Miroslav Suzara

Researcher and engineer building AI systems that amplify human capability.
AI should make people more capable over time, not just more productive in the moment. We're still figuring out how to build AI that actually teaches, strengthens judgment, and helps people grow. I build AI systems that model and support human behavior in learning and collaboration: a flight simulator where teachers practice on AI students, frameworks where humans and AI teammates work as peers. Then I study what actually happens, measuring whether people build confidence, ask better questions, and grow real skill. I'm currently finishing my PhD at Stanford in human-AI collaboration and looking for my next opportunity to do this work at scale.

TeacherSim

A teaching flight simulator where educators practice with AI students modeled on real learning patterns. Designed for deliberate practice: every session generates actionable feedback on pedagogical moves.

educational AI teacher training deliberate practice

ChatCollab

A multi-agent framework where human and AI teammates collaborate as peers inside Slack. Built to study how agent design shapes group dynamics, participation equity, and decision quality. Each configuration generates rich behavioral simulation data on how different team compositions communicate, coordinate, and make decisions.

human-AI interaction collaborative learning multi-agent systems behavioral simulation

Bruno

An AI facilitator for collaborative math problem-solving. Mediates group discussions, asks strategic questions, and tracks participation equity in real time.

collaborative learning facilitation equity

Spellburst

Node-based creative coding with LLMs, built to preserve human agency over the creative process while enabling rapid exploration at multiple levels of abstraction.

creative tools LLMs creative coding
Spellburst: A Node-Based Interface for Exploratory Creative Coding with Natural Language Prompts
Angert, T., Suzara, M., Han, J., Pondoc, C., et al.
UIST 2023
The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters' Exam Performances
Nie, A., Chandak, Y., Suzara, M., Malik, A., et al.
L@S 2025
PearProgram: A More Fruitful Approach to Pair Programming
Bigman, M., Roy, E., Garcia, J., Suzara, M., Wang, K., et al.
SIGCSE 2021
ChatCollab: Exploring Collaboration Between Humans and AI Agents in Software Teams
Klieger, B., Charitsis, C., Suzara, M., Wang, S., et al.
arXiv 2024
tap me to explore ✦
tap any section — I'll tell you more!