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
Jev Lab is a Python web app with eight demos and a Workbench for experimenting with TypeSafe's Jev model, aimed at developers who want to see how typed questions and calibrated probabilities drive application logic.
How it uses Jev
Jev answers typed Choice, Score, Noul, and Box questions over supplied state (text, JSON, images). Demos and Workbench send these requests via the TypeSafe SDK, then use returned choices, scores, and probabilities in local code for routing, thresholds, and policy decisions.
Primitives:choicescorenoul
Technique worth stealing
Compose atomic judgments with code-owned weights, thresholds, and policies so reweighting and replanning run locally without another model call.
Try it
Run `uv sync --locked` then `uv run --locked server.py`, open the browser, and connect a TypeSafe API key.
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 material0.95
- Shows a System One patternunclear0.47
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalFound in material0.61
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.11 / 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.