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
Ana Maria Montero Barrantes
The Authentic UX Talent Show
2024 • Enterprise Experience 2020
Gold
Ash Brown
Silver Linings: What DesignOps Learned in the Shift to WFH
2020 • DesignOps Summit 2020
Gold
Renee Reid
Becoming a ResearchH.E.R (Highly Enterprise Ready)
2019 • Enterprise Experience 2019
Gold
Ellen Chisa
The Values of Design
2023 • Design in Product 2023
Gold
Jodi Forlizzi
Design and AI innovation
2024 • Designing with AI 2024
Gold
Uday Gajendar
Leading through the long tail of trauma
2022 • Advancing Research Community
Denise Jacobs
Interactive Keynote: Social Change by Design
2024 • Enterprise Experience 2020
Gold
Bria Alexander
Opening Remarks
2022 • Civic Design 2022
Gold
Sean Dolan
A Practical Look at Creating More Usable Enterprise Customer Journeys
2019 • Enterprise Community
Marc Fonteijn
Increase your confidence, influence, and impact (through a Professional Community)
2024 • Advancing Service Design 2024
Gold
Megan Nipe
Human-Centered Design for Engagement: Maturing from Newsletterville to Personalized, One-to-One Messaging
2021 • Civic Design 2021
Gold
Prabhas Pokharel
Order and Chaos: New Ways of Collaborating on Synthesis and Storytelling
2022 • Advancing Research 2022
Gold
Kyria Stephens
Power to Heal: Civic Design in the Aftermath of Tragedy
2022 • Civic Design 2022
Gold
Christian Crumlish
The Pygmalion Effect: In Which a Vibe Coding Experiment Becomes a Million Lines…
2025 • Rosenfeld Community
Mark Templeton
Creating a Legacy: the ultimate experience
2017 • Enterprise Experience 2017
Gold
Briana Thomas
The Quiet Force: Uncovering Hidden Leadership in High-Impact Design Teams
2024 • DesignOps Summit 2024
Gold

More Videos

Joanna Vodopivec

"Bringing stakeholders into the kitchen early helped us learn even before sessions started and adjust designs accordingly."

Joanna Vodopivec Prabhas Pokharel

One Research Team for All - Influence Without Authority

March 9, 2022

Louis Rosenfeld

"The government is massive, so depending on the agency or program the context shifts dramatically."

Louis Rosenfeld Lashanda Hodge Senongo Akpem Chris Hodowanec

Becoming a Civic Designer: Making the Move from Private to Public Sector

November 17, 2022

Bria Alexander

"No need to take notes — session notes, sketch notes, resources, videos and decks will be shared after presentations."

Bria Alexander

Day 3 Welcome

September 25, 2024

Uday Gajendar

"Melissa Burnett is a creator of order out of chaos, leader of leaders."

Uday Gajendar Louis Rosenfeld

Day 2 Welcome

June 5, 2024

Sam Proulx

"More ways to contact support—chat, email, phone—are essential because different disabilities require different options."

Sam Proulx

Online Shopping: Designing an Accessible Experience

June 7, 2023

Russ Unger

"Unpaid design exercises are unfair because they don’t take into account people's real-life constraints."

Russ Unger

Onboarding: The Ecosystem, not the Afterthought

November 7, 2017

Catherine Dubut

"The store mobile device is the indispensable silent partner enabling store employees to balance task productivity and customer engagement."

Catherine Dubut

Bridging Physical and Digital Spaces: Approaches to Retail Service Design

March 18, 2021

Josh Clark

"Traditional software is grounded—accurate and reliable—but lacks radical adaptivity."

Josh Clark Veronika Kindred

Sentient Design: New Postures for AI-Mediated Experiences (2nd of 3 seminars)

January 29, 2025

Dantley Davis

"There were things I controlled and things I didn’t, and I needed to plan for both."

Dantley Davis

Leadership & Diversity—A Fireside Chat with Dantley Davis

September 17, 2020