Virtual agent triggers intent with less confidence threshold wheras NLU shows the correct intent with highest confidence threshold. Issue While testing NLU model in NLU workbend when 2 or more NLU intent is predicted virtual agent is triggering the intent with low confidence threshold CauseThe reason behind predicting unexpected result in Virtual agent is because of low confidence thresholdif the model threshold is 65%, then an intent will be predicted for an utterance only when the intent has a confidence score that is at least 65%. Setting a threshold that is too low may increase the false positives by predicting intents that should not be a match for an utterance. On the other hand, a model threshold that is too high may filter out intents that you do want to get predicted. Finding the ideal threshold improves your model's ability to predict intents correctly.ResolutionGo to sys_properties.listCreate "new"name : glide.mlpredictor.option.nlu.confidenceThresholdOverridevalue : {"intent:solutionName.intentName": 0.80, "intent:solutionName.intentName.EntityName": 0.80} <solutionname> is nlu_model_id and intentname is name. You can get this details from either open_nlu_predict_log record generated while reproducing the issue.