Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An experimental CLI from Sutro for building AI Functions over CSV, Parquet, and JSONL data. It finds uncertain rows, asks you to label them, and uses GEPA to improve the saved function definition.
How it uses Jev
Jev (or another decision backend) evaluates dataset rows against a typed question, producing binary, multiclass, multilabel, or score outputs with probabilities. jev-align uses the measured uncertainty to pick ambiguous rows plus an audit sample for human labeling, then feeds accepted labels to GEPA.
Primitives:choicescore
Technique worth stealing
Use model uncertainty to select which examples humans should label, then optimize the function definition with GEPA from accepted labels.
Try it
uv tool install jev-align; export TYPESAFE_API_KEY=...; run jeva
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 projectunclear0.43
- Shows a System One patternFound in material0.70
- Describes handling uncertaintyFound in material0.84
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.85
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.35 / 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 4 Nov 2026.