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
Senior Designer in a Box
An AI system that audits DTC landing pages. Six specialist agents — Attention, Value Prop, Trust, Friction, Mobile Reality, Accessibility — score a page against a rubric I built from experience.
The system pins problems on the page, ranks fixes by impact, and rewrites the hero when the scores say the page needs it. When the page is strong, it skips the rewrite. That's the part I care about. Most AI design tools generate. This one decides when to and when not to.
Demo: Ruuts (ruuts.com.co) scored 4.83 average and triggered the variant. AG1's European Spanish page scored 7.83 and skipped it. Same system, same rubric, four-point spread.
Built on Paper with Claude Code.
V2 could be the browser version: same agent system, headless rendering, interactive fix table.
Nice!
Nice. Thanks for sharing the process.
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
Challenges
View all
Related posts
Back in 2016 I made a lot of cinemagraphs for HBO.
They took a surprising amount of work. Masking footage, finding the right loop, freezing parts of the frame and getting everything to transition cleanly.
I’ve had an idea for a simpler cinemagraph tool kicking around in my head ever since.
About a month ago I built another small tool using Toolcraft as the starting point, so yesterday I wanted to see if it could handle this idea too.
A few hours later I had a working cinemagraph editor.
Drop in a video → find your loop → choose how it loops → paint the areas you want to keep still → export.
Basically the workflow I used 10 years ago, condensed into a few controls.
Still rough around the edges, but kind of wild to finally build a tool I’ve been thinking about for a decade.
The masking-and-looping history is exactly why a simpler cinemagraph workflow feels valuable; the tricky part is preserving a seamless transition without making the tool feel like a timeline editor. Curious direction for an AI-assisted app.
How I Actually Build Websites — From Inspiration to Final Build.
I don’t start with a blank screen. I usually start by exploring Pinterest to find visual references, layouts, interactions, and design ideas. Then I bring the reference into ChatGPT, explain what I want to build, and use it to turn the rough idea into a much clearer development prompt.
From there:
Pinterest → Reference → ChatGPT → Refined Prompt → Antigravity → Manual Refinement → Final Website
I give Antigravity the reference image + refined prompt, let it handle the first implementation, and then take over manually to fix the details that AI doesn't get right — spacing, responsiveness, interactions, typography, animations, and overall polish. AI speeds up the process.
But the final quality still comes from the decisions and corrections I make.
This is how I combine design inspiration, AI-assisted development, and manual frontend work to turn an idea into a real website.
I like the deliberate handoff between reference, refined prompt, and manual refinement—especially the note that the final quality comes from your corrections. That balance is what keeps AI-assisted builds feeling intentional.
🎉 Celebrating $10K+ Organic Sales in 1 Month from our Shopify Store! 🚀
"Team, we did it! 🙌"
There is nothing quite like opening your team chat and seeing a celebration of hard work paying off.
We officially crossed the $10K organic sales milestone in one month from our Shopify store; without relying on paid ads.
This milestone was the result of consistent SEO, strategic content, conversion optimization, data analysis, and continuous improvements across the store.
📊 The August 2026 Results:
💰 $10,436.38 total sales
🛒 171 orders
👥 4,476 sessions
📈 3.57% conversion rate
🔄 160 completed checkouts
🔎 ~$4.9K in sales from Google Search
📈 +56% sales growth vs. the previous period
What contributed to the growth
Shopify SEO & organic search optimization
Keyword and content strategy
Product and collection optimization
Conversion rate optimization (CRO)
Customer behavior & cohort analysis
Continuous testing and store improvements
Data-driven decision making
The biggest takeaway? Organic traffic is only valuable when it turns into revenue.
$10K+ is a milestone worth celebrating. But we're already looking at the next opportunity:
More qualified organic traffic → better conversion → stronger retention → sustainable growth. 🚀
Performance data shown in this post is based on the Shopify store's August 2026 results.
ShopifySEO Content Managment Search Engine OptimizationShopify DevelopmentGoogle AnalyticsGoogle Search Console
Solid numbers, especially 160 completed checkouts against 171 orders - low cart-to-completion drop is usually the hard part once traffic is already converting at 3.57%. Curious which CRO change moved that most - was it something on the checkout side, or upstream on the PDP?