Implementing an AI Teaching Assistant for a Class in Motion Picture Engineering

Deirdre O'Regan, Anil C. Kokaram

Since 2015, Trinity College Dublin has delivered a Master's-level “Motion Picture Engineering” (MPE) course uniquely combining core principles with cutting-edge developments in the field. In 2025, to address diverse student backgrounds, we developed a domain-specific AI Teaching Assistant (AI-TA) using Retrieval Augmented Generation (RAG). While RAG is well-established, this paper addresses practical implementation and classroom integration challenges, covering architecture, compliance, system tuning, prompt engineering, UI integration, and operational workload. The AI-TA was deployed to 43 MPE students over seven weeks during Spring 2025. Anonymous telemetry captured engagement patterns, and AI-assisted topic categorization facilitated query exploration for curriculum refinement. Exam outcomes showed no significant performance differences across usage levels, suggesting open-book assessments thoughtfully designed for AI accompaniment need not compromise academic integrity. Students found the AI-TA useful but remained cautious about its use as a tutoring substitute skeptical of its suitability for open-book exams. Our code is available on GitHub.iihttps://github.com/sigmedia/ai-teaching-assistant

Print ISSN
Electronic ISSN
2160-2492
Published
2026-07
Content type
Original Research
Keywords
motion picture engineering, education, artificial intelligence, ai, retrieval augmented generation
DOI
10.5594/JMI.2026/BGCM8723