Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jevon turns customer feedback into typed operational decisions. It is for developers and analysts who need inspectable, bounded judgments rather than generated text, exposing model probabilities and the rules that convert them into actions.
How it uses Jev
One review becomes a shared state. Jev evaluates 19 typed questions (8 Noul, 9 Score, 2 Choice) via AsyncTypeSafeClient.system_one. Backend code applies mention gates and deterministic thresholds to the returned probabilities to produce aspect ratings, sentiment, topic, urgency, churn risk, and escalation recommendations.
Primitives:choicescorenoul
Technique worth stealing
Use one shared semantic state with many typed questions, then apply explicit thresholds in ordinary code to turn probabilities into actions.
Try it
Open the hosted app or run locally with Vite proxy to port 8000; set TYPESAFE_API_KEY in Python backend.
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 material0.94
- Describes handling uncertaintynot found in the excerpt0.33
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.78
- Top-10 learning shortlist signalunclear0.47
- Is a replica of the modelnot found in the excerpt0.23
- Solves a common problem (0–2)score on a 0–2 scale1.57 / 2
- About JevFound in material0.97
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 6 Oct 2026.