Automated README summary
Automatically summarized from the README on 9 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A live comparison board for developers evaluating TypeSafe Jev and OpenAI Decisions on the same support ticket. It scores price, correctness, and latency so both APIs can be seen answering the same case side by side.
How it uses Jev
Jev answers labeled text-only support tickets using System One (text only). The app sends questions to Jev via POST /v1/systemone, then uses the returned probabilities for choice exact match, boolean at 0.5 plus Brier, and score rounded to the nearest gold level in the scoreboard.
Primitives:choicescore
Technique worth stealing
Score both APIs on the same labeled tickets and rank by accuracy, allowing ties.
Try it
git clone, npm install, cp .env.example .env.local, npm run dev, then add keys.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 projectunclear0.46
- Shows a System One patternunclear0.52
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolnot found in the excerpt0.17
- Top-10 learning shortlist signalnot found in the excerpt0.25
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
- About JevFound in material0.98
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 9 Oct 2026.