Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A demo command palette (⌘K) for a fictional mail app. It ranks 77 commands by meaning from Portuguese or English intent, side by side with a classic fuzzy matcher that fails on the same queries.
How it uses Jev
One Choice question per keystroke over the whole 77-command catalog as options. Jev returns the full probability distribution, which is used directly as the ranking. The selected command is then executed by deterministic code.
Primitives:choice
Technique worth stealing
Use the full probability distribution from a single Choice call as the ranking, avoiding embeddings and vector indexes.
Try it
npm install; cp .env.example .env; add TYPESAFE_API_KEY; npm run dev. Without a key, npm run dev:mock.
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 material0.97
- Shows a System One patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.67
- Is a runnable toolunclear0.50
- Top-10 learning shortlist signalFound in material0.75
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.15 / 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 20 Sept 2026.