Kalmia 用 Jev 筛选 agent 长跑日志中值得分析的关键步骤

Calvin Huang @calvinhhuangg原推发布于 2026.10.08

在 X 上打开原推

Long-running agents can log thousands of steps per run. Analyzing every step to find what went wrong is slow and expensive. @kalmiadev has been experimenting with @typesafeai Jev to help choose which steps matter for our harness to analyze. Same bugs found on real customer runs, 9x cheaper and 6x faster. Try now http://kalmia.dev