Interactive prototypes and research demos exploring how people think, plan, and build capability with AI. These are experiments — some from published research, some new.
An adaptive AI interface that changes how it guides you based on your working style. Built around a cognitive science insight: people approach tasks with systematically different strategies, and interfaces should adapt to that — not force everyone into the same workflow.
Structure first
Follow curiosity
Move fast
Step by step
Play the game from our NeurIPS 2024 paper on AI planning. This 4x9 board variant (free placement, connect 4 to win) was used to study how AlphaZero and humans develop different planning strategies. The AI uses minimax search — can you beat it?
4 x 9 board · Place anywhere · From Lin et al., NeurIPS 2024
My research explores how humans and AI approach complex planning differently. During my PhD, I ran large-scale behavioral experiments with thousands of participants across 9 different planning games, identifying latent dimensions of how people build strategic skill over time.
This work informs everything I build — from agent training pipelines at Amazon to adaptive interfaces like Mode. The core question: how should AI tools adapt to the way people actually think?