Harmanpreet Kaur 

Date: December 4th, 2025

Time: 16:00 (CET)

Title:  Cognitive Scaffolding in the Age of AI: Design Principles for Appropriate Reliance

Abstract: Human-AI partnerships are increasingly commonplace, yet often ineffective as people over- or under-rely on AI for support, resulting in harmful outcomes such as propagation of biases, missed edge cases, and homogenization of ideas and skillsets. My work follows the belief that for human-AI partnerships to be effective and reliable, AI should be a tool for thought—a cognitive scaffold that helps us appropriately and effectively reflect on the information we need—rather than displace human cognition. In this talk, I will first motivate this belief by sharing work that demonstrates the cognitive underpinnings of how people differently use and trust AI. Then, through use-cases spanning explainable AI, data science workflows, and scholarly research, I will present design principles for AI as an effective cognitive scaffold. For novices learning to work with AI systems, this means designing interfaces grounded in pedagogical principles—using narrative structures and progressive disclosure to build genuine understanding rather than superficial familiarity. For domain experts, effective scaffolding looks different—preserving agency and providing granular mechanisms for provenance to calibrate trust. I will conclude by examining a persistent challenge: even well-designed scaffolds face systemic barriers of time pressure and competing cognitive demands in real-world contexts.

About the Presenter

Harman Kaur is an Assistant Professor in the Department of Computer Science and Engineering at the University of Minnesota. Her research areas are human-centered AI, explainability and interpretability, and hybrid intelligence systems. She studies these areas in a variety of domains (e.g., exploratory data analysis, workplace wellbeing and productivity, knowledge search and sensemaking), applying methods towards both critically evaluating existing systems on meeting their intended goals, and designing and building new human-centered systems. She has published several papers at top-tier human-computer interaction venues, such as CHI, CSCW, FAccT, and IUI. Harman received her PhD in both Computer Science and Information from the University of Michigan, and a BS in Computer Science from the University of Minnesota. 

Homepage: https://cse.umn.edu/cs/harmanpreet-kaur