Oriol Borrás-Gené

This study presents the design, implementation, and exploratory classroom evaluation of a course-constrained educational assistant combining Retrieval-Augmented Generation (RAG) with large language models (LLMs) in Vocational Education and Training (VET). The platform retrieves teacher-provided materials, generates course-aligned responses, displays source references, and returns a predefined abstention message when evidence appears insufficient. It was deployed during a practical session in the Spanish Higher Vocational Training programme Administración de Sistemas Informáticos en Red (ASIR; Network and Information Systems Administration). Nineteen students and one instructor completed a post-session questionnaire. Students reported positive perceptions of usability, clarity, perceived reliability, and learning support, while restricted corpus coverage and the absence of conversational memory emerged as limitations. To complement the perception-based classroom study, a separate post hoc technical assessment used 30 predefined queries with the same prototype and corpus. All 16 fully answerable prompts received substantive responses; 13 were rated fully correct and three partially correct by the first author. Seven of eight deliberately out-of-corpus prompts triggered abstention, whereas one OpenShift Route query produced an unsupported answer from semantically adjacent but non-supporting Kubernetes evidence. The contribution is empirical and design-oriented rather than algorithmic. The findings are context-specific and show both the potential and limitations of bounded cognitive support grounded in instructor-selected materials.

This study presents the design, implementation, and exploratory classroom evaluation of a web-based educational assistant built on Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) for Vocational Education and Training (VET). The platform was designed to generate responses based on teacher-provided course materials, preserve source traceability, and return an abstention message when the retrieved evidence is insufficient. The assistant was deployed in an authentic classroom setting within the Higher Vocational Training programme in Network and Information Systems Administration (ASIR). Nineteen students and one instructor used the system during a practical session and completed a post-session questionnaire combining Likert-scale items with open-ended questions. The findings indicate positive student perceptions of usability, response clarity, perceived reliability, and learning support. Participants particularly valued the ability to obtain focused answers aligned with the instructional materials. The evaluation also revealed a relevant trade-off: restricting the assistant to a controlled corpus reinforced curricular consistency and perceived trustworthiness but limited its capacity to address questions insufficiently covered by the available resources. The absence of conversational memory emerged as the most frequently requested improvement. These preliminary findings suggest that course-constrained RAG assistants may constitute valuable complementary tools for transparent and pedagogically supervised AI-supported learning in technical VET contexts.

In higher education, maintaining student engagement in voluntary activities remains a challenge. While serious games are recognized for enhancing motivation, evidence regarding their long-term effectiveness in non-graded contexts is limited. This study evaluates the impact of “The Time Machine”, an interactive branching-narrative serious game, on academic motivation and participation. A quasi-experimental study was conducted across 14 undergraduate courses. The Motivated Strategies for Learning Questionnaire-Short Form (MSLQ-SF) was administered in three surveys (Survey 1, Survey 2, Survey 3). In total, 404 students completed at least one survey (635 questionnaire records). Longitudinal analyses (Friedman test) were conducted on the complete-case sample (n = 65) comprising students who responded to all three surveys and revealed no statistically significant changes in motivational dimensions. Completion rates (defined as responding to all three surveys) were significantly dependent on the implementation context (Fisher’s test, p < 0.001), being higher in groups with direct instructional support. Additionally, female students reported significantly higher test anxiety than males, while prior affinity for video games showed no influence on motivational outcomes. Narrative-driven serious games can sustain motivation over time effectively. However, their success relies critically on pedagogical scaffolding and teacher involvement rather than solely on game mechanics or students’ gamer profiles.

El juego forma parte de nuestra naturaleza, desde pequeños comenzamos a jugar y divertirnos con nuestro propio juego, buscando juegos y juguetes en lo que nos rodea. Y esto nos lleva a descubrir, competir, cooperar o simplemente disfrutar. Jugando aprendemos, con independencia de si será un aprendizaje más o menos formal o útil, pero nos induce a desarrollar estrategias, aprender a cooperar con otros, memorizar y todo acompañado de diversos sentimientos: desde alegría o satisfacción hasta la frustración. Podemos pasarnos horas jugando si el juego nos motiva y nos supone un reto alcanzable. Ahora traslademos estas ideas a otros contextos como puedan ser la salud o deporte, el mundo de los negocios o la educación en cualquiera de sus modalidades, desde los aprendizajes más formales hasta otros informales que se puedan dar en el propio puesto de trabajo con nuestros compañeros. Puede ser una oportunidad aplicar estas ideas extraídas de jugar o de los juegos para conseguir una mayor atención, dedicación, motivación, etc. en dichos contextos.

