LACY: Simulating Expert Mentoring for Software Onboarding with Code Tours
Zeynep Beg\"um Kara, Aytekin \.Ismail, Ece Ate\c{s}, \.Izgi Nur Tamc{\i}, Zehra \.Iyig\"un, Selin \c{S}irin Aslang\"ul, \"Omercan Devran, Baykal Mehmet U\c{c}ar, Eray T\"uz\"un

TL;DR
LACY is a hybrid system combining AI and expert input to create reusable code tours, significantly improving onboarding effectiveness and reducing expert workload in complex software environments.
Contribution
First hybrid approach integrating AI-generated content with expert curation for software onboarding through code tours.
Findings
Learners achieved 83% quiz scores with expert-guided tours.
Participants preferred tours over traditional self-study.
Experts found tour creation less burdensome than live walkthroughs.
Abstract
Every software organization faces the onboarding challenge: helping newcomers navigate complex codebases, compensate for insufficient documentation, and comprehend code they did not author. Expert walkthroughs are among the most effective forms of support, yet they are expensive, repetitive, and do not scale. We present Lacy, a hybrid human-AI onboarding system that captures expert mentoring in reusable code tours-to our knowledge, the first hybrid approach combining AI-generated content with expert curation in code tours. Our design is grounded in requirements derived from 20+ meetings, surveys, and interviews across a year-long industry partnership with Beko. Supporting features include Voice-to-Tour capture, comprehension quizzes, podcasts, and a dashboard. We deployed Lacy on Beko's production environment and conducted a controlled study on a legacy finance system (30K+ LOC).…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExpert finding and Q&A systems · Mobile Crowdsensing and Crowdsourcing · Scientific Computing and Data Management
