EvaluatorSelector

class aws_cdk.aws_bedrockagentcore.EvaluatorSelector(*args: Any, **kwargs)

Bases: object

Represents a reference to an evaluator for online evaluation.

Use the static factory methods to create evaluator references:

EvaluatorSelector.builtin() for built-in evaluators
EvaluatorSelector.custom() for custom evaluators

Example:

# Using custom evaluators
# my_custom_evaluator: agentcore.IEvaluator
# Using built-in evaluators
helpfulness = agentcore.EvaluatorSelector.builtin(agentcore.BuiltinEvaluator.HELPFULNESS)
custom = agentcore.EvaluatorSelector.custom(my_custom_evaluator)

Methods

bind()

Binds the evaluator reference to produce the L1 property.

Return type:: EvaluatorSelectorBindResult

Attributes

evaluator_id: The evaluator identifier.

Static Methods

classmethod builtin(evaluator)

Creates a reference to a built-in evaluator.

Built-in evaluators are provided by Amazon Bedrock AgentCore and assess different aspects of agent performance at various levels (session, trace, or tool call).

Parameters:

evaluator (BuiltinEvaluator) –

The built-in evaluator to reference.

Return type:

EvaluatorSelector

Returns:

An EvaluatorSelector instance

Example:

helpfulness = agentcore.EvaluatorSelector.builtin(agentcore.BuiltinEvaluator.HELPFULNESS)
goal_success = agentcore.EvaluatorSelector.builtin(agentcore.BuiltinEvaluator.GOAL_SUCCESS_RATE)

classmethod custom(evaluator)

Creates a reference to a custom evaluator.

Custom evaluators are created using the Evaluator construct and can be LLM-as-a-Judge or code-based (Lambda) evaluators.

Parameters:

evaluator (IEvaluator) –

The custom evaluator construct to reference.

Return type:

EvaluatorSelector

Returns:

An EvaluatorSelector instance

Example:

# my_custom_evaluator: agentcore.IEvaluator

ref = agentcore.EvaluatorSelector.custom(my_custom_evaluator)