The author built a real-time chat moderator with Jev that detects thousands of variations and spellings of bad words across multiple languages, noting its extremely low price.
I created a real-time chat moderator with jev. It can detect thousands of variations and ways of spelling a bad word, even in multiple languages—so while a script based on specific words doesn't work 100%, jev solves the problem at a ridiculously low price.
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.
