Rosenverse

This video is only accessible to Gold members. Log in or register for a free Gold Trial Account to watch.

Log in Register

Most conference talks are accessible to Gold members, while community videos are generally available to all logged-in members.

[Case Study] Don't botch the bot: Designing interactions for AI
Gold
Tuesday, June 4, 2024 • Designing with AI 2024
Share the love for this talk
[Case Study] Don't botch the bot: Designing interactions for AI
Speakers: Savannah Carlin
Link:

Summary

It seems like every company is adding a conversational AI chatbot to their website lately, but how do you actually go about making these experiences valuable and intuitive? Savannah Carlin will present a case study on a conversational AI chatbot—Marqeta Docs AI—that she designed for a developer documentation site in the fintech industry. She will share her insights, mistakes, and perspectives on how to use AI in a meaningful, seamless way, especially for companies like Marqeta that operate in highly regulated industries with strict compliance standards. The talk will use specific examples and visuals to show what makes conversational AI interactions uniquely challenging and the design patterns that can address those challenges. These include managing user expectations, handling errors or misunderstandings within the conversation, and ensuring that users can quickly judge the quality of a bot’s response. You’ll gain a deeper understanding of the intricacies involved in designing interactions for AI, along with practical advice you can apply in your own design processes. Take-aways What to consider before you add AI to your product to ensure it will be valuable, usable, and safe for its intended workflows The interactions that are unique to conversational AI experiences and the design patterns that work for them Common challenges in designing conversational AI experiences and how to overcome them

Key Insights

  • Clearly define the primary use case before building a generative AI tool to ensure its relevance and usefulness.

  • High-quality, thoroughly vetted training data is foundational for trustworthy AI outputs, especially in regulated domains like FinTech.

  • Properly framing the initial state of the chatbot guides users to ask relevant questions and reduces irrelevant or out-of-scope interactions.

  • Loading indicators should be subtle; show loading dots before text appears and let the text rendering itself serve as feedback.

  • Supporting easy scrolling and navigation between prompt input and AI output helps users refine their queries effectively.

  • Error handling in AI chatbots shifts from fixing technical failures to coaching users on better prompt writing.

  • Transparency about AI accuracy, including disclaimers and source citations, is crucial to build and maintain user trust.

  • Accessibility must be integrated from the start, including keyboard navigation and screen reader support, especially given long conversational outputs.

  • User feedback mechanisms like thumbs up/down and source link interactions produce valuable data to iteratively improve chatbot performance.

  • Narrowing the chatbot’s scope at launch reduces risks and false outputs, with future plans to expand question domains carefully.

Notable Quotes

"You need to be very clear on the primary use case and what this tool will help someone do."

"If you have any doubts about the quality of the training data, do not proceed. Do not pass, go."

"When someone arrives at this tool, how do they know what to use it for? Framing the interaction is key."

"Loading dots should only appear before any letters show up; the text appearing itself acts as a loading indicator."

"People often forget what they typed and want to scroll back to their prompt to refine it."

"Error states are less about technical errors and more about helping people write prompts effectively."

"Being transparent about the tool’s accuracy and limitations is especially crucial in FinTech due to regulations."

"Every single output should have at least three source links to allow users to verify information."

"We made sure every person could navigate the chatbot using a keyboard alone to support accessibility."

"People were asking questions they might never have emailed us about, decreasing friction to learn more."

Ask the Rosenbot
Jennifer Fraser
What would Emmy Noether Do? Math, Models and Mulling in UX Research
2023 • Advancing Research 2023
Gold
Ariba Jahan
Team Resiliency Through a Pandemic
2024 • DesignOps Summit 2020
Gold
Sam Proulx
Accessibility: An Opportunity to Innovate
2022 • DesignOps Summit 2022
Gold
Jorge Arango
Scale Smart: AI-Powered Content Organization Strategies
2024 • DesignOps 2024
Gold
Alex Hurworth
Designing a Contact Tracing App for Universal Access
2020 • DesignOps Summit 2020
Gold
Dominique Ward
The Most Exciting Time for DesignOps is Now
2022 • DesignOps Summit 2022
Gold
Sam Proulx
Mobile Accessibility: Why Moving Accessibility Beyond the Desktop is Critical in a Mobile-first World
2022 • DesignOps Summit 2022
Gold
Changying (Z) Zheng
Navigating Innovation with Integrity
2024 • DesignOps 2024
Gold
Alexis Lucio
Scaling Accessibility Through Design Systems
2022 • Design at Scale 2022
Gold
Terry Buckman
Wargaming (An Introduction) (Videoconference)
2023 • Enterprise Community
James Rampton
The Basics of Automotive UX & Why Phones Are a Part of That Future
2024 • Rosenfeld Community
Sam Proulx
To Boldly Go: The New Frontiers of Accessibility
2022 • Advancing Research 2022
Gold
Dr. Jamika D. Burge
The Future of Research: Bridging the Gaps (Videoconference)
2021 • Advancing Research Community
Angy Peterson
More Than Technology: Personalized Public Sector Experiences
2021 • Civic Design 2021
Gold
Tatyana Mamut
Opening Keynote: Breaking Conway's Law--or How to Work Differently and Not Ship Your Org Chart
2019 • Enterprise Experience 2019
Gold
Rachel Posman
A Closer Look at Team Ops and Product Ops (Two Sides of the DesignOps Coin) (Videoconference)
2020 • DesignOps Community

More Videos

Jennifer Kanyamibwa

"The blueprint is really within all of us — all the things that have brought us to this moment should come to our teams."

Jennifer Kanyamibwa

Creating the Blueprint: Growing and Building Design Teams

November 8, 2018

Brigette Metzler

"Maintaining a repo often requires 100% manual participation from researchers and that can be hard to enforce and monitor."

Brigette Metzler Dana Chrisfield

Research Repositories: A global project by the ResearchOps Community (Videoconference)

August 27, 2020

Carl Turner

"Project delays are frequently due to organizational and cultural issues rather than actions of the project team."

Carl Turner

You Can Do This: Understand and Solve Organizational Problems to Jumpstart a Dead Project

March 28, 2023

John Mortimer

"Trust, facilitation, change, and complexity—if you wrap your mind around those, you’ll get reasonably far."

John Mortimer Milan Guenther Lucy Ellis Patrick Quattlebaum

Panel Discussion

December 3, 2024

Dante Guintu

"An engaged designer is a retained designer."

Dante Guintu

How to Crush the Talent Crunch

September 8, 2022

Richard Buchanan

"Sustainability is dead because we don’t know what to sustain; we need to create flourishing communities instead."

Richard Buchanan

Creativity and Principles in the Flourishing Enterprise

June 15, 2018

Dan Willis

"Every speaker before me had these pristine backgrounds. I’m a slob and feeling really self-conscious about it."

Dan Willis

Theme 3: Intro

January 8, 2024

Dan Ward

"We do experiments to learn, and if we learn something, then it’s a successful experiment."

Dan Ward

Failure Friday #1 with Dan Ward

February 7, 2025

Chris Geison

"Researchers are positioned at the nexus of insight and action."

Chris Geison

Theme Two Intro

March 28, 2023