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 collection of small, self-contained Python demos that place TypeSafe's Jev inside tools data and analytics engineers already use, such as DuckDB, dbt, and Databricks. Each demo is labelled live or simulated, with numbers from logged runs.
How it uses Jev
Jev returns typed judgments rather than text. In the demos it scores LinkedIn drafts across eight parallel judgments, evaluates plain-English predicates like jev_noul(body, 'asks for a refund') as typed columns in DuckDB, scores candidate charts against a query's intent, and judges dbt test sentences to catch wrong or PII-leaking rows.
Primitives:choicescorenoul
Technique worth stealing
Turning plain-English predicates into typed, filterable columns via Jev judgments, with weight sliders reweighting composites without new API calls.
Try it
Run each demo from its own folder; most work without a key in labelled SIMULATED mode, or set TYPESAFE_API_KEY in the folder's .env for live results.
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 patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.40
- Top-10 learning shortlist signalFound in material0.67
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.29 / 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 26 Oct 2026.