用 Jev 判定给 agent 轨迹做可命名「嵌入」

Annabell @annabellschfr原推发布于 2026.09.26

在 X 上打开原推

you can use Jev judgments to build your own “embedding” of agent traces where every dimension has a name. E.g. conversation signals from chat agents: [user_frustrated, follow_up, corrected_agent, satisfied] [0.7, 0.8, 0.1, 0.0] Now you can cluster or search sessions like “frustrated users who had to correct the agent,” and see exactly why each one matched. Works both ways too: search for the happy users. Just as important to see what’s going right :)

这条是引用着另一条写的：x.com/annabellschfr/status/2102799529074459025