Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
Sentient Design, AI, and the Radically Adaptive Experience (1st of 3 seminars)
This video is featured in the AI and UX playlist and 2 more.
Summary
How do you use AI to do more than just “make stuff” and instead make new kinds of experiences? Machine intelligence is your new design material, and radically adaptive experiences are the result. Join Josh Clark and Veronika Kindred, authors of our forthcoming book Sentient Design, for a lively introduction to this emerging generation of intelligent interfaces. Sentient Design describes the form, framework, and philosophy for creating AI-mediated experiences that feel almost self-aware in their response to user needs. In these new experiences, the content, structure, interaction, medium, or posture—sometimes all at once—adapt on the fly to provide the right experience for the individual and the moment. These changes can be small and subtle, or big and dramatic. As you crank the “radical” dial, these experiences include: dashboards that assemble themselves into the best collection of UI elements and content; interactions and interfaces that are conceived on the spot by the user, the system, or both; and entire applications invented whole cloth for the moment. This is not ye olde website anymore. It’s weird and hairy and different from what’s come before. Josh and Veronika will share lots of examples of radically adaptive experiences in the wild, as well as strategies and techniques for bringing this approach to your own practice. You’ll also learn six fundamental shifts in perspectives that radically adaptive experiences impose: from personalized to individualized; from visual to multimodal; from reactive to proactive; from predefined to emergent; from persistent to ephemeral.
Key Insights
-
•
Sentient Design frames AI as a design material that can be woven into interfaces to create intelligent, adaptive experiences rather than just a tool or feature.
-
•
The Pinocchio design pattern enables turning low-fidelity ideas like sketches into working prototypes, demonstrating AI as a collaborator.
-
•
Radically adaptive experiences adapt content, structure, and interaction in real time based on user context and intent, going beyond static interfaces or simple chatbots.
-
•
Four broad experience postures exist in sentient design: tools (grounded), chat (peer-level dialogue), agents (autonomous goal-oriented), and copilots (continuous collaborators).
-
•
Intelligent interfaces can generate bespoke UIs on demand, as shown in Google Gemini’s birthday party planning example where AI builds the needed interface dynamically.
-
•
Integrating AI assistance directly into familiar working environments (like Figma or Google Docs) provides smoother collaboration than separate chat-based interfaces.
-
•
Machine intelligence excels at transforming and translating content across forms, mediums, and languages, liberating static content like PDFs into interactive formats.
-
•
AI outputs are probabilistic 'signals' rather than factual answers, requiring designers to treat AI-generated content as suggestions rather than absolute truths.
-
•
Designers now face a loss of full control over interaction paths due to AI’s adaptability, making defensive design critical to manage unpredictability and user expectations.
-
•
Ethical and environmental concerns around AI, including energy consumption and extractive data practices, must be acknowledged and factored into design decisions.
Notable Quotes
"AI is a design material, not just a tool or function you add to an experience."
"The Pinocchio pattern is about turning an idea, a concept, into a working reality with machine intelligence as a collaborator."
"Radically adaptive experiences bend to your current wants and needs, creating unique, unpredictable journeys."
"The interface becomes a radically adaptive surface—an intelligent canvas that reacts to your behavior and context."
"Typing prompts is not the UX of the future. Integration into the interactive context where you work is better."
"LLMs talk the talk but don’t understand the meaning. They’re master impersonators without true knowledge."
"AI delivers signals, not hard truths. They’re dream machines designed to imagine what could happen next."
"We can’t design for every possible outcome anymore. We have to anticipate fuzzy ranges of results and channel behavior accordingly."
"Machine intelligence can elevate experiences by easing frictions and amplifying human judgment and agency."
"The future should not be self-driving. It’s up to us, not the technology, to figure out the right way to use AI."
Or choose a question:
More Videos
"We’re all capable of creating and perpetuating toxic work relationships."
Darian DavisLessons from a Toxic Work Relationship
January 8, 2024
"A frustrated passenger at a delayed flight might just need acknowledgment, not dismissal."
Indi YoungThinking styles: Mend hidden cracks in your market
January 8, 2025
"Our curators have been working for months taking presentations from little ideas to something big that advances design ops as practice."
Louis Rosenfeld Bria AlexanderDay 1 Welcome
September 23, 2024
"Our products are powerful and complex, and customers use them end to end from concept to creation and monitoring."
Melissa Schmidt Adam MenterHow UX Research Hit It Big in Las Vegas
June 4, 2019
"Only one in 10 companies have quantifiable measurement for their design leaders."
Kristin Skinner Kamdyn Moore8 Types of Measures in Design Operations
April 16, 2020
"Sales and support teams are closer to ground truth than many might realize and are invaluable partners for researchers."
Dave HoraAdvice for Establishing Research
December 8, 2022
"Agents do a lot of jobs simultaneously with completely different mental contexts."
Sean Fitzell Sarah Han Kayla FarrellCraft of User Research: Building Out Jobs to be Done Maps
March 12, 2021
"Spreadsheets for profiles across an organization become really difficult to update."
Jason MesutShaping design, designers and teams
November 8, 2018
"Only 12% of employees strongly agree their organization does a great job onboarding new employees."
Dante GuintuHow to Crush the Talent Crunch
September 8, 2022
