Publications
Peer-reviewed work
We publish what we learn building AlgoArena. These papers cover teaching people to build software with AI, scoring work when an AI wrote the code, and running live coding quizzes in a real classroom. Every paper is free to read here.
SIGCSE Virtual 2026
Teaching Vibecoding: An Open Curriculum for AI-Assisted Software Development
Andy Luu, Eli Young, Michael Wehar
2nd ACM Virtual Global Computing Education Conference, November 12-15, 2026
An openly licensed course for building software by stating intent to an AI instead of writing the code by hand. Fourteen core chapters covering specification, supervising a coding agent, and verifying output that looks right but may not be.
SIGCSE Virtual 2026
A Competency Framework for Assessing AI-Assisted Programming Work
Eli Young, Andy Luu, Michael Wehar
2nd ACM Virtual Global Computing Education Conference, November 12-15, 2026
When an AI writes the code, a passing test suite no longer shows what a student can do. This paper scores the work along five competencies instead, covering how a task gets specified, how the agent is directed, and whether bad output gets caught.
CCSC Southeastern 2026
Supporting Active Learning in Computer Science with Live, Gamified Classroom Quizzes
Andy Luu, Eli Young, Michael Wehar
40th Annual CCSC Southeastern Regional Conference, East Tennessee State University, Johnson City, TN, October 23-24, 2026
A live quiz format for CS lectures, mixing short recall questions with full coding problems judged against real test cases. Reports a pilot in an undergraduate algorithms course and sixteen more quizzes run by instructors with no connection to the project.
The curriculum
The Teaching Vibecoding paper describes a course you can read and use right now. It is free for classroom and personal use under CC BY-NC 4.0.
Open the textbook