But even though most chatbots can handle moderately sophisticated conversations, like welcome conversations and product discovery interactions, the if/then logic that powers their conversational capabilities can be limiting. For instance, if a customer asks a unique yet pressing question that you didn’t account for when designing your chatbot’s logic, there’s no way it can answer their question, which hangs your customer out to dry and ultimately leaves them dissatisfied with your customer service.
Woebot has a sense of humor, and I can see people who are having a bad day sticking with the attractive platform. Woebot also has skills — in no time, Woebot had identified my mood (with emoji support), identified three thoughts underlying my mood, and helped me see that these thoughts were “distortions,” which we replaced with more helpful thoughts.
This form of obtaining information from the collective intelligence of a large number of people allows Cleverbot to respond in new conversations by taking into account the context of the conversation typed by a user and searching its database for an appropriate response. It scans its history for every user-submitted response to the given question and replies accordingly, which creates a more human-like conversation with users.
Overall: We are now able to leave our Chat on 24/7, when previously we had limited hours (due to staffing) for the Chat. It is still very much a work in progress to ensure the ChatBot has routed to the correct conversations and can sometimes be frustrating to try and figure out why the ChatBot went to a certain scenario over another. The help topics the company provides can point you in the right direction but they are written at a level above the capabilities of a brand new user to bots in my opinion. Determining whether or not no conversation with a client vs a below average conversation with a client (at times) is worth it, will determine whether we continue to renew our monthly subscription.
If you plan on using ChatBot, it'll take a while to get it near perfection. I would recommend creating a list of events or potential encounters and map it out on your website to try to predict how to fix it. Plan this out on paper and use each scenario, it'll take hours but it'll build value and make it seem like the client is talking to a real person. After that, use the chat logs where a client runs into an issue with the chat to learn what can happen and fix that scenario.
Dr. Dillon Browne is a clinical psychologist and professor at the University of Waterloo. He completed his PhD in psychology at the University of Toronto and has written numerous articles in the domains of children’s mental health, human development, and family studies. Dillon enjoys playing the guitar and piano, cycling, and fitness. Connect with him on LinkedIn.
This chatbot is one the best AI chatbots and it’s my favorite too. Evidently it is the current winner of Loebner Prize. The Loebner Prize is an annual competition in artificial intelligence that awards prizes to the chatterbot considered by the judges to be the most human-like. The format of the competition is that of a standard Turing test. You can talk with Mitsuku for hours without getting bored. It replies to your question in the most humane way and understands your mood with the language you’re using.