Reinventing mobile UX with bots
How we got here
Over the last several years, our expectations for what computers should do for us have transformed dramatically. What were functional tools that sat on our work desks only ten years ago have evolved to fit in our pockets, capture our memories, and reshape how we communicate with family and friends. With each passing year and each new leap in consumer electronics, the devices we love to use have continually become more accessible, more integrated, and more adaptable to our everyday lives.
The first 50 years of computer science were a story of humans adapting to computers. The next 50 will be a story of computers becoming more human.
One of the first trends in this new trajectory is conversational UI, a new user interface technique that’s becoming increasingly popular on mobile. Better known as chat bots, these programs are an evolution of user interface design that allow users to communicate with a digital experience using their own words and on their own terms. We examined how brand apps in particular can leverage conversational UI best practices to enhance their own apps, and what considerations should go into developers’ experiments with their first chat bot.
Table of contents
- How we got here & understanding bots • 5 minute read
- Why bots work
- How bots fit into your app’s UX • 4 minute read
- Building your bot
- What’s next
Why bots work
The most compelling thing about chat bots is that they don’t need a manual. They allow users to engage with digital products using their own words and on their own terms. Natural language processing has reached a degree of maturity that bots won’t need to know the exact phrasing of every possible request in order to act upon every single request—and that intelligence is only accelerating as bots proliferate.
But using a digital product on the user’s own terms extends beyond literal “terms.” Consider the mobile best practices for organizing an application’s content and navigation. Perhaps there’s a tab bar at the bottom of the screen, or a hamburger menu at the top left corner. Maybe options are laid out in a hierarchical table, and certain content or actions are obscured from view until the user drills down through enough menus. There’s a certain language to it, which can be optimized for as many users as possible, but it’s a language that requires a degree of UX fluency all the same.
With messaging bots, users don’t have to learn anything. If they assume the bot can perform nearly any action they’d expect of the brand—and if there’s graceful error messaging when it can’t—the interaction they have with a bot requires no thought or prior learning. This is enormously powerful as mobile reaches new audiences of varying ages and technical literacy. Imagine someone using an ecommerce app who’s never used a smartphone before. Now imagine that same person dictating requests to a chat bot that can peruse the entire store without the need to drill through various menus.
Example in practice
Consider these two incarnations of the Spring app, a popular fashion-focused ecommerce product. On one hand, you have the traditional mobile app user experience, complete with menus and navigation paradigms that would be familiar to most smartphone users. For all its gloss and flat UI design, the app still requires users to be familiar with the trends of how ecommerce sites and apps have always been organized, meaning users would have to navigate through “Women,” “Tops,” “Blouses,” and so on to find the item they want.
Alternatively, consider the Spring bot for Facebook Messenger. Here, the user can immediately request the kind of item they’re shopping for, and the bot provides them with actionable results. No searching, browsing, or poking through menus organized by even the most competent UX designer. Just a request and a response.
Messaging services are the most heavily used apps across mobile platforms, with more than 2.5 billion active users sending trillions of iMessages, WhatsApp messages, SMS messages, and Messenger stickers every day. These services account for a significant portion of the reason that mobile users pull their phone out of their pocket every few minutes, and these communication methods form the backbone of billions of people’s mobile experiences.
These figures indicate that the user experience of composing a message and sending it to a friend is now universally understood among nearly half the planet—and Activate projects messaging app usage to increase to 3.6 billion in the next few years. This is an interaction method that doesn’t need to be taught, because it’s most of what billions of people are using their devices for anyway.
For brands and third-party app developers, this universality of experience should indicate that your apps have a thing or two to learn. Third-party apps should reflect the interaction paradigms users are most familiar with. And in the age of WhatsApp and Messenger, that interaction is more likely to look like a chat conversation than anything from UIKit or Material Design.
Third-party apps should reflect the interaction paradigms users are most familiar with—and in the age of WhatsApp and Messenger, that’s more likely to look like a chat conversation than anything from UIKit or Material Design.
Further, because of the explosive growth of these messaging services, they’ve become hotbeds for innovation among developers and evolved into platforms unto themselves. Today, services like Facebook Messenger, Kik, Skype, Slack, and even iMessage have introduced features that allow third-party developers to build apps and services within users’ messaging conversations. And considering that the top four chat apps have a larger combined user base than the top four social networks, according to BI Intelligence, there’s already an enormous user base waiting to discover your app.
Building apps for Messenger or iMessage puts your brand squarely where your audience already lives, and within the services they already love. This not only aids discoverability of your service, but also accessibility for users who might not be as familiar with mobile UX patterns that others might consider obvious. Bots are the way that brands can take advantage of the global messaging app phenomenon—but that isn’t to say they’re easy to get right.
Building your bot
Because many of the largest players in the messaging space also happen to be the largest players in the conversational UI space, there are many technologies that already exist to facilitate building chat bots that integrate with these services. With open-source platforms offering APIs that scale the bot’s conversational logic across multiple messaging services—and even into proprietary brand apps and websites—third-party developers have ample opportunity to experiment with the conversational UI model without having to develop the learning and conversation modeling algorithms for themselves.
While there is a diverse toolset of technologies at developers’ disposal, they share many of the same fundamental components and functionality. Central among these is teaching bots how to learn—helping them parse the unique vocabulary and request types for each distinct application and service. Thankfully, this is particularly what the open-source artificial intelligence platforms are focused on solving for, removing a massive obstacle for developers. All brands need to bring to the table is a handful of key reference data, and in most cases the bots can handle the rest.
