At AIMUG, Joseph Fluckiger demonstrates using Jev to match repeated questions to a curated golden set of answers at runtime.
Same questions over and over? Joseph Fluckiger (@josephflu) matches them at runtime to a curated golden set of answers with Jev. #AIMUG https://youtube.com/watch?v=YPJd-RXsWI0…
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.
