When a bot gets stuck, it brings a human in to help the end-user and train itself

Creating great conversational experiences isn’t easy. As a result, most of them are less than impressive. To avoid lackluster results, a pharmaceutical company incorporated humans-in-the-loop (HitL). With this approach, when a conversational application got stuck, it addressed a live agent to help. That agent ensured the end-user experience was fulfilled while also training the system, so future occurrences don’t require intervention.