Recent shifts in pedagogical practices and study habits have highlighted the need to capture and sustain students' attention through more interactive and engaging learning experiences. Traditional lecture-based approaches have shown limitations in maintaining engagement, particularly in technically demanding STEM disciplines (Parra-González et al., 2025). Research suggests that gamified learning environments, incorporating short-term goals, visible progression, and positive reinforcement, can significantly improve motivation, self-efficacy, and academic performance in higher education (Marlow et al., 2024; Zeng et al., 2024). Concurrently, the rapid advancement of Large Language Models has opened new avenues for scalable, personalised education, enabling automatic exercise generation and immediate adaptive feedback at low cost (Meyer et al., 2024; Thomas et al., 2026).

In this context, this paper presents the development of an educational application aimed at teaching Digital Systems, Computer Architecture, and Embedded Systems, with the goal of making traditionally demanding content more accessible, motivating, and effective. The application seeks to promote consistent study through short-term goals, visible progression, positive reinforcement, and frequent challenges, drawing inspiration from the Duolingo platform and its widely recognised success (Shortt et al., 2023; Andrade et al., 2022). In parallel, the application leverages AI mechanisms, namely Large Language Models (LLMs), for the automatic generation of exercises, assessment, and immediate feedback, as well as for learner support, through a domain-specific language model oriented towards Digital Systems, Computer Architecture, and Embedded Systems (Murgia et al., 2024).