Ryan Carson单人开发：用Devin与Watchdog替代客服及QA团队
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
为独立开发者提供了具体的AI代理管理架构（文件夹+纸质清单）和自动化工作流参数（如LAN PR、Watchdog），可直接参考其单人技术栈配置。
Ryan Carson is a five-time founder and the current solo founder of Untangle, a B2B SaaS platform for family law firms. Before Untangle, he co-founded Treehouse, an online coding education platform, and has spent the better part of two decades building and leading tech companies. He’s active on X, where he shares his solo founder journey in real time, including what he actually spends on AI tools each month.
Ryan Carson 是一位五次创业者，也是 Untangle 的现任独立创始人。Untangle 是一个面向家庭法律事务所的 B2B SaaS 平台。在创立 Untangle 之前，他曾共同创办了 Treehouse，这是一个在线编程教育平台，并且花了近二十年的时间构建和领导科技公司。他在 X（原 Twitter）上非常活跃，实时分享他的独立创业历程，包括他每月在 AI 工具上的实际花费。
Listen or watch on YouTube, Spotify, or Apple Podcasts
在 YouTube、Spotify 或 Apple Podcasts 上收听或观看
What you’ll learn:
你将学到：
- Why Ryan manages 15 concurrent Devin agents with a folder system and a piece of paper, not a dashboard
- The Watchdog playbook: what he built to replace a customer success team across every law firm account
- How his LAN PR skill closes the loop on 40 daily PRs without a QA team reviewing a single one
- Why he moved off local agents almost entirely, and the one situation where he still reaches for Codex
- The design workflow we’re both using: Claude Design into a Markdown spec, then Codex to build the real thing
- What he found when he got away from his computer and met a real customer, and why it changed his entire product direction
- How he’s hiring his first engineer without a single phone screen or interview
- Why we both think more AI output is actually the wrong goal, and what to optimize for instead
- 为什么 Ryan 使用文件夹系统和一张纸来管理 15 个并发的 Devin 智能体，而不是仪表盘
- Watchdog 操作手册：他构建了什么来取代每个律师事务所客户账户背后的客户成功团队
- 他的 LAN PR 技能如何在不经过 QA 团队审核任何内容的情况下，闭环处理每天 40 份公关稿
- 为什么他几乎完全转向了云端智能体，以及在什么情况下他仍然会使用 Codex
- 我们都在使用的开发工作流：从 Claude Design 到 Markdown 规格说明，然后由 Codex 构建实际产品
- 当他离开电脑去见真实客户时发现了什么，以及这如何改变了他的整个产品方向
- 他是如何在没有任何电话面试或正式面试的情况下招聘第一位工程师的
- 为什么我们都认为更多的 AI 输出实际上不是正确的目标，以及我们应该优化什么
Brought to you by:
由以下机构赞助播出：
WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
WorkOS——让你的应用具备企业级就绪能力，支持 SSO、SCIM、RBAC 等
Jira AI SDLC—Get your tokens’ worth with Jira
Jira AI SDLC——在 Jira 中充分利用你的 Token 价值
In this episode, we cover:
在本集中，我们将涵盖：
(00:00) Introduction to Ryan Carson
(00:00) Ryan Carson 简介
(02:55) Ryan’s update: Untangle, the divorce PMF pivot, and B2B growth
(02:55) Ryan 的最新动态：Untangle、离婚产品的 PMF 转型以及 B2B 增长
(07:35) Ryan’s current Devin stack: folders, P0 threads, and the paper list
(07:35) Ryan 当前的 Devin 技术栈：文件夹、P0 线程和纸质清单
(16:29) Watchdog playbook: account monitoring across every firm
(16:29) Watchdog 操作手册：跨所有律所的客户账户监控
(18:09) Managing agent decision fatigue: Ryan’s method vs. Claire’s
(18:09) 管理智能体决策疲劳：Ryan 的方法与 Claire 的方法对比
(20:32) Producing more output does not make a better product
(20:32) 产出更多并不等于做出更好的产品
(22:47) Using cloud agents for ops beyond just code
(22:47) 将云端智能体用于代码之外的运营工作
(25:14) When to use Codex vs. Devin vs. Claude Code
(25:14) 何时使用 Codex、Devin 还是 Claude Code
(27:15) Merge Mommy recap
(27:15) Merge Mommy 回顾
(28:15) LAN PR skill: review loops, video walkthrough, and auto-merge
(28:15) LAN PR 技能：审查循环、视频逐步演示和自动合并
(30:20) Slack vs. Devin threads for async team communication
(30:20) Slack 与 Devin 线程用于异步团队沟通
(35:58) Claude Design plus Codex for building a technical design system
(35:58) Claude Design 结合 Codex 构建技术设计系统
(39:00) EA tools: Polly the OpenClaw vs. Claude Code on a Mac Mini
(39:00) EA 工具：Polly the OpenClaw 与 Mac Mini 上的 Claude Code
(42:09) Quick recap and final thoughts
(42:09) 快速回顾与最终感想
Tools referenced:
引用的工具：
• Devin (Cognition): https://www.cognition.ai/
• Devin (Cognition): https://www.cognition.ai/
• Codex (OpenAI): https://openai.com/codex
• Codex (OpenAI): https://openai.com/codex
• Claude Code/Claude Design (Anthropic): https://www.anthropic.com/claude
• Claude Code/Claude Design (Anthropic): https://www.anthropic.com/claude
• OpenClaw (Claude-based desktop client): https://openclaw.ai
• OpenClaw (基于 Claude 的桌面客户端): https://openclaw.ai
• Cursor: https://www.cursor.com/
• Cursor: https://www.cursor.com/
• BugBot (Devin’s built-in PR review): https://cursor.com/bugbot
• BugBot (Devin 内置的 PR 审查): https://cursor.com/bugbot
• Sentry (error monitoring referenced in Watchdog): https://sentry.io/
• Sentry (Watchdog 中引用的错误监控): https://sentry.io/
• Ugmonk (analog to-do system): https://ugmonk.com/
• Ugmonk (模拟待办事项系统): https://ugmonk.com/
Other references:
其他引用：
• Devin playbooks/skills documentation: https://docs.cognition.ai/
• Devin playbooks/skills 文档: https://docs.cognition.ai/
• Jack Dorsey/Buzz (async-first communication referenced): https://buzz.new/
• Jack Dorsey/Buzz (引用的异步优先沟通): https://buzz.new/
• Merge Mommy (Claire’s Eve agent for PR risk scoring, deployed on Vercel): https://www.lennysnewsletter.com/p/build-an-ai-code-review-bot-in-30
• Merge Mommy (Claire 的 Eve 代理，用于 PR 风险评分，部署在 Vercel 上): https://www.lennysnewsletter.com/p/build-an-ai-code-review-bot-in-30
Where to find Ryan Carson:
如何找到 Ryan Carson：
X: https://x.com/ryancarson
X: https://x.com/ryancarson
Untangle: https://untangle.us
Untangle: https://untangle.us
Where to find Claire Vo:
如何找到 Claire Vo：
ChatPRD: https://www.chatprd.ai/
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
网站: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
LinkedIn：https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
X：https://x.com/clairevo
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].
制作与营销由 https://penname.co/ 负责。如需咨询播客赞助事宜，请发送邮件至 [email protected]。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力