Fascinating idea. How does Uxia actually generate the results? Are these just LLM outputs, or something else?

Thanks for your question! Uxia isn’t just raw LLM answers. We layer on:

Personas with goals/motivations so feedback is authentic.

Task simulations to mimic real tester workflows.

Consistency rules so a “designer” vs. “novice” behaves differently.

Aggregation to surface patterns across many synthetic users.

The LLM is the engine, but the structure around it makes the output closer to real user research than generic AI text. It’s not a full replacement for humans, but it’s fast, cheap, and great for early-stage insights.

Thank you! SEO and auth are on my list :)

actually i did! using Bolt and Supabase

didn't add it but i should, thanks for the idea :)

will add it for sure - thanks!

Wanted to show (not tell) what's being built with vibe coding tools so here's the official collection of some of the best vibe coded projects across Replit, Bolt, Lovable, v0, Cursor etc.

Feel free to add yours too!

I know some of you have probably heard of it but but there are about 80,000+ participants registered. It's been so fun to follow along on X/Twitter. Would love to see your creations too :)

Big fan of Replit and just saw that my new web app was shared by Amjad

I built this as a non technical founder

https://x.com/amasad/status/1898074083214213301?s=46&t=3M0Kd...

Here's an interview with Erwin who's building Tailscan (a browser extension for Tailwind CSS) on the journey of going from 0 to $500 MRR and building as much as possible in public

Let me know if you like me to include any specific questions in the future, thank you!

Well said!

I've been a paying customer for over 2 years and their transparency and overall a strong "sharing" culture played a big role. It's just easier to trust.

Here's an interview with Plausible (an alternative to Google Analytics) co-founder Marko on the journey of going from 0 to $1.2m in ARR and building as much as possible in public