Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-driver is a Rust crate that turns TypeSafe AI's Jev decision model into typed Rust: option sets become enums, rubrics become enum variants, and probability thresholds become methods. It targets Rust developers building strict, validated decision pipelines.
How it uses Jev
Jev answers choice, score, and noul questions about a JSON state. jev-driver derives Rust types for the state and questions, builds a Decision, sends it via JevClient, and returns typed answers with selected enums, ProbabilityMap, Confidence, and score accessors. Results drive match arms and threshold checks like confidence.act(0.80) or probability.yes(0.50).
Primitives:choicescorenoul
Technique worth stealing
Derive macros turn option sets, rubrics, and thresholds into Rust enums and methods, with strict validation rejecting unknown keys, missing criteria, and unnormalized distributions.
Try it
Add jev-driver = "0.1" to Cargo.toml; run the testapp demo with make red (offline) or make live.
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 material0.99
- Shows a System One patternnot found in the excerpt0.30
- Describes handling uncertaintynot found in the excerpt0.15
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 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 23 Oct 2026.