This Master’s Thesis aims to enhance the education platform Artemis by implementing automatic formative feedback for students and improving semi-automatic assessment for tutors. Building on the foundational work of Athena and CoFee, which utilize NLP and LLMs for text-based feedback, this project focuses on refining these techniques for greater accuracy, reliability, and consistency. The initial phase prioritized the development of an immediate in-line feedback mechanism to provide students with feedback before the deadline of an exercise. Subsequently, we explored the latest Llama 3 and GPT models and utilized advanced LLM techniques like Retrieval Augmented Generation, Chain of Thought prompting, self-consistency, and in-context learning. The models and approaches were evaluated for accuracy, efficiency, and educational impact to ensure continuous improvement. We aim to deliver automated and reliable personalized feedback that enhances student learning and reduces tutors’ workload, creating a more efficient and supportive educational environment.