We sat down with a developer to get answers to some of the most common questions that we get from customers about chatbots. Here's what we found out!
What are chatbots?
Chatbots are essentially smart robots that are programmed to answer questions. They understand what you want and then give you the answer you are looking for.
Intelligent conversational chatbots are built on machine learning and become more “knowledgeable” the more you feed it data . It allows the website visitor to freely converse and type in their questions or responses.
A simple example would be when you ask a train company chatbot “When does the next train from London to Paris leave?” and the bot answers “The next train from London to Paris leaves at 14.00”.
How does a chatbot understand customers?
There's often a general worry that chatbot can’t understand the intent of a customer. The way that we approach this is to first train the chatbot with actual chat data.
Most companies that already use human-powered chat have existing logs of conversations. By using those logs to analyse what people are asking and they have meant.
With a combination of machine learning models it's possible to match questions that customer asks with specific intents that customers actually can have. For example “Where is my payment?” and “I have not received money”, mean the same thing as “How long does it take for the bank transfer”.
Our strength is being able to train our models, so that the bot is able to connect both of those questions to the correct intent and as a result provide the correct answer.
And even when such extensive data is not available, we have clever methods in place to extrapolate some of the existing sparse data to train the chatbot.
How do we teach chatbots?
Teaching happens the same way as you would teach a human. Only at a faster and much larger scale. When you teach a human customer service representative you show them the manual and have them read it and understand it.
With the chatbot, we essentially show it thousands of conversation logs and from those logs, the bot is able to understand what types of question requires what types of answers.
How does a chatbot continue to learn once it’s live?
Once the bot is live and interacting with customers we implement smart feedback loops. These essentially mean that when customers ask a question we give them a couple of answers by way of saying “Did you mean x, y or z”. That way customers themselves are matching the questions with actual intents (what they really want) and we use that information to retrain the machine learning model to improve the accuracy of the chatbot.
However, there are guards in place ensuring that the model will not change based on a few replies (that users cannot drive the bot crazy).
This is also ensured by the fact that the bot is not simply rephrasing what people tell it but is actually taught to answer things that the chatbot’s owner (i.e. the company) wants it to answer.
How does the bot know when to give the conversation to a human?
At the end of a conversation with the chatbot our bots ask “Did we help you” and when the person answers no, the conversation is forwarded to human support.
Similarly, when the chatbot is unable to understand the question that the customer asked, it forwards the conversation to human customer support.
Can we control the bot in any way once it’s live?
Of course. The chatbot is programmed to understand specific questions and its understanding can be expanded or shrunk according to the company’s wishes.
Bots are cool and useful. Especially in automating tasks that humans find tedious, so I welcome companies to think whether they have those workflows they wish to automate and let their employees focus on more creative work.
There you have it! Our top questions answered about AI conversational chatbots. Looking for a simpler chatbot solution? Download our 9 step guide to find out how you can build simple button-based bot without coding.
Editor's note: This blog was originally posted in 2017 as an interview with Indrek Vainu, Product Manager at AlphaBlues. It has since then been completely revamped and updated for accuracy.