Learnersourcing, an educational approach that positions students as active contributors rather than passive consumers, offers a scalable approach to co-creating instructional resources while engaging students in authentic problem-solving. However, it faces a fundamental tension: effective “learning” requires scaffolding that minimizes extraneous cognitive load and focuses attention on reasoning, while effective “sourcing” requires structure, completeness, and standardization to ensure student-generated content can be reused. These competing goals create a tradeoff: students either learn but produce content that is difficult to reuse, or generate usable resources but receive limited learning benefit. We propose a new AI-assisted learnersourcing paradigm to address this tension. By assigning collaborative roles to both learners and AI, the approach enables students to focus on cognitively meaningful sub-tasks that foster “learning”, while large language models (LLMs) handle mechanical and procedural sub-tasks for “sourcing”. Guided by user-centered design principles, we implement this workflow in ExPeerience, a system that scaffolds students in co-creating contextualized worked-out examples for database programming. Within ExPeerience, the AI serves as a collaborator for ideation, a co-creator of artifacts, and an evaluator of students’ inputs. Our evaluation with 24 participants showed that structuring AI into distinct collaborative roles improves learning engagement while producing high-quality student-generated content. Compared to a baseline using the Gemini chatbot, ExPeerience users created SQL problems in more diverse and personally meaningful contexts. They actively evaluated, edited, and refined AI-generated components, and most authored their own SQL solutions, whereas baseline participants largely accepted AI outputs without modification and did not attempt to solve the problem. Overall, ExPeerience produced more contextualized, varied, and thoughtfully constructed worked-out examples. These findings demonstrate the potential of AI-assisted learnersourcing as a paradigm to balance learning and sourcing goals. We also draw design implications for future AI-assisted learnersourcing systems that aim to produce reusable, high-quality learner-generated content while promoting educational value.

Transferring programming skills learned in the classroom to diverse real-world scenarios is both essential and challenging in computing education. This experience report describes an approach to facilitate learning transfer by fostering adaptive expertise. Students were engaged in co-creating contextualized worked-out examples, including step-by-step solutions. Through three homework assignments in a Spring 2023 database programming course, we observed substantial improvements, where students generated detailed and accurate solutions and enriched their problem-solving contexts from simple phrases to detailed stories, drawn from 17 real-life scenarios. Our results also suggest that the peer assessment process cultivated a supportive learning environment and fostered adaptive expertise. We discuss the lessons learned and draw pedagogical implications for integrating student-generated contextualized materials in other programming courses.