From Catching Cheaters to Helping Students Become Better Programmers

Abstract

While AI has many productive uses, many students now use it to skip the thinking. One instinctive response from institutions and teachers is AI detection, but detection works poorly on code. This session introduces a different approach: instead of assessing just the finished code students submit, make the coding process itself visible, giving instructors and students something concrete to talk about. Details such as the history of successful and failed runs, paste events, and active coding time shift the instructor-student conversation from "Did you cheat?" to "How did you learn?" For example, code execution history can distinguish a student who debugged their way to a solution from one whose code simply worked on the first run. Furthermore, encouraging students to reflect on their own coding process builds reflective habits that outlast a single lab assignment. The session will close with how colleges in Nepal have already adopted free tools that support such practices in their programming labs and assignments.