Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A TypeScript project that rebuilds Loopfour Studio features—workflow building, document extraction, classification—using Jev (TypeSafe's System One model) instead of an LLM, with a live race comparing Jev to claude-opus-5 and OpenAI Decisions.
How it uses Jev
Code finds candidate answers (amounts, dates, labels, block names) from the document or description; Jev picks one typed answer per question with a calibrated probability. Low-confidence answers go to a person. Code copies each value verbatim into the result, keeping its source line for the audit trail.
Primitives:choicescore
Technique worth stealing
Code finds candidates, Jev picks with calibrated confidence, code assembles verbatim—so values cannot be invented.
Try it
POST to https://l4-jev-workflow-builder.vercel.app/api/extract or /api/classify with a Jev key.
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 material0.91
- Shows a System One patternFound in material0.92
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.71
- Top-10 learning shortlist signalunclear0.53
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.83 / 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 13 Oct 2026.