2026 ASEE Annual Conference & Exposition

Programmatic assignments compose large portions of a student's responsibility in many Computer Science (CS) curricula, aiming to cement and assess Code-to-Concept (C2C) mapping. However, in the era of Generative AI (GenAI), CS students may complete assignments without mastering any C2C proficiency, leaving valuable knowledge units behind that will be demanded in subsequent, more complex work. In response, we propose a new class of GenAI application for Assessment Assistance (GenAI-AA) and feature one implementation through an app called PostCommit: a novel tool for instructors to conduct individualized technical interview style code questions asking students to explain in plain-language portions of their submitted work. By providing a second round of assessment for C2C proficiency in a proctored setting (accomplished through the PostCommit interface), students gain a new motivation for deep C2C understanding, regardless of the sources used to complete their programmatic assignments, and supplemental practice explaining their own ideation and understanding of submitted code (a skill that is often omitted from CS curricula). Likewise, instructors gain a new tool for assessing their class' C2C mastery and providing individualized feedback on how students can improve their explanations in interview or conference settings. This work details the PostCommit workflow from student code submission via GitHub Classroom to quiz question curation and automated feedback. We also present pilot data from 6 CS courses spanning grade levels of the CS curriculum that incorporated PostCommit across an academic semester, including comparisons of student PostCommit quiz scores and performance on other course elements (i.e., assignments and exams), rates of instructor changes to automated feedback, and overall student perception of PostCommit effectiveness. Data suggest large gaps in student C2C mastery when comparing explanatory vs. programmatic correctness, with PostCommit scores correlating with exam, but not assignment performance. These results highlight a new need for motivating understanding, rather than simply completion, of assignments: a priority that GenAI-AA tools may be used to meet in the adjacent future.