The criteria that the judge will use to evaluate the conversation.
Optional
maxThe maximum number of tokens to generate.
Optional
modelThe language model to use for generating responses. If not provided, a default model will be used.
Optional
nameThe name of the agent.
Optional
systemA custom system prompt to override the default behavior of the judge.
Optional
temperatureThe temperature for the language model. Defaults to 0.
Configuration for the judge agent.