quality_assurance · workflow

Mercari Readability Team uses Claude to automate PR complexity classification and code review at scale

As development intensified and PR volume surged due to team growth and AI Agent adoption, the Readability Team could no longer manually review all Pull Requests using conventional methods.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Claude classifies PR complexity
Claude automatically classifies Pull Requests by complexity and size and adds labels.
Tools used
ClaudeSQL FluffgRPCProtocol Buffer
Outcome

Claude automates PR complexity classification and code review, allowing the team to prioritize high-complexity reviews and freeing human reviewers to focus on higher-level design and architecture decisions.

Source

https://engineering.mercari.com/blog/entry/20251021-scaling-code-quality-modular-monolith-readability-team-ai-era/

How we source this →

Grounding & classification
Source type: technical build writeup
20 fields verified against source quotes.
document classificationquality inspectioncode diff prfailure mode describedhuman review describednamed customerproduction runtime claimedtools describedworkflow describedecommerceemployee productivitytechnical build writeupquality assuranceextract classify routehuman review queue