This article was originally published on QBox’s blog, prior to Cyara’s acquisition of QBox. Learn more about Cyara + QBox.
Chatbots are conversational by definition. They’re designed to hold conversations with a human, using natural language processing. But chatbots don’t think like a human and they interpret language in a different way than humans do, and they can therefore be easily broken. And it seems to be a human trait to test a chatbot to its limits, perhaps because it is human nature to see how far they can go, or perhaps to confirm it’s a chatbot rather than a human!
Cyara empowers businesses to test, monitor, and optimize chatbot performance through the entire development lifecycle.
However, a chatbot builder’s job is not to trick the user to think it’s a human—this should be made clear from the very first interaction that the user is talking to a chatbot—but rather to impress the user with its intelligence, and therefore (hopefully) encouraging further interaction, instead of just getting frustrated with the dreaded “I’m sorry I don’t understand!” response.
Part of a chatbot builder’s objective is to try to limit the number of times the chatbot “breaks.” Preventative steps can be taken to avoid these instances, and here are some top tips and best practices that may help.
What Should You Look Out For?
Some users will inevitably ask these types of off-topic questions:
- Are you a chatbot?
- How are you?
- How does this work?
- What is your name?
- How old are you?
Ensure you are prepared for these by training your chatbot accordingly, and have some short or witty answers to cover them. Let’s review a few possible examples of how you can proactively train your chatbot.
- If you have conversation flows where a user is expected to answer either YES or NO, make sure you also have the many alternative forms of yes or no in your training data that you can possibly think of, like nope, no way, I don’t think so, not now, or yep, ya, affirmative, ok, etc.
- A lot of users will say goodbye to finalize the conversation, so be sure your chatbot can respond to this (and cover the alternatives like farewell, be seeing you, so long, etc.). It’s surprising how many chatbots do not understand such a simple function!
- If your chatbot uses buttons, be prepared for users to type their responses instead of clicking on the button. It’s also worth pointing out to make sure you train your chatbot model to understand the actual text shown on the button too.
- You should also anticipate users answering outside the pre-selected responses. For example, you may provide your user with the option of women’s shoes or men’s shoes for a clothing company. However, a user might say “I want shoes for my husband.”
- Users may just simply ask for help without specifying what they need. All chatbots need to cater to this, so make sure your chatbot is trained to answer vague queries like “Can you help me?” or “I need assistance.”
Addressing Odd Questions
You will never be able to train a chatbot to answer EVERY odd or off-topic question that will get asked. But there are a few popular ones we’ve seen over the many years we’ve been reviewing chatbot customer logs that you can be prepared for such as:
- What is the meaning of life?
- Why is the sky blue?
- How much wood would a wood chuck chuck if a wood chuck could chuck wood?
- What is your favorite color/book/film/food/drink?
- Tell me a joke.
- Can you beat the Turing test?
- Any weather questions (especially if it is a British chatbot—us Brits are obsessed with talking about the weather!)
In many cases, you can add responses into your chatbot model with minimal training. Then, for any other odd questions that the chatbot has not been trained in, instead of just the stock response of “I’m sorry I don’t understand,” you can consider ways to encourage users to ask a more relevant question. For example, your chatbot could say “Hey that’s not my area of expertise, how about asking about our current offers on xx or how we can help you with xx.”
Additional Considerations
Here are a few additional tips that can help you set your chatbot up for success:
- Prepare for filler language like, “hmm,” “ohhh right,” or “tell me more.”
- Train your chatbot to address instances when users want to “start over.” In this case, a user may have come to the end of a particular conversation flow but wanted to get information on a different subject. A user can become very frustrated if they’ve already given some information that should be remembered, but the only way they can start over is by shutting the chatbot down, starting from scratch and giving the information all over again.
A chatbot should always give a satisfactory answer to any question a user asks, no matter how silly or off-topic it may seem. And you should always give the user the option to handover to a real agent.