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 cookbook of fifteen runnable Node scripts with small labelled datasets and measured results, showing developers how to apply TypeSafe's Jev decision model to real jobs like support triage, tagging, dedupe, PII scanning and a browser agent.
How it uses Jev
Each recipe builds a trimmed JSON state from the item, then asks Jev Choice, Noul and Score questions in one call. Code owns thresholds and actions, routing low-confidence answers to human review.
Primitives:choicenoulscore
Technique worth stealing
Ask all questions in one call, then keep thresholds and routing decisions in your own code.
Try it
npm run quickstart, then npm run 01 or npm run all.
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 material0.96
- Shows a System One patternFound in material0.90
- Describes handling uncertaintyFound in material0.75
- Reports measured numbersnot found in the excerpt0.20
- Is a runnable toolunclear0.56
- Top-10 learning shortlist signalFound in material0.81
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.70 / 2
- About JevFound in material0.99
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.