Automated README summary
Automatically summarized from the README on 26 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A test harness that screens a store's product catalog for goods that are illegal or problematic to sell in a given country, using TypeSafe AI's Jev evaluation model through the Vercel AI Gateway.
How it uses Jev
Jev takes one state per product (market, regulatory notes, product details) and answers five typed questions: prohibited, restricted, platformRisk (boolean), category (choice), severity (score 0–3). The returned probabilities feed a tunable threshold rule that outputs a verdict: prohibited, needs_review, restricted, or allowed.
Primitives:choicescorenoul
Technique worth stealing
Use Jev for bulk screening by combining a shared state with multiple typed questions in one call.
Try it
pnpm install; cp .env.example .env; add Vercel AI Gateway key; pnpm classify --country DE
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 material0.95
- Shows a System One patternFound in material0.81
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersFound in material0.72
- Is a runnable toolunclear0.41
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.26 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
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 26 Sept 2026.