Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A CLI and MCP server for triaging Spanish-language data-treatment policies and terms (Colombia Ley 1581). It normalizes clauses deterministically without AI, then classifies each clause and routes low-confidence cases to a human review queue.
How it uses Jev
For each normalized clause, Jev receives a self-contained mixed request: choice classifies the clause as obligacion, riesgo, or sin_accion, and score places severity on an ordered 0–2 scale, each with confidence. The pipeline buckets the clause and sends it to human review if either confidence is below 0.8 (fail-open).
Primitives:choicescore
Technique worth stealing
Embed each clause self-contained in its Jev questions, chunk to respect context budget, and fail-open to human review when confidence < 0.8.
Try it
pip install jev-norma, set TYPESAFE_API_KEY, then run jev-norma politica.html --sample 12.
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 material0.94
- Shows a System One patternFound in material0.78
- Describes handling uncertaintyFound in material0.78
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.88
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.14 / 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 28 Oct 2026.