llmAsAJudge
inline fun <T> AIAgentSubgraphBuilderBase<*, *>.llmAsAJudge(llmModel: LLModel? = null, task: String): AIAgentNodeDelegate<T, CriticResult<T>>(source)
A method to utilize a language model (LLM) as a critic or judge for evaluating tasks with context-aware feedback. This method processes a given task and the interaction history to provide structured feedback on the task's correctness.
Parameters
llmModel
The optional language model to override the default model during the session. If null, the default model will be used.
task
The task or instruction to be presented to the language model for critical evaluation.