The widespread adoption of modern artificial intelligence-based chatbots has revolutionised human–computer interactions. The use of these tools confirms reading as one of the primary ways of accessing information. The grapheme–phoneme conversion process is fundamental in learning to read and justifies the research for the development of tools capable of facilitating it. In the special case of a dyslexic student, the design choices related to a digital textual content cannot be a direct result of the aesthetic sense of the content creator. In this paper GreekDyslexic is presented, a Greek letter font that attempts to meet the characteristics proposed by the literature on high readability design. The production phases of GreekDyslexic are described, from the choice of elementary forms for their composition to the homogenisation process. This endeavour is driven by four key motivations: its application for native Greek speakers, its utility for learners of classical or modern Greek, the use of Greek letters in mathematics and physics, and its integration into digital museum materials. To achieve these objectives, a caption-based test is structured in which GreekDyslexic is compared to some of the most widely used fonts or those regarded as highly readable due to their sans serif nature. The test was administered to 98 Greek-speaking adults from Cyprus and Greece, 19 of whom reported a diagnosis of dyslexia. Despite being in the minority, a part of the sample rated GreekDyslexic positively. As a result, several potential solutions for future design interventions that effectively improve readability are suggested.
This project presents the development of a Retrieval-Augmented Generation (RAG) system applied to the customization of a Non-Playable Character (NPC), designed as the Non-Playable Character (NPC) of the President of the IDIS Foundation Città della Scienza (City of Science). The NPC acts as both a virtual guide and institutional ambassador within the science center, providing multilingual, interactive, and accessible communication for a broad international audience. Through the integration of generative models with a curated, validated knowledge base, the RAG system enables the NPC to provide accurate, context-sensitive, and up-to-date responses to user queries. Developed by the Teaching Learning Centre for Education and Inclusive Technologies ‘Elisa Frauenfelder’ at the University of Salerno, the system supports the museum’s educational mission by enhancing science communication and fostering inclusive digital engagement. The Non-Playable Character (NPC) features realistic facial animation, movement, and voice synthesis, creating a digital twin capable of simulating human-like interaction. This initiative exemplifies an innovative application of artificial intelligence for an inclusive and equitable quality education and contributes to the development of engaging, accessible, and personalized learning environments.