Process-Oriented Homework with an Instructor-Designed AI-Bot: An Early Experience in a Data Structures and Algorithms Course

Abstract

Traditional assignments focused on correct outputs are increasingly challenged by students’ ability to generate code using AI with minimal conceptual effort. Process-oriented assignments that highlight reasoning, design choices, justifications, and reflections provide a valuable alternative. Despite rising interest in such tasks, almost all previous research comes from high-resource environments, and little is known about GenAI-mediated, process-oriented homework in low-resource settings. This paper reports an early experience with an instructor-designed AI-bot for process-oriented assessment that records students’ mock interviews in a sophomore-level Data Structures and Algorithms (DSA) course at a university in Africa. We found that this low-cost system was relatively simple to build and handled diverse accents satisfactorily. We close by raising questions about potential learning gains, design principles for AI-bots that support process-oriented homework, and how to set expectations for effective learning with instructor-designed AI-bots.