Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A free, hands-on guide plus a Claude skill and four editable recipes for using TypeSafe's Jev model on marketing ops decisions like lead routing, reply triage, on-message checks, and asset tagging.
How it uses Jev
Jev answers typed questions (choice, score, noul) on text state such as leads or replies, returning probabilities and confidence. The batch script calls the TypeSafe API, writes answers with confidence bands and a row_action to CSV, and thresholds route results to auto, review, or human.
Primitives:choicescorenoul
Technique worth stealing
Confidence-gated routing: act automatically only on high-confidence answers, send lower-confidence ones to review or human.
Try it
Run python3 scripts/jev_batch.py recipes/lead-routing.json ../examples/sample-leads.csv --dry-run
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.29
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.42
- Top-10 learning shortlist signalunclear0.55
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 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 28 Oct 2026.