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 TypeScript library of decision gates for LLM pipelines: each gate asks Jev typed questions about an item and returns calibrated probabilities, letting your code own thresholds and fail-open/fail-closed policy. Built for developers filtering, ranking, or screening items in production.
How it uses Jev
Each gate sends one request per item to Jev with typed questions (Score, Choice, noul) over a small explicit state. A pure interpret function turns the answer set into a verdict (e.g. P(level ≥ 2)). Your code applies thresholds and the declared fail-open or fail-closed policy when Jev is unavailable.
Primitives:scorechoicenoul
Technique worth stealing
Replace free-text 'return indices to keep' prompts with typed probability questions, explicit numeric thresholds, and a declared fail-open or fail-closed policy.
Try it
npm install typesafe-gates @typesafe-ai/sdk; set TYPESAFE_API_KEY, then call a gate's run with createJudge.
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 material0.95
- Shows a System One patternFound in material0.88
- Describes handling uncertaintyFound in material0.84
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.88
- Top-10 learning shortlist signalFound in material0.66
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.51 / 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.