Ontwikkeling van een AI-gebaseerd prototype dat studenten en docenten ondersteunt met oefeningen

With the emergence of Large Language Models (LLMs), there is now an opportunity for students to ask artificial intelligence (AI) questions. However, there are concerns among teachers about the impact of AI on teaching quality, for example due to the accuracy of AI-generated answers and potentially reduced interaction with students. This master's thesis focuses on exploring the applications and challenges of AI in education, especially LLMs, and creating a prototype that demonstrates how these applications can be implemented.

Following the literature review, some experiments are conducted in which LLMs' responses are presented to teachers. The findings from these serve as the basis for developing several tools that can support teachers and students in exercises. Ultimately, an application is developed that makes the different tools available in a way that is transparent about the AI tools used.

Teacher-customisable LLMs, exercises suggested by a recommender and a dynamic FAQ add to the possibilities of improving teaching with AI. Collected data ensures that the interaction between teachers and students does not diminish and teachers can better tailor their material to students. This is a small sample of the possibilities of AI in education. Further research can focus on conducting a user study to evaluate the effectiveness and user experience.