One structured design prompt, three tools: Claude vs ChatGPT vs Figma Make compared
Tegadesigns · x · 2026-09-15
Designer Tega ran the same highly structured JSON-style prompt — specifying a 393x852 canvas on iPhone 16 Pro, warm orange palette, Satoshi/Inter fonts, rounded corners and shadows — asking each tool to generate a minimal, premium delivery-app home screen. The outputs from Claude, ChatGPT, and Figma Make are shared side by side with the full prompt for the community to compare. Useful reference for anyone building a structured design-prompt workflow.
Related event: Designers pit Claude, ChatGPT and Figma Make against each other(3 posts)→
More from coding & agent
- Plane to launch workspace Agents this week — JosephJacks_ · 2026-09-16
- GlossoGen: open-source platform shows AI agents spontaneously inventing new languages under pressure — EliasEskin · 2026-09-16
- Attach Claude, Codex and Gemini agents to RealSense cameras with one npx command — chrismatthieu · 2026-09-16
- One memory config across multiple agent types will quietly ruin all of them — Adventurous_Whole973 · 2026-09-16
- Twin Store lets 100k agent builders sell workflows with Stripe billing in 5 minutes — JaynitMakwana · 2026-09-16
- Claude Code creator Boris Cherny ran one prompt for 15 days straight to rewrite Electron app as native Swift — rohanpaul_ai · 2026-09-16