NumericalRatingOption[]): EvaluatorRatingScale

Parameters

• options NumericalRatingOption[] — - The numerical rating options (at least 1 required).

Returns

• EvaluatorRatingScale

Creates a numerical rating scale.

Numerical scales define labeled numeric values for scoring, such as 1 (Poor) through 5 (Excellent).