← back
The UX of AI: Making AI-Powered Apps Your Users Don't Hate - Kathryn Grayson Nanz, Progress Software
Takeaway
Bridge users' existing mental models to AI capabilities through guidance and carefully adapted interaction patterns.
Summary
- AI features often assume technical knowledge that ordinary users lack, and repeated confusing experiences discourage future use.
- Early Macintosh interfaces illustrate how familiar metaphors and gradual introduction of technical concepts can build user literacy.
- AI chat can reuse messaging conventions but needs additional controls for sources, stopping generation, and tool integrations.
- Generated interfaces reproduce established patterns; emerging AI interactions still require deliberate human UX design.
ai-uxinteraction-designuser-adoption
Original description
As a developer, AI is fun, exciting, and full of potential – but users don't always feel the same way about it. From a UX perspective, AI comes with a whole new set of considerations around user trust, privacy, and security. From a UI perspective, AI brings new interaction patterns, new icons, new visual cues, and so much more! If we want people to get the most from what we build, we have to teach our users how to use AI. Let's look at ways to introduce new capabilities in our apps and guide our users through new patterns and processes – ideally without making them throw their phone out a window Speakers: Kathryn Grayson Nanz (Progress Software): Kathryn Grayson Nanz is the Senior Design and Developer Advocate at Progress Software; her work focuses on React, UI design and design systems, accessibility, and creating software that centers the human experience. X/Twitter: https://bsky.app/profile/kgrayson.com LinkedIn: / kathryngrayson GitHub: https://github.com/kathryngraysonnanz