As part of the Aula Innova Teaching Innovation Project at Complutense University of Madrid, we developed a hybrid pedagogical model to teach programming and statistical methods to students, researchers, professors, and faculty staff in the Social Sciences. The project aims to support learners who are not necessarily familiar with programming environments, promoting digital and computational literacy across disciplines. It targets individuals from diverse academic backgrounds, especially in Economics, Sociology, Political Science, and Psychology. The model combines theoretical instruction with hands-on coding practice and has recently developed two distinct GPT-based assistants. The first assistant was designed to support programming in R, offering immediate, context-aware feedback on syntax, error messages, and basic functions. This assistant helps students troubleshoot their code autonomously, reducing anxiety and encouraging exploratory learning, especially among beginners. The second GPT was developed to simulate synthetic datasets aligned with students’ academic disciplines. Trained on undergraduate syllabi across the Social Sciences, it can generate variables and data structures that are both familiar and meaningful. These datasets are methodologically sound and support statistical exercises such as regression, hypothesis testing, and data visualization, fostering both conceptual understanding and applied analytical skills. Both assistants operate promoting accessibility and reproducibility. Rather than replacing instructors, they serve as intelligent pedagogical companions that enhance scalability, support personalization, and reinforce critical thinking. This dual integration demonstrates how generative AI can be leveraged to develop more inclusive, context-aware, and rigorous approaches to teaching programming and data analysis in the Social Sciences.