Abstract
Generative AI (GenAI) can ease software contribution while making contributors and their work harder to assess. We investigate how this tension affects the sustainability of the Google Summer of Code (GSoC) mentoring pipeline and how stakeholders respond, through a sequential qualitative study of mentor mailing-list discussions and interviews with 15 mentors and organization administrators. Participants reported that GenAI helps with onboarding, coordination, and initial review but weakens evidence of mentees’ capability, understanding, and ownership, adding verification and governance work that strains newcomer learning and mentors’ willingness to continue. Drawing on reported strategies that distribute responsibility across mentees, mentors, organizations, and GSoC, we propose a GenAI Mentoring and Governance Decision Framework of five acceptable-use stances. Sustaining OSS mentoring requires protecting newcomer development and mentor capacity together, with governance adapted to local conditions.