WHAT NEW IN X10.31 SAT

AI collections from X · 22 collections · 61,986 posts

jevARTICLE

Three days of Jev in production, failure cases included

The author describes actually using Jev on production systems for three days through mapping, shadow runs, measurement, and promotion, and lists the failure cases along with plans for further evals.

Yonatan Gross
@yonyonizArchived 2026.09.20Originally posted 2026.09.19

What this article says

这不是演示,而是作者在生产系统上连续使用 Jev 三天的复盘,明确把失败案例也写进去。他总结出一套四步工作流:map(把现有决策点映射成 Jev 可表达的结构化选择)、shadow(让 Jev 与线上原逻辑并行跑、只观察不接管)、measure(用评测指标对比两者结果)、promote(指标达标后才把决策权交给 Jev)。文章强调这套流程的意义在于把模型替换从一次性切换变成可回滚的渐进升级,并给出各阶段踩到的坑。后续计划接入 Vercel agent-browser、Pydantic AI 和 trycua,继续补充评测数据。

How I'm actually using Jev from @typesafeai. No demo: three days on production systems, misses included.

Map, shadow, measure, promote.

With @vercel agent-browser, @pydantic AI, and @trycua next. More evals coming.

More: https://yonyon.ai https://x.com/i/article/2101233808896831489

Yonatan Gross @yonyonizOriginally posted 2026.09.19
Open original on X
x.com/yonyoniz/status/2101241236107542549Archived 2026.09.20 10:10