This paper explores the integration of generative artificial intelligence (AI) into personalized learning experiences in educational settings. The authors propose an affordable and sustainable approach to personalizing learning materials within a pre-existing learning management system (LMS) at a software engineering college. They create a tool that automatically generates learning materials based on the learning outcomes provided by the professor, with three distinct styles: traditional, Batman, and Wednesday Addams. Each lesson includes automatically generated multiple-choice questions for self-assessment. The study involved 20 college students studying software engineering at a European university. The students voluntarily participated in the experiment, which was conducted over two semesters. The results indicate that students found the multiple variants of the learning materials engaging, with a preference for the traditional variant. The most popular feature was the automatically generated quiz-style tests, which helped students assess their understanding. Preliminary evidence suggests that using various versions of learning materials increases students' study time, especially for those who initially struggled with the topic. The study's small sample size limits its generalizability, but it provides useful early insights and lays the groundwork for future research on AI-supported educational strategies. The authors discuss the ethical implications of using generative AI, including biases and the potential for generating inaccurate or misleading information. They also highlight the need for further research to address the gaps in the literature, particularly in empirical studies integrating LLMs into classroom settings. personalized learning; AI for learning; character-based learning; automated content generation; LLMs in education; innovative teaching methods; learning management systemsThis paper explores the integration of generative artificial intelligence (AI) into personalized learning experiences in educational settings. The authors propose an affordable and sustainable approach to personalizing learning materials within a pre-existing learning management system (LMS) at a software engineering college. They create a tool that automatically generates learning materials based on the learning outcomes provided by the professor, with three distinct styles: traditional, Batman, and Wednesday Addams. Each lesson includes automatically generated multiple-choice questions for self-assessment. The study involved 20 college students studying software engineering at a European university. The students voluntarily participated in the experiment, which was conducted over two semesters. The results indicate that students found the multiple variants of the learning materials engaging, with a preference for the traditional variant. The most popular feature was the automatically generated quiz-style tests, which helped students assess their understanding. Preliminary evidence suggests that using various versions of learning materials increases students' study time, especially for those who initially struggled with the topic. The study's small sample size limits its generalizability, but it provides useful early insights and lays the groundwork for future research on AI-supported educational strategies. The authors discuss the ethical implications of using generative AI, including biases and the potential for generating inaccurate or misleading information. They also highlight the need for further research to address the gaps in the literature, particularly in empirical studies integrating LLMs into classroom settings. personalized learning; AI for learning; character-based learning; automated content generation; LLMs in education; innovative teaching methods; learning management systems