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
-
•
Prioritize clear use case definitions for AI tools.
-
•
High quality training data is crucial for chatbot success.
-
•
Initial user engagement should set clear expectations with specific messaging.
-
•
Design for effective loading experiences to accommodate variable speeds.
-
•
Support user navigation with intuitive scrolling and output summaries.
-
•
Error states in AI require guiding users to reformulate prompts, rather than just displaying errors.
-
•
Transparency in AI capabilities and limitations helps build user trust.
-
•
Accessibility considerations should be integrated throughout the design process.
-
•
Feedback mechanisms are essential for continuous improvement of chatbot performance.
-
•
Iterative design allows for refining user interactions and measuring engagement.
Notable Quotes
"Being clear on the primary use case is even more important now."
"If you have any doubts about the quality of the training data, do not proceed."
"The mental models are still early in forming for these tools."
"Loading indicators help users understand progress while waiting for output."
"Error states become about helping users write prompts effectively."
"Transparency is crucial, especially in regulated spaces like FinTech."
"Accessibility should be part of the testing plan from the beginning to the end."
"Our bot showed that it could decrease the friction for users to learn about MARTA."
"The chatbot had a much narrower scope to maintain accuracy and relevance."
"Being cautious about managing user expectations is vital to maintaining trust."
More Videos
"Designers are mutants, bridging gaps between disciplines."
John MaedaMaking Sense of Enterprise UX
June 9, 2016
"The way to think about it is in a simple way: how do we support this thinking style?"
Indi YoungThinking styles: Mend hidden cracks in your market
January 8, 2025
"Developing deep customer empathy is fundamental to understanding who is using a product and why."
Chris ChapoData Science and Design: A Tale of Two Tribes
May 13, 2015
"We're mining our practices to track impact over time."
Elizabeth ChurchillExploring Cadence: You, Your Team, and Your Enterprise
June 8, 2017
"We truly believe that when all of us win together, we can achieve so much more."
Rusha SopariwalaRemote, Together: Craft and Collaboration Across Disciplines, Borders, Time Zones, and a Design Org of 170+
June 9, 2022
"I believe having an ethical framework can help limit the harm typically done in design."
George AyeThat Quiet Little Voice: When Design and Ethics Collide
November 16, 2022
"I care about my team's resilience, and I'm here to share some strategies and tactics that work well for us."
Ariba JahanTeam Resiliency Through a Pandemic
January 8, 2024
"Design thinking is a set of behaviors, not just a toolbox of methods."
Julie Gitlin Esther RaiceDesign as an Agent of Digital Transformation at JPMC
June 9, 2021
"As designers, we can decide what data is required for our applications to work."
Matteo GrattonCan Data and Ethics Live Together?
October 1, 2021
