Compare the changed files with the original task. Watch for unrelated refactors, formatting churn, dependency edits, or generated files that were not part of the request.
Which files changed outside the original task, and why were they necessary?
AI Workflow Tools
AI Code Review Checklist
Review AI-generated code changes from Cursor, Claude Code, Codex, Copilot, Windsurf, ChatGPT, Lovable, Bolt, or Replit Agent before merge or deploy.
8 review checks generated
Run or manually test the path that existed before the AI edit. AI agents can satisfy the new request while quietly breaking old empty states, filters, redirects, or permissions.
What existing user flow could this patch break, and how did you verify it?
Name the command, browser path, API request, or manual checklist that proves the change works. If no automated tests exist, keep the manual gate explicit.
What exact command or manual workflow should fail if this change is wrong?
AI-generated code often handles the happy path but misses loading, empty data, failed requests, double submits, expired sessions, and retries.
Which empty, loading, failed, and retry states does this patch handle?
Check localStorage, cookies, cache keys, feature flags, query params, and persisted preferences so existing users do not get stuck after the AI edit.
Did any persisted state shape, cache key, or cookie contract change?
Search for hardcoded tokens, service keys, webhook secrets, debug flags, and server-only env vars accidentally moved into client code.
Which env vars are required, and are any private values exposed to the browser?
Review request shapes, response fields, status codes, CORS, auth headers, pagination, retries, and how errors surface to the caller.
Which API contract changed, and what existing caller might depend on the old shape?
Check narrow viewport overflow, clipped controls, keyboard focus, labels, button names, contrast, and whether generated UI text fits in its container.
What happens on a 360px wide screen and with keyboard-only navigation?
This tool is part of AI Workflow Tools. View the full workflow · AI Coding Workflow Checklist Before You Ship
About this tool
The AI Code Review Checklist is a local review workspace for AI-generated code changes from Cursor, Claude Code, Codex, GitHub Copilot, Windsurf, ChatGPT, Lovable, Bolt, Replit Agent, and similar tools.
How to use this tool
Select the AI tool, change type, impact areas, and review strictness. Add a short change summary or file list, then work through the generated review gates.
- Choose the source of the AI change and whether it is a feature, bug fix, refactor, UI change, dependency change, security edit, or deployment edit.
- Select impacted areas such as frontend, backend, database, auth, payments, API, i18n, SEO, mobile, tests, and docs.
- Use the generated checks to review scope, behavior, security, data, dependencies, mobile layout, tests, deployment assumptions, and handoff notes.
- Copy the Markdown review note into a pull request, issue, code review, or the next AI coding prompt.
Features
The tool does not scan your repo or call an AI model. It turns explicit context into review gates and follow-up questions you can use locally.
- Review gates for real AI coding tools: Cursor, Claude Code, Codex, Copilot, Windsurf, ChatGPT, Lovable, Bolt, and Replit Agent.
- Conditional checks for auth, payments, database migrations, API contracts, i18n, SEO, mobile layout, dependencies, and deployment.
- Follow-up questions to ask the AI before merging, deploying, or continuing with another agent.
- Markdown export with checked items and evidence notes.
FAQ
How do I review AI-generated code?
Start by checking whether the changed files match the original task. Then verify existing behavior, risky areas such as auth or data, tests or manual gates, and deployment assumptions before you merge or deploy.
Does this tool automatically inspect my code?
No. It is a local checklist and review note builder. You choose the change type and impact areas; the tool generates review gates and follow-up questions without uploading files.
Can non-developers use it for vibe coding?
Yes. Choose Lovable / Bolt / Replit Agent or ChatGPT as the source, then focus on changed files, visible behavior, env vars, deployment, and concrete verification steps.