An MCP plugin that scores a coding agent’s work while it runs.
Niaz Morshed built jev-review, an experimental, local-first MCP plugin. Coding agents call Jev while they work, get a score on several quality metrics, improve the code, and repeat.
A frustrated customer hits a bot loop twice; the judge checks whether a human handoff was offered.
ResourceTools & apps
An agent cancels a subscription; the judge checks the exact date the cancellation takes effect.
ResourceTools & apps
An agent quotes $29/seat against a price list; the judge checks the quote matches exactly.
ResourceTools & apps
A support agent issues a $42.50 refund; the judge checks the exact amount was stated before the refund was confirmed.
ResourceTools & apps
built `jev-review` @typesafeai it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