Teaching bots to learn
Many of the open-source AI platforms rely on developers to submit reference data or requests to the bot that will help it extrapolate meaning from users’ messages. Here’s an example of how to teach a bot to adapt to varying user requests, in this case for a bot that gives weather forecasts.
- Reference query. First, developers need to provide a sample query that a bot should field. This could be something like, “How will the weather be in Cleveland on Wednesday?”
- Identifying intent. Next, developers should help the bot understand its purpose in this instance, which would be to retrieve a weather forecast. Bots can have several purposes, called users’ “intents” when they submit a message, and these can be identified by a number of different keywords or variables. Identifying the intent for this message helps the bot to understand what kinds of supplementary information it should look for—or ask for—and what kind of data it should ultimately respond with.
- Elaborating with entities. Entities are the variables of the user’s request, which in this instance could include things like cities (“Cleveland” might be substituted for “New York” or “Chicago”), times (“on Wednesday” could just as likely be “this evening” or “next Friday”), or even forecast types (a general request like “weather” could also be more specific values like “precipitation,” “temperature,” or “humidity”). By providing reference entities and some examples of alternatives, bots can begin to parse users’ sentences and better narrow their response options. In particular, platforms like wit.ai offer ready-made entities for common requests like locations or times of day, eliminating the need for third-party developers to volunteer that data themselves and accelerating development.
- Correcting for errors. In instances when the user doesn’t submit all of the entities necessary for the bot to appropriately field their question and address their intent, the bot needs to be able to gracefully handle those errors and ask for more information. In the example given above, if the user doesn’t mention Cleveland or any particular location, the bot might respond with “Where?” or give results for the user’s current location. If the user gives more detail, the bot can then append the request with that new entity value and provide a more accurate response.
- Testing and enhancing. Like any software, the best way to test for bugs is to start using it. Many of the bot AI platforms offer a console-like interface for chatting with the bot and seeing examples of where it responds with appropriate data or where it falls down. Over time, developers can plan for common problems and ensure that conversations progress in an organic, logical way.
Teaching users to interact with your bot during onboarding is a popular best practice in preventing embarrassing errors. For the most part, the leading conversational UI programs offer “what I can answer” sections that help users understand what they should expect of the bot and its capabilities. Giving examples of the requests your bot is equipped to field helps prevent frustrating bugs and gaps in conversation logic from derailing the user experience, but it’s important to remember that no software is perfect—especially bots. For this reason, graceful error handling is imperative for users to trust the technology. Users are more forgiving of a system that’s honest about its faults (“I’m sorry, but I’m not sure I understand. Could you try asking a different way?”) than of flippant and cheeky responses (Siri often says “That’s an interesting question” in response to queries it misunderstands).
The leading bot intelligence platforms have APIs that allow them to interface with many different technologies, including apps on both iOS and Android, within SMS conversations, on a myriad of chat platforms like Slack, Messenger, or Skype, and within websites and web applications. It bears repeating that many of these bot platforms are designed and open-sourced by the stewards of the messaging platforms themselves—Facebook acquired wit.ai, which interfaces nicely with Messenger, while Microsoft’s Bot Framework is designed to fit well into Skype. Most of these platforms are free to use and easy for developers to program, meaning that technology limitations are no longer inhibitive of adding a great conversational UI experience to a third-party app.
Technology is no longer an obstacle to developing a great conversational UI experience for your app—what matters most is finding ways that bots can offer value to users.
In fact, while these technologies have equalized the playing field for developers, the challenge remains to find a worthwhile user experience that bots can facilitate within your apps. Brands need to determine the user experience they want the conversation to deliver before deciding on any one platform or technology, because—like with native development—there are many technology solutions that are better suited for one UX goal over another. However, the right marriage of a conversational UI experience coupled with a compelling value proposition for the brand’s audience can yield a more engaging and interesting mobile product than anything possible with traditional digital tools—which is reason enough to begin exploring.
What’s next
There are already many compelling examples of conversational UI experiences in the market, some more experimental than others. But already, users can order an Uber from a chat conversation within Facebook Messenger, catch up on the news from CNN, shop for clothes with Spring, or discover their company’s marketing statistics using Statbot in Slack. Further, there are solid examples of conversational UI–centric experiences within native apps, like Lark for health and wellness or Quartz for a choose-your-own-adventure style messaging thread for the news.
The largest technology players are already active in this space, offering frameworks like SiriKit to extend iOS apps’ functionality into Apple’s tentpole virtual assistant, or enhancing Google Assistant and messaging app Allo to allow for third-party input. This is a trend that only promises to accelerate, and the apps that begin collecting insights and analytics about users’ interactions early will be those who can begin streamlining and enhancing their conversational experiences first.
Bots are certainly in vogue as a mobile UX strategy, but trends and usage statistics suggest that they’re anything but a fad. In the future, certain types of experiences will be delivered exclusively as chat bots, and will deliver the same functionality we’re accustomed to in a more intuitive and expressive way than ever before. Users’ expectations for mobile experiences have begun to shift dramatically, such that they expect dialogues with bots more frequently than apps’ dialogue windows. Just as brands have had to adapt to an evolving mobile landscape with smart UX design and digital services, so too will they need to adapt to an emergent conversational trend—tomorrow, the brands we rely on for everything in our digital lives will need to be conversant in “LOL.”