Over the last few months, I’ve been focused on product design for chatbots—both text and voice. As a UX designer with a background in graphic design, it’s been refreshing to shift focus towards non-visual user experiences.
Culled from my research on conversational chatbot interfaces, user journeys, personas and bots I’ve created with talented engineers at Wizeline, here are my tips for designing the best chatbot experiences.
Hook your user
The most basic chatbot user experience is to inform the user of your bot’s capabilities, so they know what to expect from it in the future.
It is just as crucial to offer some automated content to push regularly, to re-engage the user rather than wait for them to interact with the bot. For example, pushing the latest news every morning, a local weather forecast on Mondays or the Premier League results from that week.
Customizing content then takes engagement one step further—if it’s a sports chatbot, it should ask the user for their favorite team and then offer a daily digest with latest stats, draft picks, interviews and exclusive content. You will certainly gain more subscriptions if the content is tailored to the user.
If you don’t engage your user from the beginning, the chances for repeat engagement will be nominal — it could take days or weeks until they remember your bot exists.
When in doubt, be generic
While onboarding or subscribing your users to notifications, let them know they’re in charge and can easily change their minds in the future.
Provide special keywords to trigger these settings, the more generic the better. For example, asking a user to remember complex keywords like “Daily Updates” doesn’t feel natural, and the learning curve will cause them to disengage.
Keep it simple and allow for keywords such as “Notifications”, “Settings”, or “Help”. All of these keywords are conventions for conversational interfaces.
Lead the conversation
Congrats! Your onboarding is perfect. Thanks to your clear instructions and timing, you communicate bot capabilities and how to ask for help, change settings and display the main menu. Awesome. Say the next day a user comes back, opens the chat window and… nothing. Your bot is quiet and shy, expecting instructions.
If you’re lucky, users will scroll up and click on an actionable element to resume the conversation, but most of the times they won’t—and may even forget what your bot can or can’t do.
In other words, it is your bot’s job to take the initiative. Identify the moments in which the user opens the chat window and says hi, and use that opportunity to start a new conversation and offer guidance.
Imagine one of your goals is to increase traffic to your company’s website, and you want your chatbot to serve as an entry point for users will click through and read your content.
You could simply provide a card with a web page title, a photo and description. That is a simple solution. But what if you provide a few lines of information before showing the link to the actual web page? You could engage your users first with a preview of the page you want them to visit.
Let’s take it a step further—you should make it look like a conversation. Don’t throw out a 50-word paragraph and expect your user to read them all. Think of how would you introduce a new topic to a friend—they want to hear the full story in detail. While you chat, use short messages and pauses. Allow users to finish one paragraph while the bot “writes” the next one, and display this loading speech bubble on their screens as the bot “types”.
Timing is critical here, the number of seconds or milliseconds the loading bubble is visible should be proportional to the length of your last message (not the next one), which is the one they are reading. If you throw the next one too soon or clutter the screen with a bunch of paragraphs or images, they may feel overwhelmed and will probably stop paying attention to what your bot has to say.
Keep the conversation going
Connect the conversational pieces of your chatbot in a way that the user won’t run out of options. That way, users will be able to navigate from one flow to the next without needing to access the main menu. This is a true conversational interface.
Here’s an example: imagine you are designing a chatbot that teaches people how to cook recipes from all over the world. On your system, you would have several entities:
Each of these entities would have their own properties:
Now, let’s pretend the user asks your chatbot for recipe ideas for tonight’s dinner. The chatbot may throw a carousel of cards with a bunch of recipes, and each card will display the most relevant properties of this entity: photo, name, author and cuisine.
Looks good, but what if we add more options by connecting this entity with another one, based on their properties?
If we do this, users will be able to navigate from “Recipe” to “Author” without exiting the flow to begin a new search. Same case goes for the “Cuisine” route. This makes the full user experience much more fluid.
This method is not new, particularly among eCommerce websites and blogs. I find it particularly necessary when designing chatbots, since we rely on a linear conversation and it’s all too easy for flow to be disrupted.
Target the right audience
People who visit your website or uses your mobile application may not be the same people who end up interacting with your chatbot.
For example, according to the Digital News Report of this year, the way people consume news today is very different than three years ago. This year, 51% of consumers between 18-24 obtain their news through social media. They don’t visit specific websites or blogs, but rather subscribe directly on Facebook or Twitter. It’s quick access from a variety of sources.
Why is this important? Newspapers or blogs planning to release chatbots, take note of the following:
- It’s reasonable to assume the same people who consume news on social media are the same people interested in chatting with your bot on Facebook.
- If you are still deciding between a social media chatbot or your own, and you want to target millennials, this could help you make the decision.
- The content that you push and the tone and language of your bot may be very different that what you have thought initially.
My point is that you should know your users first. If you don’t target the right audience, you may end up providing content your users are not interested in, or using language that may be too formal.
If you do target the right audience, you will know how to narrow your product to something that solves one problem in the best way possible. This could tap a new market segment, eventually increasing conversion ratings for your site.
When designers work on websites or applications, we think about the visual hierarchy we should assign based on user goals and needs. If we do it wrong, users become distracted by other less relevant elements, and become lost on the journey to complete the task for which they first came to our website.
With a chatbot, the process is not different. What varies here is the set of UI elements used: text, cards, images, emojis and quick replies. Initially, these elements may seem a bit limited, but they are more than enough to make users want to chat with your bot.
Forms, alerts, drop-down lists, checkboxes, etc. are elements that were created to maintain a conversation with the user. Now that the interface is conversational, intonation and timing are much more important if we consider that the attention of the user is focused on one thing: what your bot is saying and what it actually means.
Guest post by Wizeline UX Designer Joel Monteon.