Data labeling with decision models

CSV-to-dashboard app that charts columns automatically and optionally has Jev read every row for insights columns cannot answer.

Native macOS menu-bar app and CLI that fills Notion database properties with Jev judgments, sending uncertain rows to review.

Python library that packs many items into each Jev request for bulk yes/no classification and raises on any unanswered item.

pandas and Polars .jev accessor for classifying, sentiment-scoring and grading DataFrame rows with Jev probabilities.

CLI that scans tabular, structured and text files or databases and asks Jev which fields look anomalous, building a review queue.

Browser CSV workbench that runs up to 20 user-defined Jev questions against selected rows, with a privacy-first proxy design.

Pipeline that audits and refines topic-model clusters by checking each document against its topic label with a zero-shot decision model.

Workbench where Jev sorts training records into keep, review or reject, then trains LoRA adapters and evaluates them.

Toolkit that turns Laya into a task specialist: LLM-generated and verified training data, RLCD training, calibration and longer context.

CLI and Claude Code skill that turns one typed decision into a fine-tuned, calibrated, evaluated Laya checkpoint you can serve.

Open-Jev: open typed-decision models (2B, 9B, 27B v1.1) returning candidate probabilities without generation, with a no-code workbench.

Jag: Jev-inspired Qwen3.5-0.8B model that predicts a visual-grounding box in one forward pass, about 20x faster than its base.

Jev-curated list of Jev projects: each repo is judged by Jev for relevance, category, pattern and quality, and code applies the policy.

Rust streaming filter that keeps or rejects JSONL and Parquet dataset rows using Jev Noul checks and confidence scores.

Bilingual site cataloguing 500+ open-source Jev projects, gated by Jev itself, plus sixteen design patterns from real code.

Web tool that analyses Telegram channel JSON exports locally for intent, quality, sentiment and speaker tone with Jev.

elvex blog on wiring Jev into an agent harness as a tool for search, approvals and context, citing 2,000 expense reports in 20 seconds.

classifier.dev: free zero-shot classification HTTP service built on Jev, with no API key or account and an agent skill.

DuckDB extension that labels rows in CSV, Parquet or DuckDB tables with Jev, reported at about ten seconds per thousand rows.