Despite Generative AI's potential to support complex, open-ended creative and analytical tasks, such as designing multi-objective mechanical parts or analyzing data, professionals often struggle to integrate these systems effectively into their workflows. Key challenges include misalignment between outputs and intentions, uncertainty about how to guide the system, and reduced cognitive engagement when tasks are overly delegated to automation, often resulting in insufficient problem exploration and limited ability to evaluate generated outcomes. I argue that to better leverage GenAI's capabilities for complex, open-ended problem-solving, we need advances in interaction and system design that deliberately support people's critical thinking and reflection, alongside continued improvements to the underlying models

My research addresses this challenge by rethinking human-AI interaction for cognitively demanding professional workflows. I study how people use GenAI in domains such as mechanical design, slide presentation authoring, and data analysis, and develop interaction techniques that scaffold reflection, sharpen problem formulation, and support deliberate cognitive engagement where human judgment is critical. Building on cognitive and learning science principles, such as metacognition and Socratic dialogue, and design theory concepts, such as reflection-in-action, this thesis investigates how cognitively supportive interactions can improve human-AI co-creation.

In the first research thread, I examine how mechanical and architectural designers engage with novel AI-based design tools in multi-objective manufacturing tasks. From these studies, I identify support strategies, such as reflective questioning and thought externalization, that improve designers' cognitive engagement and outcomes. I further demonstrate how voice-based support agents can facilitate cognitive support in GenAI workflows. Additionally, I develop Novel AI prototyping methods to more effectively evaluate real-time support agent behavior. In a second thread, I present Intent Tagging, a chat-alternative input technique that supports granular and reflective control of large language models during slide presentation authoring through lightweight, structured, and adaptive graphical interface elements. Finally, through MindKicks, I introduce a modular plug-in architecture for augmenting existing AI-assisted workflows with proactive cognitive "sidekicks." Through a study with data analysts, I show how a MindKicks-based support system can complement chat-based coding agents, increase analytical engagement with AI outputs, and help analysts discover more data issues.

In sum, this thesis contributes interaction techniques, systems, prototyping methods, and empirical insights that advance human-AI interaction by enabling people to think more deeply, create more thoughtfully, and solve more complex problems with the help of AI.

353 pages

Thesis Committee:
Nikolas Martelaro(Co-Chair)
Kenneth Holstein (Co-Chair)
Aniket Kittur
Christopher McComb (Department of Mechanical Engineering, CMU)

Brad A. Myers, Head, Human-Computer Interaction Institute
Martial Hebert, Dean, School of Computer Science

Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu