Can you trust it when AI says "it's done"?

@TiedGST 泰德搞薯条 TD · Sep 21, 2026 · case #630517 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Built Foreman, which uses Jev to continuously check whether a coding agent has drifted, stalled, or finished.

The original post, translated

Can you trust it when AI says "it's done"? This project gives the Coding Agent a supervisor. The project is called Foreman. Codex / OpenCode is responsible for writing code, while another model, Jev, continuously checks nearby: whether it has gone off track, whether it is stuck, whether there are enough tests, and whether the requirements are actually finished, and then the program decides the next step according to the rules. Core highlights: 1️⃣

Show the original post in its source language ▾

AI 说“写好了”就能信？这个项目给 Coding Agent 配了个监工。项目叫 Foreman。Codex / OpenCode 负责写代码，另一个模型 Jev 在旁边持续检查：有没有跑偏、是不是卡住、测试够不够、需求到底做完没有，再由程序按规则决定下一步。核心亮点： 1️⃣

The post above is a machine translation from zh; the untranslated text is in the fold-out.

Engagement when collected

Likes2

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under agents & workflows, coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.

🤖 Agents & workflows 🛠️ Coding & developer tools