QuestionQ42VerifiedCopy linkReport a problemAsk AstroTutorSave questionWhich practice best helps you iteratively improve an agent’s prompt quality through UiPath evaluations?AIncrease the model temperature to its maximum to force more creative outputs.BTune only the agent's evaluator thresholds without updating the prompt structure.CRefine the prompt based on failed debug runs and add corrected outputs to the evaluation set.DRemove evaluations with lower scores to artificially raise the agent's average.Show AnswerAnswerExplanationRefining the prompt based on failed debug runs addresses observed weaknesses. Adding those cases with corrected expected outputs to the evaluation set enables repeatable testing and helps detect regressions as the prompt changes. (docs.uipath.com)Learn moreUiPath Agents: EvaluationsShow comments0Show commentsCommunity DiscussionNo comments yet. Be the first to start the discussion!
Community Discussion