Natural language processing and generative models are exciting and rapidly evolving areas of research that are transforming the way machines interact with humans. Large language models (LLMs) have a wide range of applications, including machine translation, speech synthesis, automatic question answering, and text generation. In recent years, generative models based on neural networks, such as Recurrent Neural Networks (RNNs) and Transformers, have achieved impressive results in many NLP tasks. These models are able to capture the complex dependencies between words and phrases in language, making it possible to generate text that is not only grammatically correct but also semantically consistent. This paper presents Sofia, a chatbot designed as an academic assistant. Developed using Microsoft’s AzureBot and OpenAI’s API, Sofia aids in educational orientation and information retrieval, fostering a smoother transition for students entering higher education. By leveraging existing models and infrastructure, Sofia ensures robust, domain-specific information delivery and supports multi-language interactions, offering a personalized and ethical tool for student support. This approach exemplifies the potential of generative AI to enhance user experience while minimizing development complexities through model reuse.