Those of you who have ever written a chatbot have probably encountered several error messages, such as: "Sorry, I don't understand your questions", which the chatbot answers. Perhaps you have even experienced that your self-developed chatbot receives extremely random questions from users who clearly only test the chatbot limits. These irrelevant demands are also called conversation divergences, which cannot be prevented.

Usually a chatbot is created to solve a specific use case or to provide a specific value. Therefore, he is obviously not in a position to answer all possible questions. So if the chatbot sends out a so called error message (also known as Fallback Response or Default Response), this basically indicates that it was not able to process the request and link it to a suitable intention. Keeping in mind how new the technology is and how fast AI will evolve, this is definitely not a criterion for not giving a bot a chance. In fact, if you know how to deal with the user in such situations, there is a high chance to ensure a positive user experience in communication. On the other hand, there is also the danger of damaging the user experience by sending poorly thought-out error messages. It is one of the main tasks of the chatbot to keep the user involved in the communication without leading him into dead ends.

In this blog post you'll learn how to write user-friendly error messages by demonstrating bad and good examples and introducing a standard framework, how to design error messages to prevent users from getting lost in the conversation.

How does error handling actually work?

How not to do it:

Example of bad chatbot error messages

The above examples show very well how error messages should not be handled.

  • The conversation on the left side with "The Weather Channel"has not provided a user-friendly answer because it only refers to the error without giving details about the cause. Also, asking the user to "try again" isn't really helpful, as he doesn't know exactly what went wrong and what he should do better next time.
  • Chat with "Dallas Mavericks"in the middle actually shows many improvements. There are definitely more ways to communicate than asking the user to use cryptic input. What is noticeable, however, is the negative undertone of "Hmm, sorry, I don't quite understand that". This error message simply gives the user the impression that the chatbot is not making much effort to please him or help him .
  • The final example on the right side of the screen does not provide a helpful formulation for the default message. It is obvious that the user will leave the chat because the chatbot does not even work because it always sends the same answer. Speaking of which, if you've already written user-friendly error messages, it's still important to implement variations of them! The probability of misunderstandings occurring more than once in a message is very high. So you don't want to annoy your users by sending the same messages.

Let's take a look at experts: Poncho's Case

The developers of the most popular chatbot Poncho, which can send weather forecasts, have also realized how important it is to write well thought-out fallback answers. For example, they implemented the following error message at the beginning:

"Sorry, I tried charging my phone. What were you gonna say? „

So what exactly went wrong? In this message, the chatbot apparently overlooks the fact that he did not understand the request. Unfortunately, this only leads to an infinite circle, since the user will repeat his question, which will be followed by an error message. The person has no idea how to deal with the chatbot and will soon leave the conversation. So the developers of Poncho came up with a better answer:

"Well, I'm good at talking about the weather. Other things don't suit me so well. If you need help, just type "help".

In this version the chatbot is uncomplicated. He explains that his only purpose is to talk about the weather and that the user should not expect to know more. He also mentions the help section to give even more help. The people behind Poncho realized that this was a better strategy to address users in these situations. To perfect error messages, we will now sketch a framework.

A framework for error handling

1. Clarification of the misunderstanding

The first step is to clear up the misunderstanding. It is important to be very transparent, honest and modest about the abilities of the chatbot. Errors should not be overridden. If the chatbot is not able to understand the request, this should also be communicated.

2. Remind the user of the abilities of the chatbot

In the second step, it makes sense to explain to the user once again what information the chatbot can provide. So if you remind the user of the knowledge, function and skills of the bot, he will be ready to ask the right questions.

Third call to action!

Calling actions is the right way to guide the user. You can either suggest him to use buttons, ask his question in a different way, or enter a keyword like "help" to re-read the documentation. It might also be useful to offer the user a handover to a person to ensure satisfaction or sometimes even restart the whole conversation. There are several options to keep the user in conversation to keep the termination rate lower.

Good examples

Conversational UX

Above you will find better versions of the standard answers. In the Porsche chat on the left, the user received a clear call to actions, either to a real employee to ask questions or to use the buttons below. Same case with ShoeDazzle. The chatbot is aware of his abilities and tries to lead the user out of the impasse.

To summarize this contribution, it is extremely important to focus on the critical parts of a conversation to prevent the user from getting lost. Error messages are crucial events. If you want to use this framework during the Conversational Designs of a chatbot, you will ensure a great user experience. Finally, you should consider the following:

Rule #1: The user is never wrong and it is never his fault! 😉