Automated README summary
Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A study POC for Jev (TypeSafe AI) that triages incoming WhatsApp messages for a fictional internet provider, classifying intent, urgency, frustration, refund requests, cancellation threats, and information sufficiency.
How it uses Jev
Jev receives the message as state and answers 6 typed questions in one call: intencao (choice), urgencia and frustracao (score), pedeReembolso, ameacaSair, informacaoSuficiente (noul). A deterministic TypeScript router uses the calibrated probabilities and confidence thresholds to decide: auto-reply, open ticket, or hand off to a human.
Primitives:choicescorenoul
Technique worth stealing
Fan-out speculative questions in one call, then route by confidence thresholds: higher cost of error demands higher confidence, money and cancellation never automated.
Try it
npm install; cp .env.example .env with TYPESAFE_API_KEY; npm run web
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 material0.92
- Shows a System One patternFound in material0.95
- Describes handling uncertaintynot found in the excerpt0.13
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolnot found in the excerpt0.23
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale0.78 / 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 28 Sept 2026.