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: New Postures for AI-Mediated Experiences (2nd of 3 seminars)
This video is featured in the AI and UX playlist and 1 more.
Summary
How do you get your head around all the different machine-intelligent experiences available to you as a designer? What are the new design patterns, and which old ones fall away? How do you name and organize those experiences? And how do you develop an intuition for how and when to use each interaction paradigm? Watch Josh Clark and Veronika Kindred, authors of our forthcoming book Sentient Design, explore the emerging diversity of AI-mediated experiences. Just as the natural world demonstrates intelligence in many forms, the same is true for machine intelligence. New “species” of interfaces roam our screens, the manner of each tailored to purpose and environment—copilots, agents, chatbots, assistants, tools, adaptive interfaces, and many more. Sentient Design offers a framework for exploring and organizing these new experience patterns, or “postures”—the way each kind of experience positions itself in relation to the user. More than just distinct functionality, each posture has its own interaction style, manner of communication, and expectations that it sets. Josh and Veronika share over a dozen of these postures, from familiar options like dedicated tools to more exotic patterns including sculptors, bespoke UI, non-player characters, and data whisperers. Get a map for exploring these postures to expand both your perspective and your toolkit as a designer.
Key Insights
-
•
Sentient Design reframes AI as a design material that enables adaptive, context-aware experiences rather than just a tool for output generation.
-
•
The Sentient Triangle categorizes AI experiences by grounded accuracy, interoperability, and radical adaptivity to better understand their trade-offs.
-
•
Four key interface postures—tools, sculptors, assistants, and agents—describe how AI interfaces relate to users, from simple inputs/outputs to autonomous task management.
-
•
Traditional deterministic tools like Shazam remain powerful but represent early-stage AI experiences compared to more interactive and adaptive forms.
-
•
Inline tools integrate AI assistance seamlessly within user workflows, offering continuous and ambient support without breaking context.
-
•
Sculptor interfaces enable iterative collaborative content creation, exemplified by in-painting in image and audio editing.
-
•
Chat-based characters and personas excel in creative, exploratory scenarios where factual accuracy is less critical than engagement.
-
•
Agents increasingly perform delegated tasks autonomously but currently face challenges with brittle, slow, and complex multi-step workflows.
-
•
Bespoke UIs dynamically generate or rearrange interface components in real-time tailored to user intent, enhancing flexibility and personalization.
-
•
Designers must embrace AI’s inherent weirdness and unpredictability as an asset, balancing risk and opportunity to create new interaction paradigms.
Notable Quotes
"Sentient design is about intelligent interfaces that are aware of context and intent so they can be radically adaptive to user needs in the moment."
"We think of AI not just as a maker of stuff but as an enabler of experiences."
"These intelligent interfaces are collaborative, proactive partners on the user’s journey."
"Traditional software is grounded—accurate and reliable—but lacks radical adaptivity."
"In-painting allows precise, targeted edits that don’t disturb the rest of the content."
"Characters live at the extreme of radically adaptive AI—they react in the moment and follow the user’s lead."
"Assistance interfaces combine open-ended dialogue with the ability to do tasks on your behalf."
"Agents set goals, plan steps, execute them, and decide when they’re done, often without user attention."
"Bespoke UI can generate interfaces on the fly based on immediate need or intent."
"Embracing AI’s weirdness can turn unpredictable outputs into experience assets rather than liabilities."
Or choose a question:
More Videos
"As manual tasks get automated, individuals can focus on higher-value tasks and training machine learning systems."
Lavy Kumar Kat Temple Shan Sebastian Tara Jensen Jenn ChouFuture of Work
June 9, 2021
"It’s really been helpful that research supports design not just in discovery but also in validating that what we build meets customer expectations."
Andreas Huebner Amy Takata Craig BrookesWhat Is It Like To Be Part of The UX Team at Compass?
March 11, 2021
"Cluster analysis is very useful if you want to avoid a one-size-fits-all approach to product or service design."
Ricardo MartinsUnlocking the power of advanced quantitative methods
March 12, 2025
"Our mission is to empower everybody to learn; not the few learning on behalf of the many."
Monty HammontreeThe Future of UX Research
December 3, 2020
"The design ops team helped designers print in BBA’s complicated systems, something they had to do alone after we lost the ops team."
Benjamin RealShowing the Value of DesignOps by Not Having a DesignOps Team
October 21, 2020
"Every operation is going to have whirlwinds and fires all the time; strategy doesn't end that."
Kate TowseyAsk Me Anything (AMA) with Kate Towsey
April 2, 2025
"Both tribes really believe in doing awesome for customers, that’s our common ground."
Steve Portigal Chris Chapo Kelly Goto Christian RohrerDiscussion
May 13, 2015
"Consistency reduces cognitive load not just for screen reader users but for people with ADHD and other cognitive challenges."
Sam ProulxOnline Shopping: Designing an Accessible Experience
March 28, 2023
"Including people with disabilities in prototype reviews can be different based on the assistive technology they use and their needs."
Sam ProulxPrototype Reviews, People With Disabilities, and You
October 1, 2021
