How Do Chatbots Work

How do Chatbots Work?

So if you keep hearing the term chatbot being banded around, you might be wanting to find out more.  Chatbots are going to be a key piece of automation for 2017. So understanding what they are and how they work, will help you see how they can fit into your business planning for the next 12 months.

What chatbots are

Chatbots are a form of automated service, a chat based interface that clients can interact with.  It is a form of artificial intelligence (AI) that operates within defined set of rules and parameters.  A chatbot can provide many functions and can be hosted in most major chat platforms like Facebook messenger, text messaging and many others.

So how does a chatbot work?

A chatbot works in much the same way as a human manning a help desk.  When a customer opens a chat dialogue to ask for assistance, the chatbot is the medium responding.  So, if a customer typed the question ‘What time does your store open tomorrow morning’, using the information available, the chatbot would immediately respond in the same way as a human would. ‘Our store opens at 9am tomorrow morning and closes at 5pm’

Have you ever asked Siri or Alexa for a weather update in your area? This is also a chatbot and, using your location, a response can be given, in natural, conversational replies.

So, what is going on behind a chatbot front end?

To answer this question we must understand that there are two types of chatbot.  As we mentioned above, all chatbots are a form of AI, and all chatbots are supported by complex programming. However they fall into two categories.  The way they are split depends on whether the dominant feature is hardcoded questions/answer or the AI. Chatbots that function on structured questions and answers are less complex and chatbots that function on machine learning harness the full power of AI.  From the front end they both look similar and as a user, you may not be able to distinguish the difference.

Scripted and structured

A chatbot working on hardcoded questions/answers has a smaller knowledge base and skill set, and can only provide the correct output to specific instructions.   This means our questions must fit with the programming they have been given.  Using our weather chatbot as an example once more, the question ‘Will it rain tomorrow’ could be answered easily. However if the programming is not there, the question ‘Will I need a brolly tomorrow’ may cause the chatbot to respond with a ‘I am sorry, I didn’t understand the question’ type response.  This bot can only be as smart as the programming it has been given. So if you struggle being understood, you might be taking to a chatbot with structured questions and answers.

Free to expand

Machine learning bots harness the power of AI, which gives it a learning brain.  It can understand language meaning the commands you give do not need to be so specific.  An AI chatbot will figure out that umbrellas and brollys refer to rain, and therefore a deviation from the standard question will not phase them.  This means machine learning chatbots get cleverer the more they are interacted with.  Obviously the amount of work behind the scenes is greater, but that doesn’t mean you need to master AI to have such a chatbot working for you. Chatbots are certainly not something to be feared, but rather something we should embrace for enhancing our customer’s UX.



Leave a Comment

Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text.