Large Language Models (LLMs) have emerged as a revolutionary force in Computer Science Education, offering unprecedented opportunities to facilitate learning and comprehension. Their application in the classroom, however, is not without challenges. LLMs are prone to hallucination and contextual inaccuracies. Furthermore, they risk exposing learning processes to cheating illicit practices and providing explicit solutions that impede the development of critical thinking skills in students. To address these pitfalls and investigate how specialized LLMs can enhance engagement among learners particularly using LLMs, we present Gurukul, a unique coding platform incorporating dual features - Retrieval Augmented Generation and Guardrails. Gurukul's practice feature provides a hands-on code editor to solve DSA problems with the help of a dynamically Guardrailed LLM to prevent explicit code solutions. On the other hand, Gurukul's Study feature incorporates a Retrieval Augmented Generation mechanism that uses OpenDSA as its source of truth, allowing the LLM to fetch and present information accurately and relevantly, thereby trying to overcome the issue of inaccuracies. We present these features to evaluate the user perceptions of LLM-assisted educational tools. To evaluate the effectiveness and utility of Gurukul in a real-world educational setting, we conducted a User Study and a User Expert Review with students (n=40) and faculty (n=2), respectively, from a public state university in the US specializing in DSA courses. We examine student's usage patterns and perceptions of the tool and report reflections from instructors and a series of recommendations for classroom use. Our findings suggest that Gurukul had a positive impact on student learning and engagement in learning DSA. This feedback analyzed through qualitative and quantitative methods indicates the promise of the utility of specialized LLMs in enhancing student engagement in DSA learning. / Master of Science / Computer science education is continuously evolving with new technologies enhancing the learning experience. This thesis introduces Gurukul, an innovative platform designed to transform the way students learn Data Structures and Algorithms (DSA). Gurukul integrates large language models (LLMs) with advanced features like Retrieval Augmented Generation (RAG) and Guardrails to create an interactive and adaptive learning environment. Traditional learning methods often struggle with providing accurate information and engaging students actively. Gurukul addresses these issues by offering a live code editor for hands-on practice and a study feature that retrieves accurate information from trusted sources. The platform ensures students receive context-sensitive guidance without bypassing critical thinking skills. A study involving students and faculty from a public university specializing in DSA courses evaluated Gurukul's effectiveness. The feedback, based on qualitative and quantitative evaluations, highlights the platform's potential to enhance student engagement and learning outcomes in computer science education. This research contributes to the ongoing development of educational technologies and provides insights for future improvements.

[pt] O presente trabalho teve como objetivo analisar a percepção dos alunos dos cursos de Administração, de cinco Universidades particulares de ensino superior do estado do Rio de Janeiro, acerca do investimento destas universidades nas tendências acadêmicas apontadas para os próximos anos, de acordo com o relatório anual de 2017, da New Media Consortium em parceria com a EDUCAUSE Learning Initiative, a saber: i) tecnologias de aprendizagem adaptativa; ii) Mobile Learning; iii) Internet das Coisas e iv) ambiente de aprendizagem virtual. Na análise dos dados, cada tendência foi dividida em duas sub-tendências. Este trabalho teve como objetivo secundário, avaliar o quanto estas tendências são consideradas importantes para seu principal público-alvo. Sendo assim, pudemos concluir que na percepção de tal público, as IES pesquisadas (PUC, UFRJ, UVA, UCAM e UNESA) têm investido pouco nestas novas tendências acadêmicas, sendo a PUC a que mais investe nas quatro tendências citadas acima. Apenas uma sub-tendência dentro de tecnologias de aprendizagem adaptativa e outra dentro de ambiente de aprendizagem virtual ficaram com percepção média acima de razoável, no quesito investimento, ambas associadas à PUC. No entanto, os alunos da PUC foram os que avaliaram a grande maioria das tendências como de menor importância quando comparados aos alunos das outras IES. Apesar disto, a média de avaliação de importância das tendências foi de razoável a muito importante. Enfatiza-se que novas pesquisas sejam feitas constantemente, visto que novas tecnologias de aprendizagem, que substituem as anteriores, estão surgindo com frequência. / [en] The present study had as a primary objective analyze the perception of students from business courses of 5 private universities of higher education in the state of Rio de Janeiro, about the investment of these universities in the academic trends pointed out for the next years, based on the annual report of the New Media Consortium in partnership with the EDUCAUSE Learning Initiative. These trends are: i) adaptive learning technologies; ii) mobile learning; iii) internet of things and iv) virtual learning environment. In the data analysis, each trend was divided into two sub-trends. As a secondary objective, this study aims to evaluate how much these trends are considered important for its main target audience. Thus, we could conclude that in the perception of such public, the universities surveyed (PUC, UFRJ, UVA, UCAM and UNESA) have invested little in these new academic trends, with PUC being the one investing most in the four trends mentioned above. Only one sub-trend within adaptive learning technologies and another within virtual learning environment were perceived to be above average as reasonable in terms of investment, both associated with PUC. However, PUC students were those who evaluated the great majority of trends as less important when compared to the students of other universities. Despite this, the average valuation of trends importance was from reasonable to very important. It is emphasized that new research needs constantly being done, as new learning technologies, which replace the previous ones, are emerging frequently.