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 dependency-free Java 21+ client for TypeSafe AI's Jev System One model, letting Java developers send state plus typed questions and receive typed answers with calibrated confidence they can act on directly.
How it uses Jev
Jev answers Choice, Score, Noul and Box questions over a state map in one request. Code reads typed answers via response.choice/score/noul/box, gates on isConfident(threshold) or isTrue(threshold), and escalates low-confidence cases to a human or bigger model.
Primitives:choicescorenoul
Technique worth stealing
Run Jev on everything, then escalate only low-confidence answers to a person or larger model using measured thresholds.
Try it
Build from source with ./gradlew jar, then use JevClient.fromEnvironment() with TYPESAFE_API_KEY set.
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 material0.98
- Shows a System One patternFound in material0.81
- Describes handling uncertaintynot found in the excerpt0.12
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 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.