Scaling assessment innovation: from immediate feedback MCQs to automated question generation with LLMs

Managing assessment in large, multi-campus computing cohorts is challenging, especially with reduced contact hours and growing demand for distance learning. We describe a trial of a modified Immediate Feedback Assessment Technique (IFAT), combining au- tomatically marked multiple-choice questions (MCQs) with peer review. This improved consistency, supported professional-style learning, and was well received by staff and students, but required extensive effort to author hundreds of MCQs. Early classroom tri- als with two student cohorts demonstrate technical feasibility and promising engagement, though outcome data is still emerging. We reflect on how LLM-assisted assessment design can make innova- tive practices like IFAT more sustainable and scalable in computing education. Separately, we extend this approach with a novel open- source command-line tool that leverages large language models (LLMs) to automatically generate Moodle-ready GIFT files directly from course materials such as PDFs or Powerpoint slides; including images. This enables the rapid creation of substantial MCQ banks in minutes, removing the major barrier to scaling the IFAT method.