AI-Assisted learning: intelligent tutoring system for the introduction to programming course

This thesis presents the development of an AI-powered intelligent tutoring system to address challenges in the Introduction to Programming course at Universidad de los Andes. Using the Lean Startup methodology, we developed a virtual assistant that connects to the Senecode database to provide personalized support to students. Senecode is an online platform where students in the course can practice coding exercises in Python and receive automated feedback. The system included a feedback agent to evaluate the student’s code and a RAG agent to guide the students through relevant topics. We evaluated the system’s impact on student learning outcomes and engagement through iterative testing and refinement based on user feedback.

• Autores: Osorio Cárdenas, Daniel; Guatibonza Briceño, Pablo Alejandro
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2025
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/75502
• Acceso en línea: https://hdl.handle.net/1992/75502
• Palabra clave: Intelligent tutoring system; Chatbot; Artificial intelligence; AI; Education; Programming; AI agents; Agents; Retrieval-Augmented Generation; Inteligencia artificial; IA; Educación; Programación; LangGraph; RAG; Ingeniería
• Rights: openAccess
• License: Attribution-NonCommercial-NoDerivatives 4.0 International