TechnologySoftware Engineering

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.

Yusuke Kaji, General Manager of AI for Business

You can have five tasks running in parallel by delegating four to Claude Code while focusing on the remaining one.

Yusuke Kaji, General Manager of AI for Business

With Managed Agents, our power users become like Galileo, contributing across domains far beyond a single specialty or discipline.

Yusuke Kaji, General Manager of AI for Business

I didn’t write any code during those seven hours. I just provided occasional guidance.

Kenta Naruse, Machine Learning Engineer

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.

Diego Mateos, Senior Machine Learning Engineer

Our time to market has been significantly brought down because Claude Code gives us those super powers to make executions much, much faster.

Manoj Desai, Manager, AI Empowerment Section

Claude Code is not just a tool—it’s part of our AI journey.

Manoj Desai, Manager, AI Empowerment Section
Get the full context.

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.

Similar Cases

Z
Zapier
89%
ai adoption rate across all employees

Zapier deployed Claude Enterprise and Claude Code company-wide, achieving 89% AI adoption across all employees — the highest adoption rate in company history. The automation platform now runs 800+ internal AI agents and saw 10x year-over-year growth in Anthropic app usage. Adoption began grassroots before a formal rollout.

TechnologyCEClaude EnterpriseCCClaude Code
H
HubSpot
Up to 40%
productivity increase across web development and content creation

HubSpot is an agentic customer platform serving hundreds of thousands of companies worldwide, from startups to enterprises, with tools for marketing, sales, and customer service. The company deployed Claude and Claude Code across engineering, marketing, and customer success teams after benchmarking multiple AI tools and finding Claude required the least human intervention on real engineering tasks. The result was a 40% productivity increase across web development and content creation, and a drop in complex troubleshooting cycles from days to under an hour.

TechnologyCClaudeCCClaude Code
S
Sentry
1 million+
root cause analyses processed annually

Sentry is a software monitoring platform that ingests billions of events daily, giving development teams deep context to debug production issues. After deploying Claude for root cause analysis through their Seer agent, Sentry extended the workflow using Claude Managed Agents to generate merge-ready pull requests automatically — closing the loop from detection to fix without custom agent infrastructure. The result: over 1 million root cause analyses processed annually and reviews on over 600,000 pull requests each month, shipped by a single engineer in weeks instead of months.

TechnologyCMClaude Managed Agents
A
Anything
800,000+
apps created by users

Anything built a full-stack AI coding agent on Claude and the Agent SDK, enabling 1.5 million non-technical users to create production-ready software — from recruiting platforms to mobile apps — without writing a single line of code. In just five months, users shipped over 800,000 apps with a 91–96% agent success rate. Claude's reliable tool-calling, coding quality, and personality made it the clear choice for Anything's agent architecture.

TechnologyCAClaude Agent SDKCOClaude Opus 4.6
MF
Money Forward
80%
engineer adoption rate

Money Forward launched its MEPAR program to embed Claude Code across its engineering organization, achieving 80% engineer adoption with 70% using it daily. API endpoint implementation time fell from two days to five hours, and developer onboarding compressed from one week to one day. Early adopters reported saving approximately seven hours per week.

Financial ServicesTechnologyCCClaude Code
N
Notion
90%
infrastructure cost reduction via prompt caching

Notion is a collaborative AI workspace used by millions of people, from individuals to Fortune 100 companies, where teams organize knowledge, manage projects, and now delegate real work to AI agents. After deploying Claude to power AI writing, search, and database features across the product, Notion extended to agent orchestration using Claude Managed Agents — letting teams kick off dozens of concurrent tasks from a single board and receive finished deliverables, from code to client presentations. Prompt caching alone cut Notion’s infrastructure costs by 90% and latency by up to 85%.

TechnologyCMClaude Managed Agents
C
Classmethod
up to 90%
reduction in development time

Classmethod, a leading Japanese cloud integrator, deployed Claude Code across its engineering teams to address chronic developer shortages. The tool automated code generation, review, and testing workflows, reducing development time by up to 90% on specific tasks and cutting code review time by 80%.

TechnologyCCClaude Code
S
Slack
97 minutes
time saved per user per week via summarization and recap features

Slack partnered with Anthropic to integrate Claude's AI models into its platform, enabling intelligent search, conversation summaries, and automated recaps. The collaboration saves the average user 97 minutes per week while unlocking organizational knowledge across billions of daily messages and files.

TechnologyCClaudeCCClaude Code