Rakuten accelerates development with Claude Code

Overview

Rakuten, a large Japanese ecommerce company, uses Claude Code to automate coding tasks across its engineering teams, reducing time to market for new features from 24 days to 5 days and achieving 7 hours of sustained autonomous coding on a complex open-source refactoring project. Rakuten also deployed Claude Managed Agents across product, sales, marketing and finance, plugging into Slack and Teams for non-engineers to complete tasks.

The challenge

Rakuten's evaluation of existing AI coding tools revealed that most required constant human guidance and couldn't navigate complex, multi-language codebases. With thousands of developers serving millions of customers, Rakuten needed AI that could accelerate time to market while maintaining enterprise-grade quality and security standards.

The solution

Rakuten redesigned development workflows around Claude Code, using it throughout the development lifecycle for writing unit tests, mocking APIs, building components, fixing bugs, generating documentation, AI-powered code review, and running multiple parallel Claude Code sessions. Rakuten also deployed Claude Managed Agents across product, sales, marketing and finance, plugging into Slack and Teams so employees can assign tasks and receive deliverables like spreadsheets, slides and apps in sandboxed environments, with each specialist agent deployed within a week.

Reported business value

Rakuten reduced time to market for new features by 79% (from 24 working days to 5 days) and delivered 99.9% accuracy on complex code modifications. In one case, Claude Code completed a complex activation vector extraction implementation in vLLM (a 12.5-million-line open-source codebase) in 7 hours of sustained autonomous coding with minimal human guidance, achieving 99.9% numerical accuracy compared to the reference method.