Routing 72 synthetic support tickets: Jev scored 93% for department, 85% for urgency, and 99% for refund detection; Laya scored 58%, 63%, and 74%, recognizing only 1 of 12 safety tickets.
Then I tried something much narrower: route 72 synthetic support tickets. Jev got 93% for department, 85% for urgency and 99% for refund detection. Laya managed 58%, 63% and 74%. Worse, it recognized only 1 of 12 safety tickets.
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.
