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
Most AI products don’t fail because of the model.
They fail because the system around it was never designed properly.
Choosing GPT, Claude, or an open-source model matters—but production AI also needs:
• Reliable data
• Strong retrieval and ranking
• Clear evaluation
• Guardrails and fallbacks
• A useful product experience
The difference between an AI demo and a real AI product is not a smarter model.
It’s an architecture that remains reliable, fast, and useful when real users arrive.
I help founders build production-ready AI products—from RAG and search to backend systems, product workflows, and deployment.
Building an AI SaaS, marketplace, or automation product? Let’s talk.
#AIEngineering #SaaS #ArtificialIntelligence
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
Excited to share the visual identity we crafted for Aivana. Head over to our site to read the full breakdown and drop a like if you love it! ❤️
Let me know what you think! 👀✨
📩 Collaborate with Us? Contra Odama Studio
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.
(insights into submission)
Imagine if AI kept improving your routine week by week, helping you achieve your goals in the most efficient way.
And imagine that when you do an intense activity, the app suggests relaxing activities like deep breathing, gentle stretches, etc.
Imagine if the app had a range of exercises to improve your focus, impulse control, critical thinking, and other important brain functions.
And if AI knew you best not through your sugarcoated chats, but through your real task performance and daily expressive writing.
For the Figma Config Makeathon, I tried to tackle this problem. While people often blame AI for causing them to underutilize their brains and making them anxious as now that they have so many goals to juggle at once while keeping up with an even faster-changing world—I thought AI could actually help solve the very problem it's being blamed for.
So I made Sarthi (Charioteer; a term representing a guiding light in Hinduism). This app helps guide us through our goals and keep our brains active.
For now, given the time and credit limitations, I was able to build out each core flow in the app (goal setting and management, expressive writing, weekly counseling, and creating various Anti-AI exercises).
I also added seed (demo) data so that the judges/reviewers can actually see how the flows will work, as well as how the app behaves when used fresh after the demo data is removed.
Although showing some of the functionalities wasn't possible within the scope of the current project (e.g., after 90 minutes of study in timer mode, the AI suggests relaxing exercises and similarly for other tasks depending on the nature of the tasks), I've tried to include as much as possible in this built prototype.
I'm looking forward to diving deeper into this app and trying to turn it into an actual product—one that has the potential to support many of us with what it has to offer.
@figma @contra, tons of thanks to you for this opportunity—for giving me access to Figma's tools and for helping me open up my mind, so that I could find real clarity in positioning myself as a designer and discovering purpose in my design.
Resharing the links:
Live Project: https://halt-math-77224343.figma.site
This deserves more than just a like
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?
