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

August 24, 2026

AI Summary

5 min read

Ryan Carson, solo founder of the divorce-tech startup Untangle, spent $20,000 in a single month on Devin, the cloud-based coding agent from Cognition. That spending spree was not a mistake — it was a deliberate bet that the future of engineering is cloud agents, not local IDEs. In this conversation, Carson and host Claire Vo walk through how their stacks have evolved over the past year, why managing agents is now the core job of a founder, and where AI still cannot replace the messy, human work of finding product-market fit.

From hand-holding to delegation: the agent management shift

A year ago, Carson was working inside Cursor, writing detailed markdown files and giving his agents step-by-step instructions. Today, he rarely opens an IDE. He lives inside Devin, running 10 to 15 concurrent threads organized into folders labeled P0 (big features), P1, P2, and Bugs. The shift mirrors a deeper change in how he thinks about his own role. "All of us have to uplevel our ability to manage agents," he says. "That is our job."

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **The Cloud Agent Manifesto** - Ryan declares the future is 100% cloud agents and explains why he went all-in, spending up to $20,000 in one month on Devin
2 (03:03) **One Year of AI Evolution: From Hand-Holding to Letting Agents Work** - Ryan and Claire reflect on how much has changed since their first episode, where Ryan was writing three-step markdown files and hand-holding every agent move
3 (04:53) **The Untangle Origin Story: Finding PMF Through Human Conversation** - Ryan shares how he built a divorce-tech startup, pivoted from consumer to B2B, and discovered product-market fit by talking to a single lawyer
4 (08:29) **Max Q: The Solo Founder's AI Stack** - Ryan walks through his current setup, living entirely in Devin on the cloud, managing 10-15 concurrent threads bucketed into folders
5 (13:53) **The Watchdog Playbook: Managing Chaos at Scale** - Ryan explains his custom Devin playbook that automatically checks all customer accounts, surfaces top issues, and tracks whether they've been fixed
6 (18:10) **Decision Fatigue and Output Constraint** - Claire shares her counterintuitive approach: she uses decision fatigue as a prioritization heuristic and intentionally constrains output
7 (21:03) **The Human Reality: AI Can't Create Markets** - Both founders agree that AI has not magically created new markets, and the mismatch between code output and commercializable product is real

+ Full timestamped outline available in the app

Guests on this episode

Ryan Carson

Show Notes

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.

What you’ll learn:

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

—

Brought to you by:

WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more

Jira AI SDLC—Get your tokens’ worth with Jira

—

In this episode, we cover:

(00:00) Introduction to Ryan Carson

(02:55) Ryan’s update: Untangle, the divorce PMF pivot, and B2B growth

(07:35) Ryan’s current Devin stack: folders, P0 threads, and the paper list

(16:29) Watchdog playbook: account monitoring across every firm

(18:09) Managing agent decision fatigue: Ryan’s method vs. Claire’s

(20:32) Producing more output does not make a better product

(22:47) Using cloud agents for ops beyond just code

(25:14) When to use Codex vs. Devin vs. Claude Code

(27:15) Merge Mommy recap

(28:15) LAN PR skill: review loops, video walkthrough, and auto-merge

(30:20) Slack vs. Devin threads for async team communication

(35:58) Claude Design plus Codex for building a technical design system

(39:00) EA tools: Polly the OpenClaw vs. Claude Code on a Mac Mini

(42:09) Quick recap and final thoughts

—

Tools referenced:

• Devin (Cognition): https://www.cognition.ai/

• Codex (OpenAI): https://openai.com/codex

• Claude Code/Claude Design (Anthropic): https://www.anthropic