You may have heard that “conversational interfaces” are the new hot trend in digital product design. Industry leaders such as Apple, Google, Microsoft, Amazon and Facebook are strongly focussed on building a new generation of conversational interfaces. Several trends are contributing to this phenomenon—artificial intelligence and natural language processing technologies are progressing rapidly—but the main reason why conversational interfaces become so important is pretty obvious: Chatting is natural for us since we primarily interact with each other through conversation.
A conversational interface is an interface that mimics chatting with a real human. Conversational Interfaces are currently of two types:
Building a genuinely helpful and attractive conversational system is still a challenge from a UX standpoint. Standard patterns and flows which we use for graphical user interfaces don’t work in the same way for conversational design. Conversational interface design demands a fundamental shift in approach to design—less focus on visual design and more focus on words.
While we still have ways to go before best practices for good UX in conversational interfaces are established, we can define a set of principles that will be relevant both for chatbots and virtual voice-controlled assistants.
One of the most challenging parts of designing a system with a good conversational interface is to make the conversation flow as naturally and efficiently as possible. The major objective of a conversational interface is to minimize user’s effort to communicate with the system. You want your conversational interface to seem like a wizard, rather than an obstacle, right?
Don’t try to design your system to do everything all at once. It’s better to create a specialised, purpose-driven chatbot/voice assistant to engage your target audience. It’s important to anticipate users’ needs and provide the right solutions with minimum user input. Answering on following questions will help you to define the purpose of your system:
The biggest benefit of the graphical interface is, that it shows you directly the limited options it is capable to fulfill. Basically, what you see is what you get. However, with conversational interfaces, the paths that the user can take are virtually infinite. It’s not a surprise that two questions most frequently asked by the first-time users are:
Users aren’t going to know that some functionalities exist unless you tell them, so it is important to guide the user promptly to start the conversation by telling them to how/where to start and how the conversational interface can help them. For example, if you design a chatbot you can start with a quick introduction and a straightforward call to action.
There are two types of questions:
While open-ended questions may seem the best in terms of human conversations, it’s better to avoid them whenever possible because they usually result into more confusion. Also users’ answers on open-ended questions are much harder to process for the system (the systems are not always smart enough to understand what the answer means).
The same goes for rhetorical questions. Most users tend to respond to them anyway, even if the system is just being polite.
As one of the original 10 Jakob Nielsen’s heuristics for usability, user control and freedom remains among the most important principles in user-interface design. Users need to feel in control, rather than feeling controlled by your product.
Users often choose system functions by mistake and will need a clearly marked “emergency exit” to leave the unwanted state. A standard GUI allows you to refine inputted data easily when processing it. Conversational interfaces should provide the same feature: neither conversation interfaces nor humans are perfect, so undo and cancel are essential functionalities for a smooth experience.
Users should be able to reset the conversation at any time during the interaction.
In order to eliminate error-prone conditions, it’s important to repeat and get a confirmation from users after they provide an input (especially for critical inputs such as payment information). Formulating confirmations as questions allow users to correct their input:
If the answer is valid, repeat it to ensure that everything is correct, and then move on to the next step.
If the inputted data isn’t valid, explain again what kind of answer you need.
Add help messages and suggestions for when the user feels lost.
Not only the flow of the conversation is important, it is also important to make the conversation sound natural.
Nobody enjoys talking to a robot that actually sounds like a robot. Follow the same user flow as you would if you were actually speaking to a person and be sure to design a system whose vocabulary and tone resonates with your target customers.
Long sentences sound like paragraphs. But people don’t speak in paragraphs, we usually speak using single short sentences. Avoid asking multiple questions at once, request information from the user or ask questions one by one. Once you get the right information, proceed to the next thing.