LACY: Simulating Expert Mentoring for Software Onboarding with Code Tours

2026-03-26

AI Summary

This work addresses the challenge faced by new developers in efficiently comprehending complex codebases when documentation and expert support are scarce, while traditional mentoring is costly and difficult to scale. To overcome this, the authors propose LACY, a novel system that uniquely integrates AI-generated content with expert curation to produce reusable “code tours.” LACY introduces innovative interaction modalities such as Voice-to-Tour, supporting voice-recorded explanations, comprehension quizzes, podcast-style audio, and interactive visual dashboards. An evaluation in Beko’s production environment demonstrates that learners using expert-curated tours achieve significantly higher quiz scores (83%) compared to those using purely AI-generated tours (57%). Experts reported lower effort in creating curated tours than delivering live walkthroughs, and the system has been formally adopted, confirming its scalability and practical utility.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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). Learners using expert-guided tours achieved 83% quiz scores versus 57% for AI-only tours, preferred tours over traditional self-study, and reported they would need fewer expert consultations. Experts found tour creation less burdensome than live walkthroughs. Beko has since adopted Lacy for organizational onboarding, and we release our code and study instruments as a replication package.

Problem

• software onboarding
• code comprehension
• expert mentoring
• code tours
• knowledge transfer

Innovation

• code tours
• hybrid human-AI system
• software onboarding
• expert mentoring
• reusable knowledge