jevbooks

← All projects

demo-shop

juanlacu/demo-shop

Demo Next.js shop showing Jev Review PR reviews.

Evaluation & Benchmarking0.64Runner-up: Verification & Guardrails
Automated README summary

Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A minimal Next.js shop (catalog, product page, cart, checkout) built to demonstrate Jev Review, a GitHub Action that reviews pull requests with TypeSafe Jev and comments on exact lines. Intended for developers evaluating Jev Review.

How it uses Jev

Jev Review runs as a GitHub Action on pull requests. For each changed file it reads the full file plus related files, then uses Jev's typed decisions in a pipeline: profile each file (Choice + Score), select evidence (Choice), classify bug mechanism (Choice), severity (Score), route to reviewer (Choice). Findings are posted as comments.

Primitives:choicescore

Technique worth stealing

Use typed decisions as small pipeline steps and keep thresholds and routing logic in code.

Try it

Add the workflow YAML, set TYPESAFE_API_KEY secret, open a pull request.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.87
  • Shows a System One patternunclear0.45
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.86
  • Top-10 learning shortlist signalunclear0.43
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale0.54 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.87Shows a System One pattern0.45Describes handling uncertainty0.05Reports measured numbers0.04Is a runnable tool0.86Top-10 learning shortlist signal0.43Is a replica of the model0.0300.51Solves a common problem (0–2)0.54 / 2012

no-judgment band (0.40–0.60)

Design patterns
Menu0.58Funnel0.2600.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 6 Oct 2026.