Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python demo that runs the Jev (TypeSafe System One) decision pipeline locally: customer support tickets go in, probability distributions come out, and thresholds split them into three action tiers. Includes terminal output and a single-file HTML report.
How it uses Jev
Jev makes decisions on ticket text state using Choice (intent/department routing), Noul (refund gate, guarded tool calls), and Score (combined with Noul for multi-question judgments). Results are calibrated probabilities; code applies thresholds (e.g., 0.85/0.55) to route to auto-execute, review, or human handoff.
Primitives:choicescorenoul
Technique worth stealing
Use option descriptions as a dictionary keyed by organizational truth, so the model can pick wrong but cannot invent non-existent values.
Try it
python run.py (offline); python run.py --live with TYPESAFE_API_KEY for real API.
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 material0.98
- Shows a System One patternFound in material0.78
- Describes handling uncertaintyFound in material0.66
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalFound in material0.77
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.48 / 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 3 Nov 2026.