WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mao, Ke, Kapus, Timotej, Åhs, Cons T, Marescotti, Matteo, Ip, Daniel, Hajdu, Ákos, Cela, Sopot, Banerjee, Aparup
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915655917240320
author Mao, Ke
Kapus, Timotej
Åhs, Cons T
Marescotti, Matteo
Ip, Daniel
Hajdu, Ákos
Cela, Sopot
Banerjee, Aparup
author_facet Mao, Ke
Kapus, Timotej
Åhs, Cons T
Marescotti, Matteo
Ip, Daniel
Hajdu, Ákos
Cela, Sopot
Banerjee, Aparup
contents The deployment of AI-assisted development tools in compliance-relevant, large-scale industrial environments represents significant gaps in academic literature, despite growing industry adoption. We report on the industrial deployment of WhatsCode, a domain-specific AI development system that supports WhatsApp (serving over 2 billion users) and processes millions of lines of code across multiple platforms. Over 25 months (2023-2025), WhatsCode evolved from targeted privacy automation to autonomous agentic workflows integrated with end-to-end feature development and DevOps processes. WhatsCode achieved substantial quantifiable impact, improving automated privacy verification coverage 3.5x from 15% to 53%, identifying privacy requirements, and generating over 3,000 accepted code changes with acceptance rates ranging from 9% to 100% across different automation domains. The system committed 692 automated refactor/fix changes, 711 framework adoptions, 141 feature development assists and maintained 86% precision in bug triage. Our study identifies two stable human-AI collaboration patterns that emerged from production deployment: one-click rollout for high-confidence changes (60% of cases) and commandeer-revise for complex decisions (40%). We demonstrate that organizational factors, such as ownership models, adoption dynamics, and risk management, are as decisive as technical capabilities for enterprise-scale AI success. The findings provide evidence-based guidance for large-scale AI tool deployment in compliance-relevant environments, showing that effective human-AI collaboration, not full automation, drives sustainable business impact.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05314
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp
Mao, Ke
Kapus, Timotej
Åhs, Cons T
Marescotti, Matteo
Ip, Daniel
Hajdu, Ákos
Cela, Sopot
Banerjee, Aparup
Software Engineering
Artificial Intelligence
The deployment of AI-assisted development tools in compliance-relevant, large-scale industrial environments represents significant gaps in academic literature, despite growing industry adoption. We report on the industrial deployment of WhatsCode, a domain-specific AI development system that supports WhatsApp (serving over 2 billion users) and processes millions of lines of code across multiple platforms. Over 25 months (2023-2025), WhatsCode evolved from targeted privacy automation to autonomous agentic workflows integrated with end-to-end feature development and DevOps processes. WhatsCode achieved substantial quantifiable impact, improving automated privacy verification coverage 3.5x from 15% to 53%, identifying privacy requirements, and generating over 3,000 accepted code changes with acceptance rates ranging from 9% to 100% across different automation domains. The system committed 692 automated refactor/fix changes, 711 framework adoptions, 141 feature development assists and maintained 86% precision in bug triage. Our study identifies two stable human-AI collaboration patterns that emerged from production deployment: one-click rollout for high-confidence changes (60% of cases) and commandeer-revise for complex decisions (40%). We demonstrate that organizational factors, such as ownership models, adoption dynamics, and risk management, are as decisive as technical capabilities for enterprise-scale AI success. The findings provide evidence-based guidance for large-scale AI tool deployment in compliance-relevant environments, showing that effective human-AI collaboration, not full automation, drives sustainable business impact.
title WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2512.05314