Claire Vo · 2 min read · Gen AI Tools
From journalist to iOS developer: How LinkedIn’s editor builds with Claude Code | Daniel Roth
Read the original on lennysnewsletter.com →
Daniel Roth, LinkedIn's editor-in-chief, built multiple production iOS apps without traditional coding by harnessing Claude Code. He explains a dual-agent AI workflow (builder and reviewer), a 'picky customer' mindset for non-technical builders, and branch-based development to ship to the App Store, all while preserving long-term context in Markdown.
Key Takeaways
- Set up a dual-agent Claude Code system (builder + reviewer) to plan, implement, and review AI-generated features.
- Adopt a 'picky customer' mindset to guide AI outputs and maintain quality when you’re not a traditional engineer.
- Prioritize features using AI-ranked impact versus build time to optimize for user value and retention.
- Save work as Markdown files to create durable context that survives AI-initiated changes and project evolution.
- Use branch-based development and an AI-assisted Copilot workflow to test and ship to the App Store without formal engineering experience.
Excerpt
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. Listen or watch on YouTube , Spotify , or Apple Podcasts 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…