The author shares that introducing Jev into a Vane Data-built after-sales support audio pipeline significantly improved judgment accuracy, and notes Vane now supports vane.ai.jev(...) and Relation.jev(...).
最近 timeline 上看大伙都在讨论 Jev，这两天试了一下，效果还不错。在售后客服的音频处理场景中，基于 Vane Data 构建的 Pipeline 中引入 Jev，对于判断的成功率有着显著的提升。 BTW 我们也在 Vane 中飞速支持了 https://vane.ai.jev(...) 和 Relation.jev(...) 的用法 @kaka11chen
The author shares a Jev usage insight: it seemed tricky at first, but clicked when framed as 'not letting the AI write text.' Using inquiry handling as an example, the conventional approach dumps everything on GPT or Claude to analyze, while Jev takes a different approach.
The prototype uses AI to estimate hesitation or interest from cursor back-and-forth movements or lingering before clicking, observing customer demeanor and supplementing explanations or suggesting comparisons.
The author built an e-commerce real-time customer service demo using Jev and gpt-live-1, which instantly suggests recommended products based on the user's speech during a conversation, delivering a great experience.
