A paper on coding agents built around Jev's three decision primitives
The author turns the Jev approach into a paper: YES/NO for bounded gates, CHOICE for routing and SCORE for risk and quality, so the frontier model only handles work that needs reasoning.
i still don't understand why everyone is letting coding agents burn frontier-model tokens on every tiny f**king decision JEV fixes exactly this i turned the JEV engineering approach into a research paper on how to build coding agents around typed decision loops instead of asking the big model to reason about everything, JEV handles the small repeated decisions with 3 primitives: YES / NO for bounded gates CHOICE for routing SCORE for risk, quality and relevance the expensive model stays focused on the work that actually needs reasoning the paper breaks down the full loop: routing, context, browser state, code review, verification, human approval and when the frontier model should actually be called one useful coding agent isn't just one giant model it's a system that knows when the expensive brain actually needs to think.
This post quotes another post: “Putting Jev in front of Claude Code for cost routing”