How Rakuten Uses Claude Code to Cut Feature Delivery from 24 to 5 Days
Rakuten is a Japanese technology conglomerate operating over 70 businesses including e-commerce, fintech, travel, and communications, with thousands of developers serving millions of customers globally. The company deployed Claude Code and Claude Managed Agents as part of its “AI-nization” strategy, enabling autonomous multi-hour coding sessions and cross-functional agent workflows. Feature delivery time dropped 79%, from 24 working days to 5, while a seven-hour autonomous refactoring run on a 12.5-million-line codebase delivered 99.9% accuracy.
Impact
79%
Reduction in average time to market for new features
7 hours
Autonomous coding session duration on complex refactoring
99.9%
Accuracy on complex code modifications
1 week
Time to deploy each specialist Managed Agent
Challenge
Rakuten’s engineering teams needed AI that could autonomously navigate large, multi-language enterprise codebases without constant guidance, while existing AI coding tools consistently required human intervention to make meaningful progress on complex tasks.
Solution
Rakuten adopted Claude Code for autonomous software development across its engineering organization and deployed Claude Managed Agents across product, sales, marketing, and finance—enabling parallel coding sessions, cross-functional agent workflows, and contributions from non-engineers via a terminal interface.
Tools & Technologies
What Leaders Say
“We want to give all our teams the power to innovate quickly and drive greater impact for customers faster. It’s about multiplying what each team can achieve, not just automating existing tasks.”
“You can have five tasks running in parallel by delegating four to Claude Code while focusing on the remaining one.”
“With Managed Agents, our power users become like Galileo, contributing across domains far beyond a single specialty or discipline.”
“I didn’t write any code during those seven hours. I just provided occasional guidance.”
“I wasn’t naturally using test-driven development before, but Claude Code makes it so easy. It generates comprehensive tests instantly, then builds features that pass them. It’s completely changed how I develop and made me a much more efficient engineer.”
“Our time to market has been significantly brought down because Claude Code gives us those super powers to make executions much, much faster.”
“Claude Code is not just a tool—it’s part of our AI journey.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
Rakuten’s scale creates problems that most engineering organizations never face. With over 70 businesses, thousands of developers, and millions of customers across e-commerce, travel, fintech, and digital content, the company needed AI capable of navigating genuinely complex, multi-language codebases—not tools that required constant hand-holding to produce incremental suggestions.
The company’s leadership had already invested in building its own large language models and AI agents, giving it an unusually clear-eyed view of what AI could and could not do. After evaluating existing AI coding tools and finding them unable to sustain independent work on enterprise-scale repositories, Rakuten tested Claude Code on a demanding benchmark: implement a specific activation vector extraction method in vLLM, a library containing 12.5 million lines of code across multiple programming languages.
Claude Code completed the entire implementation autonomously in seven hours— without a single line of code written by the engineer who initiated the task. The result achieved 99.9% numerical accuracy against the reference implementation. That outcome, combined with Anthropic’s alignment with Rakuten’s responsible AI values, moved leadership to commit to a company-wide rollout. When Anthropic released Claude Managed Agents, Rakuten deployed specialist agents across product, sales, marketing, and finance within a single week, with each agent integrated into Slack and Teams to handle long-running tasks including generating spreadsheets, presentations, and functional applications.
The impact on development velocity became measurable quickly. Average time to market for new features fell from 24 working days to 5—a 79% reduction. Engineers run multiple Claude Code sessions in parallel, delegating separate workstreams simultaneously. Non-engineers who previously had no role in technical projects can now use Claude Code via the terminal interface to contribute to coding efforts with appropriate guardrails. Individual engineers report qualitative changes too: test-driven development, once uncommon, became natural because Claude Code generates comprehensive tests instantly and then builds features that pass them.
Rakuten’s next step is an “ambient agent” that breaks complex tasks into 24 parallel Claude Code sessions, each handling a different aspect of updating the company’s massive monorepo—work that would otherwise take more than a month to complete manually. The company frames this not as automating existing tasks but as multiplying what each team can achieve, with technical barriers no longer the limiting factor for innovation.