Skip to main content
How I AI

I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)

44 min episode · 2 min read
·

Episode

44 min

Read time

2 min

Topics

Productivity, Remote Work, Relationships

AI-Generated Summary

Key Takeaways

  • Cloud Agent Migration: Devin's cloud-based architecture allows agents to run 24/7 without requiring the developer to be at their machine, enabling Carson to ship approximately 40 pull requests daily. Local IDEs like Cursor limit throughput to active working hours. Founders still coding locally should evaluate whether cloud agents could multiply their output without multiplying their hours.
  • Agent Priority Folder System: Organize cloud agent threads into labeled folders — P0 for business-critical features, P1 for secondary work, P2 for lower priority, and a separate Bugs folder — with a maximum of 10–15 concurrent threads. Pair this with a physical weekly priority list to avoid losing focus across simultaneous agent sessions.
  • Watchdog Playbook for Customer Monitoring: Build a repeatable agent playbook called Watchdog that scans each customer account for errors, recent activity, and unresolved bugs since the last check. It surfaces the top three active issues, flags whether open PRs address them, and eliminates the need to manually monitor multiple accounts while handling sales, engineering, and customer success simultaneously.
  • Automated PR Risk Scoring: Deploy an event-driven agent — triggered when a PR passes CI checks — that scores each pull request across five risk dimensions including blast radius and security exposure. Low-risk PRs receive automatic approval and merge without human review. Medium and high-risk PRs trigger a Slack notification to a designated reviewer, maintaining compliance controls while clearing PR queues efficiently.
  • Coding Agent Scope Expansion: Cloud coding agents with full codebase access can handle business operations beyond software development. Carson uses Devin for custom customer quoting, investor update drafts via a saved playbook, and operational documentation. Any repeatable business task that benefits from codebase context is a candidate for delegation to a background agent rather than a human hire.

What It Covers

Solo founder Ryan Carson details spending $20,000 in a single month on Devin, a cloud-based AI coding agent, while building Untangle, a B2B legal tech product for family law firms. He contrasts cloud versus local agent workflows, agent prioritization systems, and explains why human customer conversations remain irreplaceable for finding product-market fit.

Key Questions Answered

  • Cloud Agent Migration: Devin's cloud-based architecture allows agents to run 24/7 without requiring the developer to be at their machine, enabling Carson to ship approximately 40 pull requests daily. Local IDEs like Cursor limit throughput to active working hours. Founders still coding locally should evaluate whether cloud agents could multiply their output without multiplying their hours.
  • Agent Priority Folder System: Organize cloud agent threads into labeled folders — P0 for business-critical features, P1 for secondary work, P2 for lower priority, and a separate Bugs folder — with a maximum of 10–15 concurrent threads. Pair this with a physical weekly priority list to avoid losing focus across simultaneous agent sessions.
  • Watchdog Playbook for Customer Monitoring: Build a repeatable agent playbook called Watchdog that scans each customer account for errors, recent activity, and unresolved bugs since the last check. It surfaces the top three active issues, flags whether open PRs address them, and eliminates the need to manually monitor multiple accounts while handling sales, engineering, and customer success simultaneously.
  • Automated PR Risk Scoring: Deploy an event-driven agent — triggered when a PR passes CI checks — that scores each pull request across five risk dimensions including blast radius and security exposure. Low-risk PRs receive automatic approval and merge without human review. Medium and high-risk PRs trigger a Slack notification to a designated reviewer, maintaining compliance controls while clearing PR queues efficiently.
  • Coding Agent Scope Expansion: Cloud coding agents with full codebase access can handle business operations beyond software development. Carson uses Devin for custom customer quoting, investor update drafts via a saved playbook, and operational documentation. Any repeatable business task that benefits from codebase context is a candidate for delegation to a background agent rather than a human hire.

Notable Moment

Carson initially assumed consumers needed AI help navigating divorce, built a product for that market, and found zero traction. A single in-person meeting with a family law attorney who immediately offered to pay revealed the actual market — a reminder that no volume of shipped code substitutes for one direct customer conversation.

Know someone who'd find this useful?

Episode Transcript

If you're out there listening and you are doing engineering, you're doing your work locally, you really need to open your eyes. I think the future is pretty much a 100% cloud agents. I went all in. So much so, I spent $5,000 on Devon, and then I went up to $20,000 one month. You know, I think one of my big messages for today is that all of us have to uplevel our ability to manage agents. Like, that is our job. How do you effectively manage hundred, five hundred employees? This is the whole reason that organizations were built as pyramids. Like, humans can't scale and have a thousand directs. What is in your stack right now, and have you structured stuff to make you successful and build things effectively? So what I'm doing is figuring out how to manage, you know, throngs of agents. And in Devon, what what you're seeing is, is folders. And you'll notice p zero is the big stuff. The these are the the main things I need to move forward as the business, new features, p one, p two. So our priority zero, we got bugs. Let them work. Usually, give them a goal, and it's just such a crazy different world we live in now. Welcome back to How I AI. I have a super special guest, Ryan Carson, one of our earliest How I AI episodes, who is here to show us what has changed in the last twelve months in the age of coding agents. We're going to wax poetic about our favorite little AI intern, Devin, talk about all the ways you're underutilizing your coding agents, and give maybe the most anti AI episode of How I AI where we talk about where AI can't solve your problems, how you need to get out in front and actually talk to people, and how pen and paper still have a place in his stack. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your Copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop in APIs for enterprise features so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using Work OS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com. Start …

Get the full transcript (7,935 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all How I AI transcripts →

You just read a 3-minute summary of a 41-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • Medium and high-risk PRs trigger a Slack notification to a designated reviewer, maintaining compliance controls while clearing PR queues efficiently.
  • SPONSORS [{'name': 'WorkOS', 'url': 'https://workos.com'}]
  • Local IDEs like Cursor limit throughput to active working hours.
  • by Atlassian

    SPONSORS [{'name': 'Jira by Atlassian', 'url': 'https://jira.dev'}]
  • DevinRecommended
    Solo founder Ryan Carson details spending $20,000 in a single month on Devin, a cloud-based AI coding agent, while building Untangle, a B2B legal tech product for family law firms.

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

You're clearly into How I AI.

Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime