The rise of Artificial Intelligence (AI) and Large Language Models (LLMs) has profoundly influenced various sectors, such as education and healthcare. LLMs like OpenAI’s ChatGPT are increasingly used by students and educators globally. However, their effective integration in education remains underexplored, and no comprehensive framework exists to guide their optimal use. This research aims to address this gap by examining current LLM applications in education, namely mental care and obstetrics education, identifying patterns, assessing impacts on learning outcomes, and proposing a framework to enhance their effectiveness. Following the Design Science Research (DSR) methodology, we will propose a framework to assist educators in effectively leveraging LLMs to enhance learning outcomes. The framework will be validated through the development of a prototype and case studies.