When asked where the ticket belongs, Jev returned billing at 0.84. When the question was changed to where the root cause could be fixed, the same ticket was classified as engineering. This shows how question phrasing affects Jev's analysis.
I sent it to jev with the question: "where does this ticket belong?" four options: billing, engineering, product, fraud. jev returned billing at 0.84. Then i changed the question. "where can the root cause be fixed?" same ticket, same four departments. jev returned engineering
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.
