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 Portuguese-language live sales copilot for reps. It analyzes each utterance of a call and updates close probability, call stage, next best play, open objection, live signals, and an optional personalized phrase.
How it uses Jev
On each utterance, the app sends about 37 typed objective questions to Jev in one request. Jev returns calibrated probabilities for close likelihood, stage, play, objection, and signals. All math (probability, averages, talk ratio) is done in code in copilot/engine.py.
Primitives:choicescorenoul
Technique worth stealing
Batch ~37 typed questions per utterance into one Jev request, then compute all aggregates in code.
Try it
Clone, set OPENROUTER_API_KEY in .env, run iniciar.bat (Windows) or ./run.sh, open http://localhost:8000.
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 material0.97
- Shows a System One patternFound in material0.98
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersunclear0.43
- Is a runnable toolFound in material0.67
- Top-10 learning shortlist signalFound in material0.63
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 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.