Skip to main content
Running evals across Maxim is now fully configurable. We’ve extended the Flexi eval capability beyond logs to include Prompt, No-code, HTTP and Voice agent testing and simulations. Instead of being limited to predefined parameters like input, output, context, etc, you can now decide exactly which value in the user query, agent response, or test dataset should be mapped to the corresponding field for your evaluators. This makes your evaluators highly reusable and helps eliminate noise from evaluation parameters. Flexible Evaluators