Skip to content

/AWS1/CL_BDOEVALUATORCONFIG

The configuration that defines how an evaluator assesses agent performance, including the evaluation method and parameters.

CONSTRUCTOR

IMPORTING

Optional arguments:

io_llmasajudge TYPE REF TO /AWS1/CL_BDOLLMASAJUDGEEVALU00 /AWS1/CL_BDOLLMASAJUDGEEVALU00

The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

io_codebased TYPE REF TO /AWS1/CL_BDOCODEBASEDEVALTRCFG /AWS1/CL_BDOCODEBASEDEVALTRCFG

Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.


Queryable Attributes

llmAsAJudge

The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

Accessible with the following methods

Method Description
GET_LLMASAJUDGE() Getter for LLMASAJUDGE

codeBased

Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

Accessible with the following methods

Method Description
GET_CODEBASED() Getter for CODEBASED