Most AI conversations happen in decks. Mine happen in production.

I'm YY — COO of Laimi, building AI infrastructure for Asia's travel loyalty market. I run agent systems across multiple ventures and document what actually happens when AI meets real operations — not the theory, the friction.

YY Sng working on a laptop

What I Build

Agent systems. Running in production.

Laimi SEO Agent

building

An AI agent built by the Laimi Vietnam team to research, write, and optimise SEO content at scale — replacing a manual production process.

AI OS Brain

live

A personal AI brain built on Supabase with pgvector — stores insights, priorities, and context across all ventures. Every Claude session loads from it.

BD Research Agent

live

An agent that researches BD leads, classifies fit, and saves structured intel to Supabase automatically. Powers Laimi partner outreach.

Personal Content OS

live

The system behind my LinkedIn content — tracks post performance, runs weekly learning reviews, and generates new posts grounded in what actually worked.

Evergreen

live

A system that keeps personal brand websites alive by connecting them to a live data brain. Update your site by prompting an AI — no developer, no CMS, no redesign cycles.

Where I Operate

Three ventures. One operating system.

  • Laimi → AI-native travel infrastructure for Asia's loyalty economy
  • EzyCoaching → AI agent upskilling for teams and individuals
  • Evergreen Personal brand sites that update themselves via AI

Less AI theory. More AI in production.