【文章标题】：How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio) 【文章标题】：我是如何将Claude改造成自我进化的产品经理助理 | Daniel Blum（Melio产品经理）
【文章正文】： Daniel Blum 丹尼尔·布鲁姆
is a product manager at Melio, a B2B payments company, and one of the most systematic thinkers I’ve had on the show when it comes to personal AI infrastructure. He’s spent the past year building a Claude- and Cowork-based productivity system that manages his Notion board, processes his Slack and email, and runs self-improvement loops every week without needing to be prompted. Beyond his own workflow, Daniel built and scaled a “Workstation” onboarding plugin that gets any Melio employee up and running with a personalized Claude setup in about 15 minutes. 作为B2B支付公司Melio的产品经理，丹尼尔是我节目中关于个人AI基础设施最具系统思维的嘉宾之一。过去一年他构建了基于Claude和Cowork的生产力系统，能自动管理Notion看板、处理Slack和邮件，并每周自主运行自我改进循环。除个人工作流外，他还开发并推广了”工作站”入职插件，让任何Melio员工都能在15分钟内完成个性化Claude配置。
Listen or watch on 收听或观看平台：
YouTube YouTube
,
Spotify Spotify
, or 或
Apple Podcasts 苹果播客
What you’ll learn: 您将了解到：
Why Daniel says the two rules that make any AI system powerful aren’t about the tool you pick 为什么丹尼尔认为强大AI系统的两条法则与工具选择无关
How his weekly prep automation fills an entire Notion board from scratch every Sunday, without his touching it 他的周度准备自动化如何每周日自动生成完整Notion看板而无需人工干预
The morning brief feature that teaches Claude new internal terms on its own, so company jargon never slows it down 晨间简报功能如何自主教会Claude内部术语，使其不受公司行话影响
Why he describes Notion as “read-only” now, and what that says about how PM workflows are changing 为何他现在称Notion为”只读”工具，这反映了产品经理工作流的哪些变革
The self-improvement loop that watches Daniel’s edits, spots recurring friction, and suggests new skills to build 自我改进循环如何观察丹尼尔的编辑、发现重复摩擦并建议新技能
How he uses a skill called “Improve” to filter the endless flood of AI tips without drowning in them 他如何运用”改进”技能筛选海量AI建议而不被淹没
What he built to scale his personal system to every PM at Melio, and the UX lesson he learned the hard way 他将个人系统推广至Melio全体PM时构建的工具，以及付出代价学到的UX经验
The capability gap that’s still keeping him from running 100% of his work through Claude 目前仍阻碍他100%通过Claude处理工作的能力缺口
Brought to you by: 本期赞助商：
Optimizely —Your AI agent orchestration platform for marketing and digital teams Optimizely——面向营销和数字团队的AI智能体编排平台
Jira AI SDLC —Get your tokens’ worth with Jira Jira AI开发生命周期——让您的令牌物有所值
In this episode, we cover: 本期内容时间轴：
( 00:00 ) Daniel’s background and the PM overhead problem he needed to solve (00:00) 丹尼尔的背景与亟待解决的产品经理效能问题
( 03:30 ) His AI stack at Melio (03:30) 他在Melio的AI技术栈
( 05:00 ) The two rules that make any AI system genuinely powerful (05:00) 真正强大AI系统的两条黄金法则
( 06:00 ) The Notion board Cowork built for him (and manages on his behalf) (06:00) Cowork为他构建（并代管）的Notion看板
( 07:30 ) How he contextualizes Claude with voice memos, links, and recurring updates (07:30) 如何通过语音备忘录、链接和定期更新为Claude建立上下文
( 09:00 ) His weekly prep automation (09:00) 他的周度准备自动化流程
( 11:00 ) His morning brief (11:00) 晨间简报功能详解
( 15:00 ) How Claude flags unknown internal terms and saves them to context (15:00) Claude标记未知内部术语并存入上下文的机制
( 17:30 ) Running 70% to 80% of his workday through Cowork (17:30) 日常工作70%-80%通过Cowork运行的实践
( 19:00 ) Chrome connector vs. MCPs for tools without integrations (19:00) 无集成工具场景下Chrome连接器与MCP方案的对比
( 20:00 ) The real ROI question: why the early weeks feel slow, and why you push through anyway (20:00) 真实ROI问题：为何初期进展缓慢却仍需坚持
( 25:00 ) Scaling the system to the team with the Workstation plugin (25:00) 通过工作站插件实现团队级扩展
( 26:30 ) The self-improvement loop (26:30) 自我改进循环机制
( 31:00 ) How the Improve skill separates actually useful AI tips from the hype (31:00) “改进”技能如何从炒作中筛选真正有用的AI建议
( 32:00 ) The Workstation onboarding flow, and the UX lesson from distributing “Spectacular” (32:00) 工作站入职流程及推广”Spectacular”获得的UX教训
( 38:00 ) The 20% Claude still can’t do, and what changes when it can (38:00) Claude目前20%无法完成的工作及突破后的影响
( 41:00 ) What Daniel spends his reclaimed time on (41:00) 丹尼尔如何利用节省的时间
( 42:30 ) Claude rage (42:30) “Claude愤怒”现象
Tools referenced: 提及工具：
• Claude: https://claude.ai • Notion: https://notion.so • Notion：https://notion.so
Other references: 其他参考资料：
• From a 3M API: How a non-coder built Memelord | Jason Levin: https://www.lennysnewsletter.com/p/from-a-690-newsletter-to-3m-api-how?utm_source=publication-search • 从6.9美元简报到300万美元API：非程序员如何打造Memelord | Jason Levin
• How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman: https://www.lennysnewsletter.com/p/how-the-founder-of-morning-brew-built?utm_source=publication-search • Morning Brew创始人如何打造永不枯竭且优质的Claude内容机器 | Alex Lieberman
Where to find Daniel Blum: 丹尼尔·布鲁姆联系方式：
LinkedIn: https://www.linkedin.com/in/blumd/ Website: https://www.imdanielblum.com 个人网站：https://www.imdanielblum.com
Where to find Claire Vo: 克莱尔·沃联系方式：
ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ 个人网站：https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo 推特：https://x.com/clairevo
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co. 节目制作与营销由Penname.co负责。赞助咨询请联系jordan@penname.co