devwithjev
— reading now— views
Submit a build

Jev Selects Coding Candidates for Codex

The creator connected Jev to Codex, with Codex researching and fixing code while Jev decided which candidate to pursue. They organized code across four projects and checked that it worked after Jev’s decisions.

伊藤貴將(いとぱん)|AIエージェント×創作開発@takamasa045𝕏
話題のJevをCodexにつないで、何ができるか試してみた。 調べて直すのはCodex。 「どの候補から進める?」を判断するのがJev。 映像制作ツールや会員サイトなど、4つのプロジェクトでコードを整理。判断を受け取ったあとに、ちゃんと動くか確かめるところまで。 AIを増やすだけじゃなく、仕事を分けるとどうなるか。 その実験を28秒の動画にしました👇
Sep 18, 2026X postsView on X
The projects included a video-production tool and a membership site. The creator presented the experiment in a 28-second video about dividing work between AI agents.

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.

  • Custom Agent Harnesses with Jev

    Elvis uses Jev to build custom harnesses and reports success with guardrails, routing, and verifiers.

  • 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.