CoreWeave 推出 Agent Lens,自动归因智能体失败对话
CoreWeave 出了个 Agent Lens,专门查智能体哪些对话跑错了,还会把同类失败自动归组,做 agent 的可以看看。
CoreWeave 发布 Agent Lens,用于排查生产环境中智能体的失败案例。官方示例中一个智能体一夜处理 40,000 次对话,其中 230 次出错,工具会记录这些对话的 traces。它不抽样,而是读取全部生产语料,把失败模式相同的对话自动分组,即使措辞和工具调用顺序不同也能归到一起,并将每组关联到可查证的 traces。
Your agent handled 40,000 conversations overnight. 230 went wrong. No alarm. All 230 reached customers.
That is why CoreWeave Agent Lens exists.
Log your agent's traces and it reads the entire production corpus, not a sample.
It groups the conversations that fail the same way, even when the wording or the tool sequence differs, and links each group to the traces that prove it. https://t.co/PV6xPvbj57