Taking Your Chatbot To The Next Level

Or, the longer your chatbot “lives” the more it can learn.  If you started small (the sensible route to launching a bot), then you can monitor and analyze the most common requests to your chatbot and create a training plan aimed at building up the bot’s knowledge and broadening the number of questions it can easily answer.

However, in the case of chatbots, failure actually IS an option.  In fact, it’s one of the key ways that your bot will evolve and improve.  When a chatbot is unable to answer a question, in addition to offering a suggestion and/or sending the user to a human for help (as Gecko’s Chatbot module does), the back end of your bot system will alert you that a low confidence answer was offered.  Check this frequently, accept answers that the bot got right into the answer bank and add new answers for the ones it got wrong, or only partially correct.  Doing this daily grows your chatbot’s capability and helps it to learn.

On that note, how do chatbots “learn”?  Aside from the training that you provide, chatbots are powered by Artificial Intelligence (AI), so have the ability to learn on their own, too.  The term used to describe this is “machine learning”, a sub-category of AI that enables a chatbot system to improve from experience without being explicitly programmed or trained.  In essence, the chatbot recognises patterns over time and uses these to make better decisions in future when asked similar questions.

When it comes to learning, between your efforts and the chatbot’s own you will have a smarter bot with every day that passes.

 

Another phase in your chatbot’s evolution could be to move from just being a reactive answer bank to providing proactive engagement with your users.  We work mostly with higher education intuitions, so I’ll use that as an example, but in any industry where you would like a user to take an action, your chatbot can help.

So, back to the higher education example.  Say you are recruiting for new students and they have decided to enroll at your school.  Using a platform like GeckoEngage, you will be able to pull a list of all the students that haven’t yet completed the necessary paperwork for accomodation.  A mass text message can then be sent with a reminder about booking accommodation, and any responses to the text can trigger the chatbot to provide a link to the appropriate form and field any questions.  The time saved by the internal team here is significant; within a few minutes, all students who haven’t yet submitted a form have been prompted to take action.

Another HigherEd example might be around event attendance and management.  During the enrollment process, there may be thousands of prospective students wishing to visit a campus, take a tour, attend seminars and experience what a university has to offer.  Using a chatbot, universities can answer early questions online, proactively ask if they would like to attend an event and then kick off a workflow that allows prospects to book a space on an open day, receive a ticket and manage the content of their day on campus – all without personal intervention from a member of staff.

 

Chatbots are a great asset when it comes to building relationships and personalizing communication with your customers.  A chatbot’s very reason for being is to gather data from its user and provide a customized response on a personal level.  Asking the right questions through your chatbot provides a rich mine of individual data that can be used to shape communications as you move forward together.

Whenever somebody engages with your chatbot, they make decisions that provide information on who that person is and what it is they want.  Harnessing this knowledge allows you to give them what they want, when they want it – delivering a great brand experience and at-scale personalization.  On top of this, individual experience is enhanced and the relationship with that person is strengthened on the back of the personalized service received.  Win win.