The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
New case study: Prefill
I used Claude Code + Paper.design to generate an MVP for a software that autofills job applications using multi-profile data. Functional in hours. But functional isn't designed.
The AI added a sidebar for 2 pages (21% of screen space, wasted), required 30+ clicks for a 15-field form, and opened full pages for single-field additions.
I stripped all of it back. Removed the sidebar, scoped every action to its context, and built a browser extension on top: 3 clicks to fill any form, regardless of field count.
Full breakdown here: Prefill — Autofill That Understands Who You Are
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Designed a modern SaaS website for InterviewFocus – AI-Powered Interview Preparation Platform.
Clean and professional UI focused on helping users develop job-ready talent through intelligent interview training, real-time feedback, performance analytics, and practice tracking.
Nice work as usual
Title:
I built a design system generator inside Figma Make. Here's the workflow.
The problem I kept running into: every new client project meant re-explaining the brand to every AI tool from scratch. Figma Make didn't know the colors. Cursor didn't know the tokens. Claude didn't know the rules. I was the shared memory — and I kept losing things.
So I built Design System Gen. Entirely inside Figma Make. Powered by Claude API.
The workflow:
Upload brand references → Claude API analyzes them across 8 dimensions (palette, mood, typography, composition, lighting, texture, motion, UI DNA) → structured data, not vibes → generates 11 files, each formatted for a specific tool in your stack.
figma-make.md → paste once, Figma Make knows your entire design system
design-system.css → all tokens as CSS custom properties
tokens.json → W3C format, imports directly into Figma Variables
starter.tsx → React starter with tokens already bound
.cursorrules → Cursor knows your system from root
Claude.md → Claude reads it automatically every session
+ 5 more for docs, LLMs, prompts, components
Every tool gets its own context file. All consistent with each other.
The part I'm most proud of: I'm a designer. I don't write code. The entire tool — UI, API integration, file generation logic — was built and shipped inside Figma Make. No external hosting. No separate codebase.
Live at: vibecodingdsgen.figma.site
Add your Claude API key and try it with your own moodboard.
#FigmaMake #DesignSystem #VibeCoding #AI #Claude #UXUI #DesignSystems #ConfigMakeathon
As someone who constantly jumps between Figma, Claude, ChatGPT, Cursor, Lovable, and other AI tools, this problem feels very familiar 😅
The tools are getting smarter, but keeping context consistent is still surprisingly manual. Love seeing people tackle that gap.
AgentOps Deal Desk
AgentOps Deal Desk is an AI-assisted dashboard that helps freelancers and service operators convert scattered opportunities into a ranked action pipeline. It scores each deal by fit, urgency, budget, readiness and risk, then turns that signal into a proposal angle, bid range and delivery checklist.
Category: Dashboard.
What it does: the app turns freelance and consulting opportunities into a deal pipeline. Each opportunity has a win score, readiness score, budget, deadline, category and status. Selecting a deal opens a structured view with the client pain, proposal angle, bid range, delivery checklist and risk flags.
How it builds on the Bubble AI baseline: I started with a Bubble AI-generated app foundation from a detailed product prompt covering the dashboard category, opportunity scoring, proposal angles, bid ranges, delivery checklists, risk flags and the core navigation. I then refined the product concept around decision speed: helping an operator know which deal to chase, how to position it and what proof is needed before sending a proposal.
Demo video and AI baseline proof are attached.
Great attention to detail. The result feels very refined.
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
MagicPath
The canvas is infinite, and exploration is becoming the workflow. How are you using MagicPath?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?