ChatPLT: An intelligent tutoring system for teaching Physics in Higher Education

The application of artificial intelligence (AI) has attracted great interest in higher education, highly influenced by the development of information and communication technologies. Integrating artificial intelligence into learning ecosystems is one of the biggest challenges for higher education. In this work, an intelligent tutoring system based on AI has been designed but with control of the possible responses. For this, a first diagnostic phase was carried out that determined the selection of initial material that will be used by the neural network or classifier algorithm, so that the teacher has control of the answers offered, limiting the sources of information used. Subsequently, this selection of documents is part of the input, together with the question in a large language model (LLM) ChatGPT-type conversational network. All developments have been done using open access resources. It is the first stage of a project to obtain a predictive analysis of each learning studding.