The emergence of generative artificial intelligence (GAI) has revolutionized numerous aspects of our lives and presents significant opportunities in education. However, specific digital competencies are essential to effectively leverage this technology’s potential. Notably, prompt engineering proficiency presents a significant barrier to achieving optimal outcomes. In response, various solutions are being developed, including custom GPTs available through OpenAI’s ChatGPT platform. This study validates ‘GamifIcA Edu’, a specialized GPT-based assistant for gamification and serious games, designed to enable educators to implement these pedagogical approaches without requiring advanced prompt engineering expertise. This is achieved through the utilization of pre-designed instructional frameworks. The assistant’s effectiveness was evaluated using a comprehensive rubric across five distinct use-case scenarios. Each scenario underwent four different tests, representing varied learning contexts across multiple academic disciplines. The validation methodology involved a systematic assessment of the assistant’s performance in diverse educational settings. The findings demonstrate the successful implementation of this custom-designed GPT, which generated contextually appropriate responses through natural language interactions, thus eliminating the need for complex prompt structures. This research highlights the potential of instruction-based design in the development of AI assistants that empower users with limited prompt engineering knowledge to achieve expert-level results. These findings have significant implications for the democratization of AI-enhanced educational tools.

Aim/Purpose: This paper addresses the problem of low student engagement, motivation, and deep learning in traditional university teaching methods. It explores how integrating flipped classroom strategies and gamification through digital badges can effectively overcome some of these limitations. Background: With the consolidation of active methodologies in higher education, supported by blended learning environments and innovative tools, the flipped classroom and gamification have gained prominence as strategies to enhance participation and self-regulated learning. Yet, their joint application in teacher training programs remains underexplored, particularly regarding their impact on digital competence development. Methodology: The study employed a quantitative research approach, analyzing student performance data (grades, tasks completed, video viewing) and survey responses on perceptions of the teaching methods used. The research sample consisted of 63 first-year university students enrolled in an Early Childhood Education bachelor’s degree at Universidad Rey Juan Carlos. Contribution: This paper contributes to the literature by providing empirical evidence on the effectiveness of combining flipped classroom methodologies with gamification elements, specifically digital badges, in enhancing student motivation, engagement, and academic performance. It highlights how structured integration of technology-supported active learning strategies can successfully address challenges commonly associated with traditional educational methods. Findings: Students who participated in the flipped classroom model and earned digital badges demonstrated significantly higher academic performance compared to those who did not complete the full intervention. The flipped classroom methodology was highly accepted by students, who perceived pre-class video viewing as more effective than traditional lectures. Digital badges effectively increased student motivation and provided a clear visualization of their learning progress, encouraging higher engagement and course completion rates. Recommendations for Practitioners: Practitioners should integrate flipped classroom approaches with gamification techniques, such as digital badges, to boost student engagement, motivation, and academic performance. Additionally, they are encouraged to develop interactive multimedia content that clearly communicates learning progress and outcomes, thereby enhancing students’ active participation. Recommendation for Researchers: Researchers are encouraged to investigate further the integration of gamification strategies, such as digital badges, within flipped classroom models to enhance student engagement and learning outcomes. Impact on Society: The wider implications are that adopting active, technology-supported methodologies, such as flipped classrooms and gamification, in higher education can significantly improve student engagement, motivation, and learning outcomes, ultimately fostering essential digital skills among future educators and positively influencing teaching practices in broader educational contexts. Future Research: The future goal is to develop a more comprehensive badge system designed to engage students from the outset, particularly targeting those at risk of dropping out, by assigning badges to incremental achievements, such as completing individual lessons.

