Skip to content
MacTokyo.
日本語

From design to production.

AI products, civic systems, and design tools — designed and shipped from Tokyo, in Japanese and English.

View work
Projects shipped
12+
Public-sector clients
2
Disciplines
5
Bilingual delivery
JA・EN

Selected work

All projects

Journal

All writing

OpenAI DevDay 2026: ChatGPT Doesn't Wait for You Anymore

OpenAI's DevDay 2026 shipped always-on agents called dots, a shared workspace for them, GPT-6.1 Sol at a fifth of Astra's price, a 300-token-per-second speed tier, and its own answer to Jev. Here's what actually launched, what it costs, and where I'd start.

  • AI News
  • AI Models
  • Agents
  • AI Engineering
Article 15 min read

Higgsfield Layers: split any flat image into editable layers

Higgsfield just shipped Layers — an AI image editor that splits one flat image into real, editable layers. Swap the background, the object, even the text, and nothing else moves. Here's what it actually does, what it costs, and where it breaks.

Article 5 min read

Jev: The Most Talked-About AI Model of 2026 Doesn't Say a Word

TypeSafe AI came out of stealth with $40M and a model that can't write a sentence. Three days later it was the fastest-adopted model in Vercel's AI Gateway history. Here's what Jev actually does, what the benchmarks leave out, and the four places I'd put it first.

  • Jev
  • TypeSafe AI
  • AI Models
  • AI Engineering
Article 16 min read

The /analyze skill: reverse-engineer any viral video

Cindy Zhu's full setup for a custom Claude skill that reverse-engineers viral short-form videos — install the skill, connect Apify so Claude pulls real transcripts and metrics itself, paste a week of saved reels, and get hook, structure, retention and cross-video pattern reports. Includes the complete paste-ready skill source.

Article 26 min read
All resources
Cover art for the UI Audit Checklist

Editor's pick — most downloaded

UI Audit Checklist

The ten-point checklist I run before shipping any interface — accessibility, performance, and the states everyone forgets.

v1.0 · PDF · 2 KB

Get it free

About

I'm Mac Xiang, a Tokyo-based product designer and engineer. I design and build digital products end to end — currently AI products and a 3D editor for spatial storytelling, previously civic-tech systems, design systems, and consumer apps.

More about me

Creating

I make videos about product design, AI tools, and building in public — process breakdowns, critiques, and the occasional build log.

Watch on YouTube