Dec 8, 2025
Vibe coding as a non-technical designer
How 0xDesigner uses MCPs, Codex, PRDs, and agent-driven workflows to build faster, and stay focused on product intent.
Workflows
Jasmine KaurStrategic AI Designer @Georgia Tech
In this journey of tracking AI workflows in Design, 0xDesigner shares his perspective on the MCPs, workflows, and mental models that help him build faster with agents. In this article, we unpack his thinking around setup, PRDs, testing, and how to work with Codex and Claude effectively.
In this article, we highlight our biggest takeaways from this chat.
Which MCPs are must-haves in your setup and why?
- Figma MCP: I use it to round trip UI. I import a live page into Figma, polish it, then point the agent at a component and it implements the pixel changes. It even ships a fixed prompt that generates design system rules, which makes restyling the whole app trivial.
- Playwright MCP: Gives the agent real browser access for checks and lightweight tests. I use it when I need the web, though it can flood the token window so I keep it targeted.
- Railway MCP: Fast deploys and environment setup through the agent. Keeps me out of manual infra work.
★★★★★
It's basically like Mobbin,
but specifically for AI
but specifically for AI
Lead Product Designer at FocaldataCreate a free account
to keep reading
No credit card required. Upgrade later when you want the full playbook.
RELATED INSIGHTS
Building an agent harness for your team
How to turn individual workflows into a shared workspace, especially inside design teams
Making your design system agent ready
Everything you need to get started with an agentic design system.
I spent the afternoon with AI design leaders
An eye-opening experience into the future of design work.
Updated weekly with new examples
200+ curated AI interactions
From ChatGPT to Figma AI, explore the best AI UX patterns from leading products.
Join 14,000+ design and product folks