Automated TypeSafe AI Questionnaire Filling

梭哈.AI used JEV with DeepSeek V4.1 Flash to fill out TypeSafe AI’s application questionnaire from an unfamiliar URL. The author reports that it completed 16 questions in 38 seconds with no human intervention.

View on X time38 秒一次性刷完 16 道题

梭哈.AI@SUOHA_AI𝕏

太爽了！终于找到了JEV的最强应用场景之一--全自动化 Browser use 我用JEV全自动填完 TypeSafe AI 的申请问卷，我只给它丢了一个完全陌生的网址，让它全自动帮我完整填完：38 秒一次性刷完 16 道题，全程没停顿、零人工干预具体的逻辑是：我看到 @typesafeai 文档里一句话很有启发：“将 AI 与可靠的软件相结合，这样就可以在后台无限次地运行该系统，而无需人工干预。” 所以JEV最强的应用场景之一就是做全自动化！很多自动化慢得像幻灯片，就是因为把流程控制、视觉和思考全堆给大模型，大模型要思考推理，根本不可能跑得快我的解法很简单：用 JEV 专职负责判断，再搭配一个高速小模型推理（我用的是DeepSeek V4.1 Flash）👇 比如这个问卷填写：遇到新页面，由 JEV 毫秒级快速判定“这里该做什么”（是勾选、点击还是提交）；一旦需要填空，由小模型

Sep 20, 2026X postsView on X

The author describes JEV as quickly deciding what action to take on each new page, such as selecting, clicking, or submitting. They pair it with DeepSeek V4.1 Flash and cite a TypeSafe AI documentation passage about running AI systems reliably without human intervention.

Also filed under Agents & browsers

Evaluates Tool-Using Agents with Jev in CI
The project evaluates a real tool-using AI agent using code checks, a calibrated Jev judge, and an LLM judge. It is wired into CI.
Watchdog for AI Coding Agents
Jev Watch is a watchdog for AI coding agents that stops Codex or OpenCode when they loop, stall, or drift off task, then resumes the same session with a correction.
Fraud Investigation Agent
The author is building a fraud investigation agent using Jev and TigerGraph. Its flow goes from an alert through graph evidence, a Bayesian update, a pattern, Jev’s extra lookup, policy, a verdict, and human approval.
Coding-Agent Runtime Using Jev Decisions
Distill is a coding-agent runtime that uses Jev decisions for model routing, context retention, and tool selection.