Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A TypeScript library that routes classification requests to TypeSafe's Jev first and escalates to a System 2 (LLM, rules engine, or human queue) only when Jev is unsure, errors, or times out.
How it uses Jev
Jev answers a typed `choice` question over the input state, returning a label and per-label probabilities. If confidence clears `minConfidence`, the label is returned; otherwise, or on error/timeout, the request escalates to System 2 with Jev's attempt.
Primitives:choice
Technique worth stealing
Use Jev's calibrated confidence as a gate: answer locally when confident, escalate to an expensive model only when not.
Try it
bun install && bun test; run eval with TYPESAFE_API_KEY=... bun run eval:run
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 material0.93
- Shows a System One patternFound in material0.94
- Describes handling uncertaintyFound in material0.98
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolunclear0.52
- Top-10 learning shortlist signalunclear0.53
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.52 / 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 3 Nov 2026.