Just played around with @typesafeai, and the result was
Tested Jev on a customer support ticket about a late order, using its strict output format to get a reship decision instead of a written analysis.
The original post, translated
Just played around with @typesafeai, and the result was much more useful than having the model write an analysis. There are strict formatting requirements when using it, so it took a bit of getting used to at first. Wrote a State as follows: Hi, my order #8821 was supposed to arrive Friday. Tracking hasn't moved since Wednesday. I need it before Monday for a client meeting. Can you reship
Show the original post in its source language ▾
刚刚用 @typesafeai 玩了一下，结果比让模型写一段分析有用得多。用的时候有严格的格式要求，开始还是有点不习惯。 写了个State如下： Hi, my order #8821 was supposed to arrive Friday. Tracking hasn't moved since Wednesday. I need it before Monday for a client meeting. Can you reship
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 @Leo_Web3_BTC · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post