Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A learning project and eval harness for TypeSafe AI's System One models, comparing Jev against mock and LLM stand-ins across 24 operational decisions in four domains: CI triage, checkout risk, dunning retries, and Dependabot PR review.
How it uses Jev
Jev is invoked as a function call: a JSON state plus atomic questions (noul/choice/score) are POSTed to /v1/systemone, returning typed answers with probabilities. The project's own decide() code uses those probabilities with thresholds and confidence gates to choose actions.
Primitives:choicescorenoul
Technique worth stealing
Batch many independent atomic questions in one call; use confidence as a second decision axis for gating actions.
Try it
nvm use && npm install && npm test; npm start -- --compare
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 projectFound in material0.80
- Shows a System One patternnot found in the excerpt0.17
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersnot found in the excerpt0.22
- Is a runnable toolnot found in the excerpt0.09
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelnot found in the excerpt0.30
- Solves a common problem (0–2)score on a 0–2 scale0.52 / 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 6 Oct 2026.