Design

AI-assisted app building with Claude Code and Figma MCP

Builds apps with Claude Code and Figma MCP, using AI to assist with implementation/prototyping alongside design work.

Why the human is still essential here

Human judgment is required to define requirements, ensure UX quality, and validate solutions; AI assists with building but doesn’t replace design accountability.

How people use this

Figma-to-React component scaffolding

Using Figma context via MCP, AI generates a React component scaffold that matches the layout, states, and naming conventions for developer handoff.

Claude Code / Figma

Clickable prototype with mocked data

AI scaffolds a small web app that mirrors the designed user flow and uses mocked API responses so the team can test interactions quickly.

Claude Code / GitHub Copilot

Design tokens export and sync script

AI creates a design-tokens JSON and a sync script that maps Figma styles to CSS variables for consistent implementation.

Figma Tokens / Claude Code

Community stories (1)

I couldn’t care less about AI

To be fair I use AI everyday in my design process, I pay Gemini and Claude, I have built apps with Claude Code and Figma MCP. AI is useful and impressive, but I miss the good old days when we were just designers focusing on the user experience. I feel that AI is turning companies into complete chaos. Making PMs feel that they can design the final experience just prompting mediocre UIs, making CEOs think designers are not needed, and wanting to turn designers into semi-developers and product managers to prove their value, because now “anybody can design”. Now we have a bunch of people in the organization jumping right into the solution, building mediocre and inconsistent user experience and forgetting completely about the process to understand the problem we’re trying to solve.

TheNuProgrammerUX designer

Mar 5, 2026