Interaction 19
4-10 February 2019
Seattle, WA
United States

How to (Build and) test conversational / spoken UIs

workshop – Full day (8h) | Feb 5 – 9:00

Learn best practices, tools, and tips for chatbots and more generalized AI from someone who did this recently; I’ll share pitfalls to avoid and tips for reaching the best experience faster.

Sold out

This workshop is sold out. Check out the rest of our workshop program.

“Speaking from experience, I can tell you it’s virtually impossible to test intent. By this, I mean that when you are building a mostly spoken UI, such as Alexa, it is imperative to test your conversations early and often, but the kicker is that it can be really difficult to do with more traditional user testing techniques. Can you set up remote user testing sessions when there is no tangible thing or site to interact with? How do you perform in-person tests that mimic the ““real experience”” with lo-fi prototypes?

Having recently spent six months researching, prototyping, testing, and building some conversational UI components for a robot, I plan to share what worked well, including specific tools (Mural, Twine, paper prototypes), techniques (use an object similar to the ““real one”” if the source of your conversation is not yet built or too complex to build a working prototype, like a robot), and tips for success (test with literally as many people as possible, focus on the JTBD). We will cover doing this for chatbots, as well, and how that differs, but not as in-depth, as that is a topic that has been well-covered at content strategy and AI conferences lately.”


Generally, this workshop will consist of 75% hands-on activities, and 25% lecture time. Lectures will include foundational information on how the process and content differs when we start designing and writing conversational UIs, as well as concrete knowledge on how to use the tools which will be used in the workshop – Mural and Twine. Activities will span the day and will take participants in smaller breakout groups from creating a basic conversational UI architecture, through iteratively testing and revising it, and ultimately create a working prototype, which will be tested, revised, and presented back to the rest of group.

Target audience

Content strategists, business strategists, user researchers, interaction and experience designers and strategists may all find this workshop relevant to them. There is no particular prior knowledge needed, but knowing current best practices for HCI design and research will create the contrast for participants between how this differs from what we’ve been doing for click/tap interfaces for years. The primary audience is anyone who plans to wants to get into creating conversational UIs for bots and AI.

About the speaker

Stacey Seronick

Stacey Seronick

Currently, I am an AI Intent and Experience Strategy Designer at Wells Fargo Bank, within the Innovation group. I have been designing, writing and strategizing for services and products for about 20 years, and hold a Master’s degree in HCID. It has been a lifelong practice to design from and for the edges (“edge cases”) first, and to advocate for this point of view to others. Previous adventures have included designing and running my own couture line of latex clothing, managing a record label and talent booking agency, and being instructed in fitness techniques by Courtney Love. In my free time, I paint math-based oil paintings, write blog posts and poetry, and draw lumpy stick-people cartoons. And try to spare anyone else the pain of listening to me practice electric bass.

Code of Conduct   •   Accessibility   —   Copyright 2004 › 2018 Interaction Design Association   —   Credits   •   Media