How I AI
From Journalist to iOS Developer: How LinkedIn’s Editor Builds with Claude Code | Daniel Roth
Why It Matters
The discussion highlights how AI can democratize software development, enabling creators without formal engineering backgrounds to build and launch apps quickly while maintaining security standards. As generative tools become more accessible, understanding these workflows is crucial for product teams looking to accelerate innovation and reduce reliance on traditional engineering resources.
Key Takeaways
- •Claude agents Bob and Ray coordinate code building, security reviews
- •Non‑technical background used CloudCode, AI prompts to launch iOS apps
- •Personalized software like Commutely emerges from self‑generated feature backlog
- •Dual‑agent workflow mimics product‑engineer handoff, improving code quality
- •Markdown logs preserve context, aiding learning in AI‑assisted development
Pulse Analysis
In this episode, former Fortune editor Dan Roth explains how he pivoted from journalism to iOS development using Claude Code and CloudCode. By treating AI as a collaborative teammate, he built "Commutely," a hyper‑personalized train‑tracking app that solves a niche problem he himself faces. Roth’s workflow showcases how non‑technical founders can generate product ideas, rank them with AI‑driven impact scores, and iterate rapidly without traditional coding expertise. The discussion highlights the rise of personalized software, the power of prompt engineering, and the importance of documenting every step in markdown to keep the AI’s context intact.
A core innovation Roth shares is his "dueling agents" system: Bob the Builder drafts code plans, while Ray, a senior‑engineer persona, audits security and architecture. This handoff mirrors real‑world product‑engineer collaboration, forcing the builder to pause for review and ensuring that each module meets quality standards before merging. By assigning clear roles—planning, security, and tie‑breaking—Roth reduces spaghetti code, avoids branch‑merge headaches, and creates a transparent audit trail. The approach demonstrates how AI can enforce best‑practice discipline, even for creators without formal software training.
For business leaders, Roth’s methodology offers a scalable blueprint for AI‑augmented development. Leveraging Claude’s multi‑agent capabilities, teams can accelerate prototype cycles while maintaining enterprise‑grade security—a concern echoed by WorkOS’s emphasis on authentication, access controls, and audit logs. The episode underscores that the future of product building lies in combining human intuition with AI‑driven process management, turning ideas into market‑ready apps faster and more safely than ever before.
Episode Description
Daniel Roth, editor in chief at LinkedIn, went from business writer to iOS app developer, without ever learning how to code. Using Claude Code, Daniel built and shipped multiple production-ready iOS apps to the App Store, including Commutely, a personalized train-tracking app for New York commuters.
What you’ll learn:
How to set up a dual-agent Claude Code system (builder + reviewer)
Why being a “picky customer” is the right mindset for non-technical builders
How Daniel prioritizes features using AI-ranked impact vs. build time
Why saving everything as Markdown files creates long-term context
The importance of branch-based development—even when AI writes the code
How Daniel ships to the App Store without formal engineering experience
His end-of-day “What did I drop the ball on?” Copilot workflow
—
Brought to you by:
WorkOS—Make your app enterprise-ready today
Vanta—Automate compliance and simplify security
—
In this episode, we cover:
(00:00) Introduction to Daniel Roth
(02:46) Daniel’s AI development workflow overview
(05:56) Using Claude to prioritize feature ideas
(08:58) Building vs. marketing
(09:47) Creating a retention plan for his app
(10:38) Introducing Bob the Builder and Ray the Reviewer
(13:50) How Bob and Ray work together to build features
(14:37) Why Daniel focuses on learning the process
(16:34) The importance of using branches for development
(17:39) Managing AI agents like managing a team
(21:12) Navigating the App Store
(23:06) Being a “picky customer” rather than a PM
(25:00) Testing in Xcode and shipping to the App Store
(28:14) Quick recap
(30:00) Creating terminal aliases with Claude
(31:38) Demo of his Commutely app
(32:10) Using Copilot to manage work responsibilities
(35:05) How Daniel talks to AI without personifying it
—
Tools referenced:
• Claude: https://claude.ai/
• Claude Code: https://claude.ai/code
• Cursor: https://cursor.sh/
• Xcode: https://developer.apple.com/xcode/
• Canva: https://www.canva.com/
• Microsoft Copilot: https://copilot.microsoft.com/
• Terminal: https://support.apple.com/guide/terminal/welcome/mac
• Obsidian: https://obsidian.md/
—
Other reference:
• Commutely (iOS app): https://apps.apple.com/us/app/commutely/id6755789873
—
Where to find Daniel Roth:
LinkedIn: https://www.linkedin.com/in/danielroth1/
Newsletter: https://www.linkedin.com/newsletters/forward-deployed-editor-7378272989982683137/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Comments
Want to join the conversation?
Loading comments...