jev-review (devagrawal09)
A staged code-review workflow and local dashboard built with TypeSafe Jev.
by @0xLogicrw
Overview
jev-review orchestrates a staged review pipeline in TypeScript and uses Jev for bounded judgments, presenting reports in a local dashboard on 127.0.0.1:4317.
Problem: Monolithic LLM code reviews are slow and non-deterministic compared to staged structured judgments.
Built for: Developers running local diff or full-repo reviews with a dashboard on localhost.
First indexed on Jev Directory: 2026-09-19
Creator and team
- Name
- Dev Agrawal
- Organization
- Independent
How Jev is used
- Role in the product flow
- Multi-stage code review and codebase scan judgments
- Primitives
- NoulChoiceScore
- State in
- Git diffs or discovered source files plus selected evidence hunks and test context per README workflow.
- Decision out
- Staged risk matrix, file profiles, evidence selection, mechanism classification, severity scores, and reviewer routing decisions.
- Noul risk matrix
- Choice + Score file profiles
- Choice evidence selection
- Choice mechanism classification
- Score severity
- Conditional Choice reviewer routing
The README documents an explicit pipeline where each stage is a focused Jev call type. Policy thresholds live in TypeScript, not in model prose. The dashboard binds to localhost and never serves .env files, which makes the tool suitable for experimenting with parallel questions before wiring CI gates.
Features and stack
Features
- review:changes and review:codebase modes
- Local dashboard with collapsible sections
- Requires Node.js 24+ and TYPESAFE_API_KEY
- Dependency-layer enforcement via scripts/check-dependencies.ts
Stack
- TypeScript
- Node.js 24+
- Git
- TypeSafe System One
Pricing: Uses TypeSafe API key from console.typesafe.ai per README.
Demo
Showcase clip with the same lightbox player as the homepage. Click to play.
Jev code review gate
A merge button that listens to parallel Jev questions instead of one giant LLM rant per file.
Links
FAQ
- How is this different from jev-codes?
- jev-review is a staged review dashboard. jev-codes audits diffs against YAML standards packs with per-hunk parallel calls.
Related learn guides
Original Jev guidance that pairs with this product pattern.
- Jev use cases
The patterns builders actually search for: moderation, routing, triage, RAG verify, and agent gates.
- Jev vs LLM classification
When to gate with System One probabilities instead of asking a chat model to label things.
Related products
Hand-picked neighbors with rich profiles or overlapping tags.