The author tries TypeSafe's judgment-focused AI Jev in customer support, noting its speed and accuracy, but warns that even near-perfect results include must-not-miss cases, so role division among Code, LLM, and Human matters.
Jevという「判定特化型AI」が出たので触ってみました！ お問い合わせ対応で使えそうか試すと、速いし結構当たる。 でも、ほぼ正解でも“外してはいけない1件”はある。 Jevに全部任せるより、Code / LLM / Humanとの役割分担が大事そう。 記事はスレッドに👇
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.
