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 dashboards show you the drop and leave you to dig for why. This one tells you: Safari checkout broke in Tuesday's deploy, 312 payments failed.
That's a same-day fix instead of a month-end surprise.
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
What if Sri Lankan tradition found its way into the LEGO app? 🇱🇰🧱
A small product design exploration.
Had a small idea and decided to visualize it. ✌️
I reimagined a few elements of Sri Lankan culture traditional dancers, masks, musicians, and instruments as brick built characters, then explored how they might live inside a LEGO style mobile experience.
Just a hypothetical design experiment combining culture, product design, and a little AI-assisted exploration.
Not affiliated with or endorsed by LEGO.
#ProductDesign #UIDesign #DesignConcept #DesignExploration #CreativeAI #SriLanka #SriLankanCulture #LEGO
That's awesome great job 🎉🎉
100+ people already use my free skill file to stop their AI from making the same 25 design mistakes.
Drop it into your project and your agent gets better at typography, spacing, color, and dark mode. Link in the comments.
I built an AI support-ticket router on Replit, then tested it against the real model. Three things broke that no mock would have caught.
A silent failure. The first run sent 33 of 40 tickets to "needs a person". The newer Claude model rejects the temperature setting, and my code swallowed the error, so every call quietly failed. Now every failed call is logged.
The model thinks before it answers. With a tight token limit, some tickets got no answer at all and some draft replies stopped mid-sentence. Both have room now, and a cut-off draft is never saved.
One incident looked like four bugs. Four Safari checkout failures each got a different issue key, so the "3+ tickets, same problem" alert never fired. Sorting tickets in arrival order and asking for keys that name the problem rather than the customer turned them into one flagged incident.
If you're adding an LLM feature to your product, test it on real inputs early. The failures are rarely where you expect.
Live demo: https://sorta--krishnanbhupath.replit.app
