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
Business networking app, live on Android and iOS with 10K+ downloads. Built at SilverSky Technology.
My part:
Built live face verification for profile photos (Vision Camera, ML Kit)
Added 6 languages, including right-to-left Arabic
Made the app ~20% smaller by removing unused media and replacing heavy libraries
Stack: React Native, Vision Camera, Google ML Kit, i18n
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 my latest design project: Nexus 📊
Nexus is a B2B SaaS landing page designed to make discovering business data metrics and exploring deal pipelines completely seamless. The main focus was to break down complex enterprise data trackers into a clean, minimal, and frictionless web user journey.
From smooth dashboard preview features to a transparent pricing tier selection flow, every section is crafted with close attention to clear visual hierarchy and layout consistency.
Making enterprise data trackers feel frictionless is a real win, Zubair. The dashboard previews and transparent pricing flow show smart information architecture. Clean, confident work.
New project out!
here's the link: https://www.behance.net/gallery/256870005/Migo-Private-Social-Mobile-App-UXUI
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.
