Automated README summary
Automatically summarized from the README on 17 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jevkit is a Python library for developers using TypeSafe Jev. It prepares state, composes typed questions, maps answers to act/confirm/escalate bands, and recalibrates bands from real outcomes, keeping application code in control.
How it uses Jev
Jev answers typed questions (Noul, Choice, Score) with calibrated probabilities. jevkit fans out questions over a shared state, then maps each answer's confidence to a band (act/confirm/escalate) via band() and DEFAULT_BANDS. Code uses bands, extracted choices, and resolved calls to decide actions, confirmations, or escalations.
Primitives:choicescorenoul
Technique worth stealing
Map calibrated probabilities to three confidence bands (act/confirm/escalate) instead of a single threshold, and recalibrate bands from logged outcomes.
Try it
pip install "jevkit @ git+https://github.com/tegersdorfer-collab/jevkit.git@v0.2.2"; set OPENROUTER_API_KEY or TYPESAFE_API_KEY; run the 60-second tour.
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 material0.92
- Shows a System One patternFound in material0.92
- Describes handling uncertaintynot found in the excerpt0.30
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.71
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.06 / 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 17 Oct 2026.