Scaffolding systematic reviews in learning design and technology through mentoring and AI integration

Abstract Systematic reviews (SRs) are increasingly conducted in the field of Learning Design and Technology, reflecting both the growth of the field and the need for rigorous synthesis of diverse literature. Although the existing methodological guidelines provide clear procedures, the practical implementation of SRs is often more complex, particularly for novice researchers. Rather than reintroducing standard SR procedures or presenting a model SR, this paper addresses a complementary yet underexplored need: to illuminate the realities of conducting SRs in practice and to provide guidance for novice researchers and interdisciplinary teams. We frame SRs as intentional learning experiences that unfold across stages of the review and require mentoring and technological support. Drawing on our experience as a team with varying levels of SR experience and domain expertise, we reflect on challenges at each stage of SR and describe strategies used to manage ambiguity, foster consistency among our team, and maintain review quality despite disciplinary differences and variable reporting conventions. While automation tools reduced some procedural burdens such as screening, interpretive decisions still required substantial human oversight. Importantly, we found that hands-on engagement, mentoring support, and peer discussion were central to sustaining team cohesion and methodological rigor.