Crystal Chang

Fit Receipt

Founder building playful AI experiences

#1004126732 followers 15 following

+3 stacked products

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.

Links

Github

Badges

Tastemaker

Tastemaker 5

Gone streaking 10

Gone streaking

View all badges

Maker History

Fit ReceiptA private fitting agent that knows when to call JEV
Sep 2026
Second Eyes Automatically shortlist photos for faster publishing
Sep 2026
Talk Me Out of ItA virtual fitting room that gives you a second opinion
Aug 2026
Odyssey: The Journey HomeAn AI literary journey where Homer remembers your choices
Jul 2026

🎉

Joined Product HuntJuly 20th, 2026

Forums

p/fit-receipt

•

5d ago

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?

•

2d ago

Fit Receipt - A private fitting agent that knows when to call JEV

Try on lingerie virtually; every pick has an AI judgment receipt. Fit Receipt is a reference implementation. The agent handles chat; code protects facts and pricing. JEV (TypeSafe) is a judgment model that scores trade-offs with calibrated confidence in ~300ms—not essays. Low-confidence results stay unresolved; judgments are recorded; works without JEV. Photos stay in your browser; no server photo storage. JEV sees typed fields, never the photo. Rate-limited API. Vercel + open source.

p/second-eyes

•

11d ago