About

Founder and brand builder in Taipei, creating playful AI experiences at the intersection of literature, design, and human reflection. I’m interested in how bounded AI can make complex ideas more personal, memorable, and accessible—without replacing the original work.

Badges

Tastemaker
Tastemaker
Tastemaker 10
Tastemaker 10
Tastemaker 5
Tastemaker 5
Gone streaking 10
Gone streaking 10
View all badges

Maker History

  • Reel Crew
    Reel CrewTurn brand archives auto into reels with production memory
    Oct 2026
  • Fit Receipt
    Fit ReceiptA private fitting agent that knows when to call JEV
    Sep 2026
  • Second Eyes
    Second Eyes Automatically shortlist photos for faster publishing
    Sep 2026
  • Talk Me Out of It
    Talk Me Out of ItA virtual fitting room that gives you a second opinion
    Aug 2026
  • Odyssey: The Journey Home
    Odyssey: The Journey HomeAn AI literary journey where Homer remembers your choices
    Jul 2026
  • 🎉
    Joined Product HuntJuly 20th, 2026

Forums

•

12d ago

Reel Crew - Turn brand archives into reels with production memory

Reel Crew turns a brand's existing creative archive into a video production system that remembers. Gemini + Google ADK query production memory through ClickHouse MCP, plan a call sheet, and hand it to a deterministic renderer. Explore a recorded walkthrough of a completed run, hosted directly on Google Cloud Run. The public demo is a replay; fresh live generation is not currently available in this launch experience. Open source (Apache-2.0).

Vibe coding for physical products?

Vibe coding got people who'd never written code to try building apps. I keep wondering what those same people would make if getting started with a physical product felt more approachable.
Lately, my feed has been full of Astra and Opus 3D demos lately. I've spent eight years working in 3D, so seeing people describe something and start experimenting with a model is pretty exciting. Now I want to see what they'll create and how far their imagination stretches.
That's what we're working on at Autonomyware: you describe what you want to make and AI works through the design and engineering towards something buildable. Getting more people to try making their first physical product is a big part of why I'm involved.
So I'd love to hear from the people here building apps, websites, whatever else: have you ever wanted to make something physical and just had no idea where to start?
Tell me, what would you like to create?

Where should an AI fitting agent show uncertainty before recommending?

Fit Receipt keeps the person in control:
code protects product facts and pricing, while JEV weighs bounded trade-offs and shows uncertainty when the evidence is weak.

Where should an AI fitting agent explain its reasoning, and where should it leave room for personal preference?

View more