The store has evolved from "configuring automatic replies"
Described how e-commerce shops move from keyword auto-replies to configuring Jev to make judgments on varied customer messages.
The original post, translated
The store has evolved from "configuring automatic replies" to "configuring automatic judgment." In the past, when running a Taobao shop, customer service relied entirely on piling up keywords yourself. As soon as a buyer sent "refund," it automatically replied "Dear, please wait"; if they typed "free shipping," it directly popped up the shipping fee explanation. But as long as the buyer changed their wording and didn't hit a keyword, the bot went completely silent, with no reaction at all. The rules were hard-coded, and someone still had to keep an eye on things to cover the gaps. Now the approach has reversed. Jev is not going to write
Show the original post in its source language ▾
店铺从 “配置自动回复” 进化到 “配置自动判断” 以前开淘宝，客服全靠自己堆关键词 买家一发 “退款”，自动回 “亲稍等”；打 “包邮”，直接弹运费说明 但只要买家换个说法，没命中关键词，机器人直接哑巴，啥反应没有 规则是写死的，后面还是得有人盯着兜底 现在路子反过来了 Jev 不是去写
The post above is a machine translation from zh; the untranslated text is in the fold-out.
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under general Jev builds. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @youguqi2023 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post