Automated README summary
Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
JevShield is an npm workspace providing a headless SDK, a Tauri v2 + React desktop IDE, and a cloud gateway for teams building on TypeSafe AI's Jev decision engine.
How it uses Jev
JevShield wraps Jev to answer typed Choice, Score, and Noul questions over an enriched state. It injects an adversarial Noul question into the same round trip for injection defense, validates limits before requests, and renders decisions to deterministic prose without a model call.
Primitives:choicescorenoul
Technique worth stealing
Inject a parallel adversarial Noul question into the same Jev round trip to detect prompt injection at the cost of one extra answer.
Try it
npm install @jevshield/core, then call shield.decide({ state, questions }) with 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-1.13.0- 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 material0.85
- Shows a System One patternFound in material0.68
- Describes handling uncertaintyunclear0.41
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.59 / 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 27 Sept 2026.