Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Companion source code for the 'Mastering TypeSafe Jev' book, teaching Python developers to build fast, typed System One decision engines. It ships two capstone packages: a FinTech incident triage engine on hosted Jev and a SmartPlant industrial IoT engine on self-hosted Kev.
How it uses Jev
In Part I, a shared decision client sends a support/fraud payload's evidence state to Jev in one call, asking is_fraud_suspected (Noul), urgency_rating 1-5 (Score) and dispatch_target (Choice). The returned probabilities feed code that applies eligibility, fraud override, confidence gates, refund limits, circuit breaker and fresh-state verification.
Primitives:choicescorenoul
Technique worth stealing
Confidence-gated routing: treat Jev's calibrated probabilities as inputs to explicit policy code, not as final answers, with fallback and fresh-state verification.
Try it
Install uv, run uv sync, set TYPESAFE_API_KEY and JEV_MODEL, then uv run pytest -q.
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 material0.92
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolnot found in the excerpt0.28
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelnot found in the excerpt0.20
- Solves a common problem (0–2)score on a 0–2 scale1.73 / 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 4 Nov 2026.