This study investigates the impact of AI-generated contexts on preservice teachers’ computational thinking (CT) skills and their acceptance of educational robotics. This article presents a methodology for teaching robotics based on AI-generated contexts aimed at enhancing CT. An experiment was conducted with 122 undergraduate students enrolled in an Early Childhood Education program, aged 18–19 years, who were training in the Computer Science and Digital Competence course. The experimental group utilized a methodology involving AI-generated practical assignments designed by their lecturers to learn educational robotics, while the control group engaged with traditional teaching methods. The research addressed five key factors: the effectiveness of AI-generated contexts in improving CT skills, the specific domains of CT that showed significant improvement, the perception of student teachers regarding their ability to teach with educational robots, the enhancement in perceived knowledge about educational robots, and the overall impact of these methodologies on teaching practices. Findings revealed that the experimental group exhibited higher engagement and understanding of CT concepts, with notable improvements in problem-solving and algorithmic thinking. Participants in the AI-generated context group reported increased confidence in their ability to teach with educational robots and a more positive attitude toward technology integration in education. The findings highlight the importance of providing appropriate context and support when encouraging future educators to build confidence and embrace educational technologies. This study adds to the expanding research connecting AI, robotics, and education, emphasizing the need to incorporate these tools into teacher training programs. Further studies should investigate the lasting impact of such approaches on computational thinking skills and teaching methods in a variety of educational environments.

This study investigates the impact of AI-generated contexts on preservice teachers' computational thinking (CT) skills and their acceptance of educational robotics. This article presents a methodology for teaching robotics based on AI-generated contexts aimed at enhancing CT. An experience was conducted with 122 undergraduate students enrolled in an Early Childhood Education program, aged 18-19 years, who were training in a Computer Science and Digital Competence course. The experimental group utilized a methodology involving AI-generated practical assignments designed by their lecturers to learn educational robotics, while the control group engaged with traditional teaching methods. The research addressed five key questions: the effectiveness of AI-generated contexts in improving CT skills, the specific domains of CT that showed significant improvement, the perception of student teachers regarding their ability to teach with educational robots, the enhancement of perceived knowledge about educational robots, and the overall impact of these methodologies on teaching practices. Findings revealed that the experimental group exhibited higher engagement and understanding of CT concepts, with notable improvements in problem-solving and algorithmic thinking. Participants in the AI-generated context group reported increased confidence in their ability to teach with educational robots and a more positive attitude towards technology integration in education. The results underscore the importance of context and support in fostering both confidence and acceptance of educational technologies among future educators. This research contributes to the growing body of literature at the intersection of AI, robotics, and education, advocating for the integration of AI and robotics into teacher training curricula. Future research should explore the long-term effects of these methodologies on CT skills and teaching practices across diverse educational settings.

Educational escape rooms aims to motivate students, to strengthen knowledge and evaluate learning. Pre-service teachers enrolled in “Computer Science and Digital Competency” course shows lack of motivation and difficulties to realise its usefulness in everyday practice, becoming an ideal context to apply this strategy. 157 students belonging to a European university participated in the experience as case study. The educational escape room was conducted following a hybrid model, mixing a physical organization of props with a virtual organization of the narrative, tests and achievements. The experiment was designed to answer two hypotheses, first if applying escape room as an educational strategy fosters pre-primary and primary students' motivation, since this method address complex concepts in a practical way, and second, if the application of this strategy as teaching strategy makes students perceive the learning process as a game.

Personal learning environments or their acronym PLEs are understood as a set of tools, resources, connections, and activities that each person regularly uses for learning. This study examines the PLE approach in a university setting, evaluating its impact on student learning in a university subject within an education master’s program. The effect is assessed from two perspectives: a quantitative one based on the ‘PLE test’—administered at the beginning and end of the course—and a qualitative one based on the assessment provided by the students themselves regarding the impact of training in digital tools and competencies on their PLE, at the beginning and end of the course. The ‘PLE test’ measures four factors: time organization, creation–editing, searching–investigating, and collaborating–contact networks. In all four factors, by the end of the course, there is a significant increase in usage scores, especially in the last two. The students’ assessments of the evolution of their PLEs reflect the evident impact of this approach as a strategy for more effective and self-managed learning.