jevbooks

← All projects

jev-pii

senthilsweb/jev-pii · Homepage

Column-level PII discovery in DuckDB SQL with typed Jev answers.

Compliance & Legal0.61Runner-up: Data Labeling & CurationFail open, fail closedCheck-up
Automated README summary

Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A DuckDB SQL extension and browser SQL studio that profiles table columns to find personal data and applicable privacy regimes, for analysts and data engineers doing compliance discovery.

How it uses Jev

Jev answers typed questions per row or per column sample: a noul score for 'is it personal data?', a choice with per-option probabilities for the category, and one noul per regime (GDPR, CCPA, HIPAA, LGPD, PIPEDA, DPDP). Answers come back as extra columns; a plain-code policy maps them to keep/mask/hash/drop/review.

Primitives:noulchoice

Technique worth stealing

Ask a typed schema instead of parsing text: each answer becomes a filterable, joinable column, and a code policy (not the model) decides the action.

Try it

Open https://www.senthilsweb.com/jev-pii/ for the browser studio, or run the notebook via requirements.txt and jupyter lab.

View on GitHub

Start using Jev: API key and your first request →

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 material0.97
  • Shows a System One patternnot found in the excerpt0.33
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.89
  • Top-10 learning shortlist signalFound in material0.69
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.97Shows a System One pattern0.33Describes handling uncertainty0.03Reports measured numbers0.04Is a runnable tool0.89Top-10 learning shortlist signal0.69Is a replica of the model0.0500.51Solves a common problem (0–2)1.16 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.84Check-up0.81Funnel0.68Grey zone0.52Questionnaire0.44Traffic light0.3300.51

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 26 Oct 2026.