What it is
Stanley is a single-user prospecting and workflow assistant for a NetSuite account executive. It combines a hosted Next.js app with local, supervised sales workflows for TAM/TAL management, account research, missions, and pipeline tracking.
How it uses Jev
Jev interprets source evidence and guides account research. It ranks research and interprets changed sources, operating-topic matches, and saved research questions. Eligible findings publish to Triggered with source passage and preserved model judgments. Claude handles chat, cited account stories, and a separate legacy classifier.
Primitives:choicescorenoul
Technique worth stealing
Publish eligible Jev findings directly to Triggered with source passage and preserved model judgments, without a second-model review.
Try it
npm ci; cp .env.example .env.local; configure Supabase; npm run dev
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricunclear0.41
- Shows a System One patternno0.20
- Handles uncertaintyno0.06
- Measuredno0.03
- Runnableyes0.93
- Worth recommendingunclear0.44
- Model replicano0.08
- Problem scopescore on a 0–2 scale1.00
- About Jevyes0.94
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.