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.

Don't botch the bot: Designing interactions for AI

Gold
Tuesday, June 4, 2024 • Designing with AI 2024
Share the love for this talk
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

  • Defining a clear and specific primary use case is crucial before starting any generative AI chatbot project.

  • High-quality, thoroughly reviewed training data is foundational to delivering accurate and useful AI outputs.

  • Initial state messaging must clearly frame what the chatbot can and cannot help with to reduce irrelevant or off-topic queries.

  • Loading indicators for AI text responses should be subtle, with progress reflected by text appearing rather than distracting animations.

  • Supporting efficient scrolling and prompt review is vital since users frequently check and refine their inputs against often long answers.

  • Error states in AI chatbots shift from traditional fixed errors to helping users write better prompts to get more relevant results.

  • Transparency about accuracy, AI limitations, and source citations builds user trust, especially in regulated domains like FinTech.

  • Providing users with prompt engineering guidance via documentation significantly improves the quality of chatbot interactions.

  • Accessibility considerations, like keyboard navigation and screen reader compatibility, must be integrated from the start, especially given the large text outputs.

  • Chatbots can reduce customer support friction and encourage users to ask questions they might not have otherwise, enhancing user engagement with the product.

Notable Quotes

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

"You want to assist people in framing the interaction and setting their expectations correctly so they know how to be successful."

"The biggest difference with error states in AI bots is helping people write prompts effectively, not just recovering from simple failures."

"Loading text itself is a loading indicator; the letters appearing show progress better than jumpy animations."

"People often forget what they wrote and then want to check their prompt again before refining it."

"Every output should have at least three source links, almost like citations in a research paper."

"We had to be very careful about accuracy because we're in FinTech and compliance is critical."

"People started asking questions to the bot that they wouldn’t have taken the time to email about."

"It’s really important to be clear and transparent about what the tool is good at and what it’s not good at."

"Accessibility testing included making sure everyone could navigate it using a keyboard alone."

Ask the Rosenbot
Ryan Matthew
Bridging Design and Code: AI-Powered Design System Integration
2025 • Rosenfeld Community
Hugh Dubberly
Problems with Problems: Reconsidering the Frame of Designing as Problem-Solving
2019 • Enterprise Community
Rachael Dietkus, LCSW
Trauma-Responsive Design: Reimagining the Future of Design Now
2021 • Civic Design 2021
Gold
Brendan Jarvis
It was the Best of Times. It was the Worst of Times.
2024 • DesignOps Summit 2024
Gold
Sean Baker
Weaving Knowledge Management into the Fabric of Our Design Practice
2025 • DesignOps Summit 2025
Gold
Melissa Eggleston
Practical People Skills for Building Trust on Teams and with Partners
2021 • Civic Design 2021
Gold
Aurobinda Pradhan
Introduction to Collaborative DesignOps using Cubyts
2022 • DesignOps Summit 2022
Gold
Sha Hwang
The First Fifty Years of Civic Design
2022 • Civic Design 2022
Gold
Tala Tayebi
Voice and influence in an age of noise
2026 • Advancing Research 2026
Gold
Jaskiran Kang
Why Community is Key to Professionalizing Design
2022 • Civic Design Community
Doug Powell
DesignOps and the Next Frontier: Leading Through Unpredictable Change
2025 • DesignOps Summit 2025
Gold
Emilia Åström
Unlock Your Team’s Intelligence with Collaboration Design
2022 • Design at Scale 2022
Gold
George Zhang
UX Research Excellence Framework
2021 • Advancing Research 2021
Gold
Nalini P. Kotamraju
An Organizational Story: Salesforce Lightning Design System
2016 • Enterprise UX 2016
Gold
David Conrad
The Feeling of Data
2023 • Enterprise Community
Taylor Klassman
The Evolution of UX Research Platforms
2026 • Advancing Research 2026
Gold

More Videos

Kate Towsey

"Building ecosystems of interconnected tools that work seamlessly is crucial for modern, fast-moving organizations."

Kate Towsey Basel Fakhoury Oren Friedman Graham Gardner

Participant Recruitment and Management Tools

March 12, 2026

Jennifer Kong

"Users were initially excited but six months later expressed frustration and uncertainty about the tool’s usefulness."

Jennifer Kong

Journeying toward AI-assisted documentation in healthcare

June 5, 2024

Kevin M. Hoffman

"Project management is the ecosystem connecting everyone to deliver the best branded dog communication technology."

Kevin M. Hoffman

Theme 2: Enterprise Team Journey

June 3, 2019

Amy Marquez

"There’s been a huge convergence because everybody’s got a mobile device now and expects a certain kind of experience."

Amy Marquez

INVEST: Discussion

June 15, 2018

Gretchen Anderson

"That’s the kind of feature that never would have made it to the top of anyone’s backlog without design."

Gretchen Anderson

Scaling the Human Center

June 8, 2017

April Reagan

"Foresight is a team sport—the more perspectives you have, the better your future scenarios become."

April Reagan

Look, Think, Act: The Futures-Smart Design Organization

October 1, 2021

Dante Guintu

"My superpower is to connect the dots between people, places, ideas, and opportunities."

Dante Guintu

How to Crush the Talent Crunch

September 8, 2022

Jaime Creixems

"Respect your design system rules to ensure consistent experiences across your product and teams."

Jaime Creixems

Best Practices when Creating and Maintaining a Design System

June 7, 2023

Billy Carlson

"Collaboration is key; wireframes shouldn’t be thrown over the fence from UX to design without discussion."

Billy Carlson

Principles of Team Wireframing

October 2, 2023