A Jev draft checker went silent and stalled the whole pipeline
The author put Jev between GPT and themselves to block rule-breaking drafts, but the agent chose silence and stopped sending anything, requiring a second agent to unstick it; they list four ways to handle the silent branch.
it's f*cking insane Jev sat between GPT and me, killing every draft that broke my rules before i saw it. good setup. then Jev did not answer. the agent decided silence was safer and stopped sending me anything at all. took a second agent to unstick it. your checker needs a branch for the moment it goes quiet: > let it through tagged unverified and keep moving > hand the risky span to the big model > park it in a queue and retry in a minute > wake a human when the action is irreversible 70-500 ms one Jev call, by TypeSafe's own number. a half-second checker still takes down the whole pipeline when it has no default.
This post quotes another post: “Jev model answers structured questions in parallel in 0.114 seconds”