More output does not mean more taste.
When generation is cheap, the scarce work is comparison: seeing dimensions, tradeoffs, and evidence across options.
Design judgment + human-centered AI
I build and study interfaces that help people think, design, and build with AI: exploring possibilities, seeing tradeoffs, and developing taste over time.
Cognitive Science Ph.D. student at UC San Diego Advised by Prof. Steven P. Dow in ProtoLab.
Thesis thread
My main thesis thread is Scaffolding for Taste: how AI can help people develop taste, discernment, and evaluative judgment in a world of generative abundance. When AI can generate ten options in a minute, the hard part is learning what differs, what matters, and why one direction is worth pursuing.
Good interfaces should make differences, tradeoffs, consequences, and evidence easier to see, so people can reason about what to try next.
I like applying this to urban design, architecture, interior and product design, fashion, robotics, education, and creative media: places where ideas move from vibes -> variables -> value.
Why now
AI makes it easy to produce variants; my question is how people learn to choose well.
When generation is cheap, the scarce work is comparison: seeing dimensions, tradeoffs, and evidence across options.
Designers, researchers, PMs, and engineers all shape early artifacts now. Interfaces need to support shared reasoning before decisions harden.
Fast cycles are useful only if teams keep room for critique, incubation, and explaining why a direction is better.
Research focus
A small interactive sketch of the loops I keep studying: generating directions, reading evidence, and grounding assistance in the situation where work happens.
Motion pattern inspired by Stripe's homepage craft and Katie Dill's design-quality framing. Stripe design team and Katie Dill at Stripe Sessions.
Showing the Design motion sketch.
I study interfaces that scaffold creative judgment: helping people explore and refine generative possibilities without losing the dimensions, constraints, and values that make a design worth pursuing.
I care about what changes after a tool enters the loop: diversity, verification cost, calibration, appropriate reliance, and whether traces help people revise the artifact after deployment.
This is ongoing work around systems that support everyday tasks through in-situ intelligence, spatial interaction, and real-world use, where the right assistance depends on the person, task, tool, and physical or social context.
Selected publications
Updates
Pinned Met the great Don Norman and even got a selfie + a “To Sirui” signed “Yellow Book”!
Our CHI 2026 workshop position paper, What Happened and Why? Trace-Guided Micro-Episodes with Elicited User Explanations for Product Iteration, was accepted to Herding CATs - easily one of the best workshop names ever! The whole ProtoLab is going to Spain! Might be a UCSD party!
HotSpot got selected as a CVPR 25 Highlight!
Research opportunities
I like working with undergraduate and master's students who can stay curious about a messy question long enough to make it sharper.
You do not need to arrive as an expert. It helps if you enjoy reading closely, making prototypes, testing claims, and explaining what changed your mind.
Connect