I Tested Claude Code vs. Codex on Design. It Wasn't Even Close.

About this video

Try Granola for FREE today: https://www.granola.ai/?via=nate-herk My playbook for growing a $1M AI agency: https://app.aiautomationsociety.ai/opaa-ads-optin My FREE resources: https://www.skool.com/ai-automation-society/about?el=claude-vs-codex-design&hcategory=youtube-videos&utm_campaign=free-group My Tools💻 FREE MONTH voice to text: https://get.glaido.com/nate Code NATEHERK for 10% off VPS (annual plan): https://www.hostinger.com/vps/claude-code-hosting I gave Claude Code and Codex the same prompts, brand guidelines, and source files to build eight websites, then compared the design quality, speed, token use, agent count, and estimated API cost. Codex won most of the subjective design rounds while using about one-third of the time and roughly one-fifth of the output tokens. The final tests also show how detailed prompting can make two different coding agents produce nearly identical results. Sponsorship Inquiries: 📧 nate@smoothmedia.co Connect with me: https://www.linkedin.com/in/nateherkelman/ https://x.com/nateherk https://www.instagram.com/nateherk/ TIMESTAMPS 0:00 Test Setup 0:28 Bowl & Bloom 4:29 MinuteCraft 7:46 Trail Latch 12:15 Present & Clear 13:59 North Ledger Studio 15:17 Open-Ended Design Test 18:00 Detailed Prompt Tests 19:49 Final Results