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
Alfred Kahn
A Seat at the Table: Making Your Team a Strategic Partner
2023 • Design in Product 2023
Gold
Louis Rosenfeld
The Bigger Picture: A Panel Discussion
2019 • DesignOps Summit 2019
Gold
Ana Ferreira
Designing Distributed: Leading Doist’s Fully Remote Design Team in Six Countries
2024 • DesignOps Summit 2020
Gold
Jeff Gothelf
Innovation Studios: the Engines of Enterprise Experimentation
2015 • Enterprise UX 2015
Gold
Iram Shah
Closing Keynote: The View from the Top
2019 • Enterprise Experience 2019
Gold
Jessamyn Edwards
Surviving Your UX Career in Enterprise Design (Videoconference)
2021 • Enterprise Community
Sam Proulx
Understanding Screen Readers on Mobile: How And Why to Learn from Native Users
2023 • Advancing Research 2023
Gold
Miles Orkin
Creativity and Culture
2018 • DesignOps Summit 2018
Gold
Vicky Teinaki
Short Take #3: UX/Product Lessons from Your Industry Peers
2022 • Design in Product 2022
Gold
Jazz Improvisation as a Model for Team Collaboration
2017 • DesignOps Summit 2017
Gold
Tricia Wang
Spatial Collapse: Designing for Emergent Culture
2024 • Enterprise Experience 2020
Gold
Ben Davies
Expert Panel: The Principles of Research Repository Design
2022 • Advancing Research 2022
Gold
Michal Anne Rogondino
Saving Outer Space: The First UX Design System for Our Nation’s Satellites
2024 • Enterprise Experience 2020
Gold
Verónica Urzúa
The B-side of the Research Impact
2021 • Advancing Research 2021
Gold
Marisa Bernstein
It Takes GRIT: Lessons from the Small, but Mighty World of Civic Usability Testing
2021 • Civic Design 2021
Gold
Rittika Basu
Age and Interfaces: Equipping Older Adults with Technological Tools (Videoconference)
2023 • Advancing Research Community

More Videos

Alex Hurworth

"Policies must evolve to reflect the urgency of our situation."

Alex Hurworth Bonnie John Fahd Arshad Antoine Marin

Designing a Contact Tracing App for Universal Access

October 23, 2020

Laine Riley Prokay

"We wanted to actively promote the Design Ops discipline to more people, especially those not familiar with our craft."

Laine Riley Prokay Lisa Gordon

Carving a Path for Early Career DesignOps Practitioners

September 9, 2022

Eniola Oluwole

"Everyone wanted to know what was the official pattern and who was accountable for it."

Eniola Oluwole

Lessons From the DesignOps Journey of the World's Largest Travel Site

October 24, 2019

Nathan Shedroff

"Rather than aiming for the chief strategy officer directly, build relationships with junior strategists who are more accessible."

Nathan Shedroff

Double Your Mileage: Use Your Research Strategically

March 31, 2020

Sam Proulx

"Apple premiered mobile accessibility in a very exciting way with the iPhone 3GS and VoiceOver announcement at WWDC."

Sam Proulx

Mobile Accessibility: Why Moving Accessibility Beyond the Desktop is Critical in a Mobile-first World

November 17, 2022

Feleesha Sterling

"If your design team cannot act quickly on findings, rapid research is not the method for you."

Feleesha Sterling

Building a Rapid Research Program (Videoconference)

May 18, 2023

Neil Barrie

"Triple win cultural roles speak to what a company commits to, what users need, and wider cultural tensions."

Neil Barrie

Widening the Aperture: The Case for Taking a Broader Lens to the Dialogue between Products and Culture

March 25, 2024

John Devanney

"For many years, folks came to us with questions beyond design — about career paths, tools, skills, and intake management."

John Devanney

The Design Management Office

November 6, 2017

Katy Mogal

"You need to understand stakeholders’ fears, motivations, and incentives to change hearts and minds."

Katy Mogal

But Do Your Insights Scale?

March 12, 2021