Iris Groher

Iris Groher, Patrick Heissenberger, Michael Vierhauser

Large Language Models (LLMs) have become part of how students solve programming tasks, offering immediate explanations and even full solutions. Previous work has highlighted that novice programmers often heavily rely on LLMs, thereby neglecting their own problem-solving skills. To address this challenge, we designed a course-specific online Python tutor that provides retrieval-augmented, course-aligned guidance without generating complete solutions. The tutor integrates a web-based programming environment with a conversational agent that offers hints, Socratic questions, and explanations grounded in course materials. Students used the system during self-study to work on homework assignments, and the tutor also supported questions about the broader course material. We collected structured student feedback and analyzed interaction logs to investigate how they engaged with the tutor's guidance. We observed that students used the tutor primarily for conceptual understanding, implementation guidance, and debugging, and perceived it as a course-aligned, context-aware learning support that encourages engagement rather than direct solution copying.

Iris Groher, Michael Vierhauser, Markus Weninger

The recent emergence of generative AI and Large Language Models (LLMs), particularly following the release of ChatGPT in late 2022, has significantly impacted both academic research and industrial practice. This development has vast potential to impact educational practices across various domains, particularly within computer science and software engineering courses. Unfortunately, there is still a lack of actionable guidance on how to integrate AI technology coherently into computer science curricula. In this paper, we therefore introduce the concept of AI-Blueprints, a structured approach to integrating AI-related topics and activities into various computer science courses. We describe our approach and outline a structured process for creating new blueprints. Our vision is to provide these blueprints as open educational resources, allowing educators to adapt and integrate AI into diverse courses and topics. As a preliminary validation, we conducted semi-structured interviews with six university-level educators, collecting feedback on how our blueprints could help to integrate AI topics into existing courses. Based on this feedback, we lay out plans for future research and expanding our AI-Blueprint concept.

Ruzanna Chitchyan, Joost Noppen, Iris Groher

Sustainability (defined as 'the capacity to keep up') encompasses a wide set of aims: ranging from energy efficient software products (environmental sustainability), reduction of software development and maintenance costs (economic sustainability), to employee and end-user wellbeing (social sustainability). In this report we explore the role that sustainability plays in software product line engineering (SPL). The report is based on the 'Sustainability in Software Product Lines' panel held at SPLC 2014.