Guide to how conversational UI and chat bots can help reinvent any app’s UX
Conversational UI is an industry buzzword—but its overarching themes can actually help any mobile experience feel more lifelike
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.
These trends are a continuation of what computers have been doing since the first PC. The first 50 years of computer science were a story of humans adapting to computers, rethinking their thoughts around word processors and discovering new business models that fit into the web. The next 50 years will be a story of computers becoming more human — changing how we interface with them beyond mice and keyboards and instead incorporating elements of how we interface with other humans.
The first 50 years of computer science were a story of humans adapting to computers. The next 50 years 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’ve 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.
Chat bots are a quintessential mobile trend — something flashy and tech-forward that some brands are sloth to adopt. But what their conversational UI model represents is something greater: a revolution in how humans interact with computers, the descendants of which will define our mobile experiences for decades to come.
The idea of a chat bot is nothing new, but it’s growing in popularity as a user interface technique for mobile experiences. This is mostly due to the massive adoption and ubiquity of messaging apps, many of which have hundreds of millions of users and are poised to become development platforms unto themselves. While chatting with a computer is a concept that dates back well before the age of AOL Instant Messenger, the idea of marrying this interaction paradigm with new advancements in natural language processing is actually the latest in a series of transformations in how we interact with digital products.
Marrying a chat-like interaction paradigm with new advancements in natural language processing represents a transformation in how we interact with computers.
To understand the significance of this shift, it’s important to recognize its context in the evolution of user interface models. One of the biggest transformations in how people interact with computers was the graphical user interface (GUI), which replaced the command-line interfaces of the 1980s with dynamic and visual user interfaces populated by buttons and windows. The change was intended to bring digital experiences closer to our experience in the real world, which is filled with physical objects that represent our work and play spaces.
In 2007, the capacitative touchscreen on the first iPhone allowed for a new input method, where users could simply tap on-screen items to perform actions. This was bringing the interface language of computers further into human context — there’s no abstraction of a mouse-and-cursor when people interact with objects in the real world, so why should there be such barriers when they interact with information in the digital world?
The trend is obvious in hindsight: each of these changes brings the digital world a step closer to our physical human experience. We understand spacial relationships better than a lexicon of computer commands. We understand direct manipulation better than indirect mouses and cursors. As computers become more powerful, and the services that run on them become more sophisticated, new interface paradigms are necessary for humans to more closely relate to the digital experiences in our lives.
And this is where bots come in — a new way to interface with computers that more nearly approximates the experience of interacting with a friend.
What are bots?
Chat bots are web-assisted programs that allow users to perform actions or get information that would have traditionally required opening an app or navigating to a website. Need the weather? Shoot off a chat message to a Slack bot and get an immediate response. Want to shop for new clothes? Ping a Messenger bot for images and prices from your favorite store. Put simply, bots represent a way to perform the same actions we’re accustomed to on mobile devices in a new way, a way that’s more intuitive and expressive than ever before.
Bots perform the same actions we’re used to on mobile devices in a new way — a way that’s more intuitive and expressive than ever before.
This approach works because technologies exist to understand users in natural language, allowing anyone to compose requests and have the computer understand them. Whereas app user experiences before mandated that users engage with them on the apps’ terms — having static buttons and a limited set of input options — chat interfaces and natural language processing allow users to engage with apps on their own terms, choosing how they express their requests from within their natural speaking style and using their own language.
Just as the GUI’s “desktop metaphor” helped bring an increased level of familiarity to digital experiences in the 1980s, so too do bots bring an increased level of familiarity and comfort to engaging with digital systems in 2016. Billions of people chat with friends and loved ones on their mobile devices, sending trillions of texts and iMessages and WhatsApp messages every day. It’s a natural extension that they would begin chatting with their mobile apps, too.
Going forward, this new experience will evolve to support voice input, and products like Amazon Echo and Google Home are the first players in this new category. The closer to ordinary life that a digital experience can feel, the better — asking Siri about the weather will be the modern equivalent of having “folders” on your “desktop.”
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 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, 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 messaging app phenomenon — but that isn’t to say they’re easy to get right.
