Iterative semester-long improvement cycles combining feature integration with real-world testing¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The authors describe an ongoing improvement cycle in which "each cycle would consist of integration of new features (in the system or curriculum-wise) and a following semester-long testing in a real world setting." Future plans include rolling the ITS out as a course-long support tool, using it as a training and development tool in study projects where students develop novel features, adding an authoring interface for teachers, learner-model dashboards with improved explainability, and A/B testing with pre- and post-tests to compare pedagogical models.

Design Implications¶

Context¶

Requirements¶

• Real-world semester-long testing settings to validate each feature cycle
• Empirical studies to validate variations of the outer loop

Constraints¶

• The system currently requires manual task file uploads; an authoring interface is planned but not yet built

Target Learners¶

• Advanced undergraduate and early postgraduate computer science students

Target Learning Goals¶

• Longitudinal support of Python and data science knowledge acquisition

Related Strategies¶

• Establish continuous improvement cycles that monitor and evaluate POG implementation
• Planned enhancements: multi-turn conversational follow-up, RAG-based personalization, and feedback analytics for AI-assisted instruction
• Integrate background grade-prediction models into early alert advising systems

Examples¶

-

Key Sources¶

• Alina Deriyeva, Jesper Dannath, and Benjamin Paaßen. (2025). SCRIPT: Implementing an Intelligent Tutoring System for Programming in a German University Context. Artificial Intelligence in Education (Springer). https://doi.org/10.1007/978-3-031-99261-2_16