Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026
Case study RakutenResults as reported by Anthropic

How Rakuten ran a seven-hour autonomous vLLM change with Claude Code

Rakuten engineers use Claude Code across the development lifecycle. In one test, it implemented a method in the open-source vLLM library in a single unattended run.

The problem

Rakuten wanted to scale AI-assisted development across thousands of developers without lowering quality. Earlier tools needed frequent human guidance and struggled with large, multi-language codebases.

How they did it

  1. Used Claude Code for unit tests, API mocks, components, bug fixes, documentation and code review.
  2. Ran several tasks in parallel by handing most of them to Claude Code while engineers worked on one.
  3. Had new team members use Claude to understand complex codebases and past architectural decisions.
  4. As a test, gave Claude Code an activation vector extraction task in vLLM, a library with 12.5 million lines of code.

Results as reported by Anthropic

  • As reported by Anthropic: 'Claude Code finished the entire job in seven hours of autonomous work in a single run.'
  • The implementation reached '99.9% numerical accuracy compared to the reference method'.
  • Time to market for new features fell 'from 24 working days to 5 days—a 79% reduction'.

These figures are as reported by Anthropic in Anthropic customer story ↗. Anthropic sells the product used here. AgentGid did not measure or independently verify them.

Takeaway. Hand well-specified, long tasks to the agent in parallel, and keep your own attention on the one task that needs judgment.
AgentGid's take

This suits teams with a mature codebase, good tests, and engineers who can write tight specs and review large diffs, since the unattended run only helps if someone can verify the output. Note that the 7-hour, 99.9% accuracy, and 79% figures are vendor-reported by Anthropic, and Claude Code needs a paid plan (from $20/mo). Pi (Free, OSS) is a cheaper terminal alternative, though you pay model costs.

The agent used here

Similar use cases

Guides