Rakuten fixes issues twice as fast with Codex

OpenAI
Rakuten uses OpenAI's Codex to accelerate software development, reducing incident response time by 50% and enabling autonomous execution on complex projects.

Summary

Rakuten, a global innovation company, has integrated OpenAI's Codex into its engineering stack to enhance speed and safety across its complex product ecosystem. Yusuke Kaji, General Manager of AI for Business, focuses their AI agenda on three priorities: building faster, building safer, and operating smarter ("AI-nization"). Codex helps compress Mean Time To Recovery (MTTR) by up to 50% by accelerating root-cause analysis using KQL monitoring data. For safety, Codex is integrated into the CI/CD pipeline to automatically conduct code reviews and vulnerability checks against internal standards. For autonomy, Codex drives large, ambiguous projects forward, exemplified by one project where it implemented a full-stack mobile application from partial requirements, reducing development time from a quarter to weeks. This shift is changing the engineer's role to defining clear specifications and verifying outputs rather than checking every line of code.

(Source:OpenAI)