Blog

Notes from building CatMD.

Engineering, design, and applied research from a solo founder shipping a cat AI that tries not to sound like one.

A thoughtful cat sitting at a small writing desk in soft afternoon light — hero illustration for an essay on the architecture of believable cat AI voice
Engineering · 11 min

Cat AI is going to be slop. Here’s how we tried not to be.

A 4-tier voice quality gate, a 15-mood daily lottery, pop-culture voice modes, and 17 rounds of audit. The architecture behind a cat AI that tries not to sound generic.

A dignified cat in a softly-lit drawing room beside a small stack of books — hero illustration for an essay on translating HCI research into cat AI voice modes
Applied research · 7 min

From Natsume to Bridgerton: how an HCI paper changed our cat AI

An HCI paper validated defamiliarization as the lever for non-mundane LLM cat voice. Their reference set was 1906 Japanese literary fiction. We translated it to pop culture our users actually recognise.

A cat curled on the corner of a wooden desk next to an open laptop in late-afternoon light — hero illustration for a build log on shipping an AI app solo in 14 days
Build log · 9 min

I shipped a cat AI app in 14 days with Claude as pair programmer. Here’s the playbook.

Solo dev, Singapore-based, zero outside funding. From create-expo-app to Google Play production in fourteen days. The workflow, the audit loop, what Claude was good at, what it wasn’t.