Jev-Powered Deal Alert Platform
Leeco built a deal-subscription platform using Jev to match Chinese e-commerce deal posts against users’ product and price criteria.
Leeco@leecobaby𝕏
我拿 @typesafeai 的 Jev 去读了中文互联网最脏的一批文本:电商线报。 顺手做了个线报订阅平台。 场景特别简单。你就想囤点抽纸,或者等一箱可乐降到 40 以内。 但线报群一天刷几百上千条,你要么全翻,要么错过。 现在你只说一句「我要什么、多少钱以内」,剩下的它替你守。 跑了一轮真实进件: 267 条线报 × 每条 15 个判断 = 4005 次判断 延迟 p50 724ms,最快 515ms 全程花了 $0.0206 结果是每个订阅者平均只收到 10 条, 其余 96% 的刷屏他根本不用看见。 63.3% 的线报,它谁也不推。 做过推送的都懂——不打扰,比推得准难多了。 视频是实机,里面每个数字都是真跑出来的。 也许很快上线,感兴趣的话我会陆续放细节 👇
In a test of 267 deal posts with 15 judgments per post, subscribers received an average of 10 alerts each. The system sent no alert for 63.3% of posts.
Also filed under Triage & routing
- Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using Jev AI. It is designed to speed up agent loops by routing decisions without relying on large generative LLMs at every step.
- Local Candidate Scoring with Jev
Bev performs local Jevfire-style candidate scoring using ternary models and a System One API. Its probabilities are candidate-relative.
- Team Agent Workspace for Routing and Model Selection
Agentconnect is a team agent workspace that uses Jev typed decisions for response routing and model selection.
- Desktop AI Assistant with Jev Plugin
PyGPT is a desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.