The author tested an email Agent on 5,039 emails and includes 5 scenario prompts
English text is being prepared.
The author ran their own QQ Mail inbox of 5,039 emails through the email Agent on mobile; of 69 emails from the past month, about 20 needing action were filtered out in 43 seconds. The article provides prompts for 5 common scenarios, plus a memory template of "user profile + 10 behavioral guidelines," usable by copying without writing any code. Core scenarios include finding hidden AI auto-charges and SaaS renewals in 17 seconds, and merging multiple banks' Chinese and English monthly statements and calculating foreign currencies separately in 30 seconds.
Why read this
AI score 55
The author tested it on their own 5,039 emails and provides email agent prompts and a memory template that can be copied directly, transferable to everyday reconciliation scenarios.
Topics
View original posthttps://t.co/BSzz78Spop
View original
https://t.co/BSzz78Spop
Body
我最近AI实践的一个顿悟是，AI 用在邮箱上最狠的从来不是帮你写客套信，而是把散在几千封邮件里的关键信息捞出来，拼成一张能看的表，再把截止日期自动变成待办。
这篇我跟兄弟们只捞干货，我拿自己 5039 封邮件的 QQ 邮箱在手机端全部实测跑通。
5 个最常用场景的指令全贴在文里，
文末还有「用户档案 + 10 条行为准则」记忆模板，不写一行代码，照着抄一遍就能直接用。
全篇核心讲三件事： 1、怎么在手机上只用17秒就把所有隐蔽的AI自动扣费、SaaS续费一个不落全找出来？ 2、怎么30秒把分散在各家银行的中英文月结单合成一个表，外币还自动分开算？ 3、怎么写进10条行为准则，以后每月初只跟AI说一句话就自动对账？
我的 QQ 邮箱，收件箱一共 5039 封，银行月结单、扣款通知、订阅到期、条款修订、API 调价，全混在一起，一直没时间整理。
 最近一个月是 69 封，让我的邮箱agent翻了一遍，它说真正需要我动手的大概 20 封，剩下的是营销推广和例行的账单通知，前后用了 43 秒。