Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
JEV Guard is a configurable guardian for company AI agents. Before an agent sends email, launches campaigns, modifies CRM, or publishes content, it decides in milliseconds whether the action is safe. Doubtful cases go to an LLM; critical ones to a person.
How it uses Jev
JEV evaluates typed questions about the proposed action and its context (agent, action type, task, recipient, purpose) to produce a fast, calibrated judgment. The verdict (allow, block, hold) is returned to the calling agent, which obeys it. Rules handle exact cases; JEV handles quick judgment; an LLM or human handles uncertainty.
Primitives:choicescorenoul
Technique worth stealing
Three-layer decision: code rules for exact matches, JEV for fast judgment, LLM or human for doubt.
Try it
python -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt && python scripts/demo.py
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 material0.90
- Shows a System One patternFound in material0.86
- Describes handling uncertaintyFound in material0.90
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.79
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.90 / 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 18 Oct 2026.