Automated README summary
Automatically summarized from the README on 2 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A hands-on comparison of TypeSafe AI's Jev and an LLM with structured outputs on the same decision: should an expense claim be approved, rejected, or need clarification? Includes code, 30 test claims, raw outputs and terminal logs.
How it uses Jev
Jev answers typed questions about the claim state. In Round 3, it answers 7 yes/no questions in one call (e.g., 'Alcohol, personal item, gym, gift or fine?'), and plain code applies the policy rules to produce approve/reject/needs_clarification.
Primitives:choicenoul
Technique worth stealing
Ask narrow yes/no questions and let code apply the rules, rather than one big question.
Try it
Run compare.py with the provided cases.csv and API 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 projectFound in material0.71
- Shows a System One patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersFound in material0.95
- Is a runnable toolnot found in the excerpt0.08
- Top-10 learning shortlist signalunclear0.57
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale0.82 / 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 2 Oct 2026.