Moving the agent routing layer to Jev fixes production failures
The same agent task that passed in 41 seconds in a scripted demo looped through 8 sub-agents, 12 tools and 10 retries in a real repo; handing routing to Jev let it pick tools step by step, stop loops at retry 3, and escalate to a human only when state was truly ambiguous.
a chinese dev just used JEV to kill the "demo works, prod fails" problem every agent builder is quietly dying from run A: scripted agent, task is "add pagination to /orders", 3 steps, 14/14 tests pass, done in 41 seconds. run B: same agent, same task, no fixtures, real repo. 8 sub-agents, 12 tools, 10 retries, 780 frames later. TESTS looping, DOCS stalled, REVIEW stalled, APPROVAL waiting on a human. internal adoption 97.9%. external adoption 0.7%. that gap is where every agent demo on this planet dies. the first version let the main agent pick its own route through 12 tools and ask for human approval every third step. then he moved the routing layer to Jev. now Jev picks the next tool at every step, kills loops at retry 3, and only escalates to a human when the state is actually ambiguous. no fixtures. no scripted path. real repo. the agent finishes. I pulled the exact routing policy he used and it reads less like a prompt and more like an on-call runbook. full breakdown in the article below ↓
This post quotes another post: x.com/0xricker/status/2102396090012115030