Automated README summary
Automatically summarized from the README on 24 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A local web app for people drafting messages to colleagues, managers, teachers, clients, friends, or family. It checks politeness, intent, expected reply, urgency, formality, emotion, and sarcasm, and supports A/B comparison. The interface is available in Chinese and English.
How it uses Jev
The app sends the draft text and fixed evaluation questions to Jev, which returns structured probabilities. These are used to generate goal checks and a full probability breakdown. Recipient presets and selected goals are local UI settings and are not passed to Jev.
Primitives:choicescorenoul
Technique worth stealing
Using fixed typed questions to get calibrated probabilities for communication signals, then applying local goal thresholds.
Try it
Install Bun and set AI_GATEWAY_API_KEY in .env.local, then run `bun run dev`.
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 material0.88
- Shows a System One patternnot found in the excerpt0.31
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.22 / 2
- About JevFound in material0.97
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 24 Sept 2026.