Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A tutorial for engineers integrating TypeSafe Jev jev-1.14.0 into business code: API key setup, first request, four question types, parallel fan-out, image box localization, long context, confidence thresholds, and troubleshooting.
How it uses Jev
Jev evaluates typed questions (noul, choice, score, box) in parallel over a state string or object and returns calibrated probabilities. The guide shows routing tickets by combining noul probabilities with choice/score confidence, and gating box results with a paired noul.
Primitives:noulchoicescore
Technique worth stealing
Fan out many atomic questions over one state, then threshold on confidence (or abs(2p-1) for noul) to auto-execute, audit, or escalate.
Try it
Set TYPESAFE_API_KEY and POST to https://api.typesafe.ai/v1/systemone with model jev-1.14.0, state, and questions.
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 material0.96
- Shows a System One patternFound in material0.95
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolunclear0.46
- Top-10 learning shortlist signalFound in material0.74
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 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 28 Oct 2026.