How to Review AI-Written Code: Lessons From the Claude Code Team and Hacker News

Description and use

Reviewing AI‑written code is effective when design is controlled upfront and verification is automated. Claude Code’s seven‑step pipeline—AI review, security checks, linters, and risk‑based human approval—reduced review rounds, increased pass rates, and improved code stability.

Problem

Reviewing AI‑written code is hard because line‑by‑line human review does not scale and automated tests can miss shared blind spots.

Outcome

The pipeline reduced review iterations, increased PR pass rate, lowered revert rates, and doubled merged PRs while maintaining code stability.

Workflow

• 1. Agent runs tests, build, and linter locally before PR creation.
• 2. Fresh‑context subagent reviews the diff against the repo and PR intent.
• 3. Automated security review runs; PR cannot merge if any finding remains.
• 4. Blocking automated checks (lint, type, tests, build) run on every PR.
• 5. Human approval scaled by risk tier (low, medium, high).
• 6. PR enters merge queue with feature flags and gradual rollout.
• 7. Feature flags enable fast rollback and weekly on‑call monitoring.

Evidence

The share of pull requests passing after just one review and fix round increased from 65% to 78%. Pull requests requiring five or more rounds dropped from 8.9% to 1.5%.

Source

The first layer verifies the work before anyone else looks at it. Claude runs tests, the build, and the linter and shows the output.

Source

The same Tokely API key also accesses OpenAI and Google models, such as GPT-6.1 Sol and Gemini 4 Argon, through the OpenAI-compatible Chat Completions endpoint.

Source