Zhixuan
Zhang
Product Designer at IBM
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
Wed May 13 - 4:30 PM EDT/New York (See in local time)
Add to Calendar
05/13/2026 4:30 PM
05/13/2026 04:50 PM
America/New_York
#WTGC2026
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
#WTGC2026
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
https://www.womentech.net/ringcentral
https://www.womentech.net/ringcentral
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
"Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty"
Don’t miss out and join visionaries, innovators, and thought leaders from all over the world at the Women in Tech Global Conference.
Vote by Sharing
Unite 100 000 Women in Tech to Drive Change with Purpose and Impact.
Do you want to see this session? Help increase the sharing count and the session visibility. Sessions with +10 votes will be available to career ticket holders.
Please note that it might take some time until your share & vote is reflected.
Session: Designing Trustworthy AI Products: UX Patterns to Manage Hallucinations, Bias, and Uncertainty
As AI features move from demos into real products, teams face a recurring challenge: users must make high-stakes decisions with systems that can be uncertain, biased, or wrong. In this talk, I’ll share practical UX patterns for building trustworthy AI experiences—especially for enterprise tools—covering how to communicate uncertainty, reduce over-reliance, design human oversight, and create audit-ready interactions without overwhelming users.Drawing from my experience designing complex B2B products and AI-powered experiences, I’ll walk through a repeatable framework: (1) define failure modes (hallucinations, bias, data gaps), (2) map risk to UX affordances, (3) add “verification loops” and user control, and (4) instrument feedback to continuously improve model + UX. Attendees will leave with concrete design patterns, a lightweight checklist for design reviews, and examples they can adapt to their own AI products.
Key Takeaways
- A simple taxonomy of AI failure modes (hallucinations, bias, data gaps) and how they show up in UX.
- UX patterns to communicate uncertainty and reduce over-trust without harming usability.
- Human-in-the-loop design tactics: verification loops, fallback flows, and user control.
- A lightweight “Trustworthy AI UX” checklist you can use in design reviews.
- How to instrument feedback so UX + model quality improve together over time.
Bio
Zhixuan Zhang is a UX/Product Designer working on IBM enterprise FinOps and cloud cost management products. She designs complex data and decision workflows that help teams understand, govern, and optimize cloud usage at scale. Maggie also explores AI-powered product experiences, focusing on trustworthy UX patterns, human-in-the-loop design, and responsible deployment in real-world settings.