How Bots Fit into Your App’s UX
When considering how bots can integrate into an existing app or service’s user experience, it’s important to note that the changeover to embrace the bots-centric conversational UI paradigm doesn’t have to be total. The chat bot–type interface is flexible, and can extend to include as much or as little of a digital product’s experience as makes sense for the user. There are three primary ways that bots can be integrated into a mobile user experience.
Bots can become the core user experience for certain types of apps. This doesn’t work for every app’s user experience, but some apps can afford to reinvent themselves to be fully conversational UI–focused. This works best for apps and products that already feel conversational, rather than transactional, where the primary methods of user feedback and interaction are a give-and-take of information between the human and the system. If this experience can be made to feel more personal through a chat bot–like interface, then rethinking the primary UX around a text conversation could make a lot of sense.
Bots can be integrated into an app to support one feature or functionality. While not every app can support a conversational UI approach as the primary interaction model, some specific features of those apps translate well to a text-based chat bot UI. For example, if the primary function of the app’s user experience is best represented as a traditional button- or table-view–centric interface, but there’s a customer support portal that requires two-way communication between the user and the app, it could lend itself well to a chat-bot-style UX makeover. Further, if the on-boarding flow for a particular app is long and arduous, requiring the user to complete several forms and volunteer information about themselves in a specific order, a chat bot can make that process feel lightweight and friendly rather than boring or intimidating. Again, this doesn’t work for every app, but many larger mobile products have areas or features that could be better represented as a conversation.
According to data from the Evercore Group in the Wall Street Journal, capturing half of the predicted business for customer support via a messaging interface would represent a brand-new revenue opportunity of $4 billion for brands.
Bots can be an extension of your app or service within third-party platforms. This approach is perhaps the lowest barrier to entry for third-party developers, but one of the toughest justifications for inserting a chat bot interface for a mobile product into users’ lives. Bots can extend the product’s services or data into third-party platforms like Facebook Messenger, Slack, or even Siri with SiriKit in iOS 10. Each of these platforms comes with its own strengths and limitations, but integrating digital services into new contexts like messaging platforms presents an opportunity to interact with customers in the apps they already use. For users, it’s much easier to strike up a conversation with your brand in the Messenger app they already have installed rather than seeking out your app on the App Store and waiting for it to download.
So how should brands approach this problem, and determine how bots would best intersect with their mobile products? For starters, it’s important to consider how and where users already expect to interact with your brand, your services, or your data. Considering users’ contexts when they seek out the services your digital product provides can help qualify or eliminate any of the places bots could be incorporated into your experience. If users need quick and easy access to your app’s data, perhaps adding a Messenger bot and other bot environments to your brand’s digital portfolio makes sense. However, if users only have a conversational relationship with your brand when they’re seeking out one-on-one customer support, perhaps adding a chat bot help line as one feature of a larger mobile experience is a better option.
Gartner claims that 85% of all customer interactions won’t require human customer service representatives by 2020, and instead will lean upon automated analysis of social media channels, CRM software, and personalized chat bots to greatly reduce the need for traditional call centers.
Secondly, it’s critically important to be mindful of providing bot-like assistance only when users actually need or request it, and avoid nagging users with unhelpful or irrelevant messages. The infamous Clippy character from Microsoft Word is a perfect example of what is ostensibly a “chat bot” verging on the annoying. The reason users hated Clippy wasn’t just that he was so often wrong — offering help with composing a letter when users had no intention of writing one — but it was because if a bot isn’t providing any real value, and instead is just a gimmick, it’s a nuisance that can sour users’ perceptions of your app. Before anything else, brands need to identify a place where a conversational UI can provide real value to users, and that may be within the confines of an app or website, and it may be outside of them.
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 this weekend?”
- 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 (“this weekend” could just as likely be “this evening” or “next Wednesday”), 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 on-boarding 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 User, but I’m not sure I understand. Could you try asking a different way?”) versus offering flippant and cheeky responses (Apple’s 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 native platforms, 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 developed and open-sourced 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.
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.”
BY Connor Mason // October 5, 2016 When considering how bots can integrate into an existing app or service's user…www.punchkick.com
This guide was originally published by Punchkick Interactive. For more information about user experience, mobile development, and more, check out punchkick.com.