SpecCheck: review checklist for AI-written code

Move developers from line-by-line AI review to risk-tiered spot checks

Problem

Trust in LLM-written production code varies wildly: some review every line, some only read tests, some barely look. Threads repeatedly show "I review everything so I can't even use that many tokens" and "I'm not sure how much to trust it." Without a risk-tiered checklist, teams either over-review or miss critical defects.

Solution

A lightweight review companion: pulls the PR diff and generates a tiered checklist by code type (auth, payments, migrations, UI), flagging high-risk functions, missing tests, and suspicious error handling — then says "you only need to look at these three spots." Logs blind spots over time so teams build their own review policy.

Users

Full-stack/backend devs who accept AI-written code but don't fully trust it; tech leads at small teams

MVP

Pull GitHub PR diff; risk-rule checklist generation; highlight missing tests and error handling; mark reviewed/passed with audit trail; export a review record per file

Revenue

Free for public repos, paid monthly for private; team tier with shared review policies

Why now

AI coding is normal but review methodology isn't — teams want a practical 'trust tiering' tool, not another code generator