How Chatbots are Changing Design

Conversational UI is getting a lot of buzz out in the world, and for good reason. SMS is going through a renaissance, and its immediacy and accessibility make it an ideal channel for building services at a time when apps are no longer the medium for digital experiences.

Beyond the buzz, conversational UI shows us that everything in design should be considered a conversation. All elements in an experience are exchanges between people, brands, businesses, services, and, increasingly, machine-powered intelligence. Conversation is the primary design material for designers — and its general purpose is to impact people’s behaviors and emotions.

Designing Conversations

The ambiguous design process.

These days there’s a strong focus on chatbots and conversations as end products, but in our IDEO New York studio, we’ve been using conversations as a prototyping tool to test assumptions, learn, and inspire design. Chatbots are exciting, but we’re also excited about what they unlock for us as a learning medium, not just because they’re the next big thing.

Here's one of our experiences using chatbots as a design tool.

Walkbot: Prototyping Content and Engagement

In 2014, together with a Japanese electronics manufacturer, IDEO designed a device and smartphone app that captures a woman’s activities in order to generate thoughtful, actionable insights about her fitness choices.

At the time, wearable devices were heavily marketed towards men. The women we were addressing wanted meaningful content, and were far more focused on competing with themselves than with others. It also turned out that our product was too data-heavy.

"I like that it’s there if I need it. It’s kind of like a little friend." [anonymous user]

Walking alongside our participants during field research.

The dashboard created to communicate with users and track responses.

To uncover what meaningful content looks like for these women, we went to the women themselves.

A software designer on our team built a custom tool leveraging Twilio’s SMS API, and created an SMS platform that a team of people could use to manage and direct messages. We recruited a panel of women, and during their workouts, a team member would send messages like “great workout, keep going” or “you’ve walked ___ steps today, add a 5 minute walk to reach 10,000.”

Lisa: “Ugh, he wants me to pick up my intensity and burn more calories.”

IDEO: “How do you know it’s a man?”

Lisa: “Because I’m mad at it right now."

An example of our real-time SMS prototyping — a team member would secretly text messages to our participant during her workout.

The responses were surprising. For one thing, women who participated in the design research would project gender and personality on to our bot. In moments of frustration, the bot was referred to as a “he,” when, in fact, the messages were coming from our female colleague. For another, not only did the women want to share their activities, they also wanted to share their failures. For them, fitness wasn’t purely about achieving a goal, but also the process it took to get there.

What we learned:

• The best way to understand what a conversation needs to be is by starting it. Figure out tone of voice, pacing, and interactions  as it unfolds.
• It’s possible to make conversations feel more personal with only a few data points. Be intentional and creative.
• Every participant will project an identity onto the bot — regardless of whether the design team gave it one.
• Bots allow for a nuanced interaction that might bring surprising elements to your product. Be willing to pivot in response to happy accidents.

Our Chatbots Protocol

During the past few years, the interaction design and design research teams at IDEO New York have worked closely with real people to test value propositions and the desirability of digital products and services. Together, we built ad-hoc tools that helped us design conversations with users, and engage with them in real-life contexts.

As we planned and ran these prototypes, we developed a set of principles we now rely on in our research.

• A prototype is a question, embodied. What are you trying to learn? Who are you learning from?
• Hack existing tools. There’s no need to build from scratch.
• Iterate in real-time. The beauty of SMS is that you can adapt quickly.
• Be explicit about the intentions of your work, and make sure that your actions are in line with the ethics of field research
• Consider all the stories, anecdotes, and insights you gathered through your chatbot to inspire the design.

Meet Stanley

There are several services that can help you set up an SMS-based platform. Alternatively, you can create your own conversation bot following the instructions we shared for Stanley, the SMS-based platform that we use.

You can find the source code, and the instructions to setup Stanley here.

For some more on using bots for design research, read this article on IDEO Labs.

The above is an abridged version of a longer Medium article that details three case studies where we’ve used chatbots to prototype services and products. Read the full article here.

Illustrations by Amy Wang.