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.
Prototype of Real-Time Customer Service by Jev📝 From the cursor's back-and-forth movements or lingering before clicking, estimate hesitation or interest using AI. Closely observe the customer's demeanor and assess their state. Supplement explanations, suggest comparisons, or
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 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.
The demo uses AI to determine comment meaning and route live comments into Questions, Impressions, Requests, or Others, making it easy to grasp by running it.
