Building with AI

From strategy to shipped product

AI expanded what a commercial operator can build independently. I use it to test assumptions, prototype workflows, ship products, and shorten the distance between strategy and execution.

I wanted to understand AI beyond presentations and strategy discussions, so I started building with it. These are not a software-engineering portfolio; they are evidence of an expanded operator toolkit.

WordGyms English Writing Coach

The problem: I wanted to test two hypotheses about how children learn to write: whether AI can coach in real time through repeated practice, and whether the model can help without ghostwriting.
The constraint: I deliberately set the product constraint that the model coaches but never ghostwrites: it can give feedback, hints, and scoring, but cannot write the answer for the child.
What I did: In 2025, I designed, built, and shipped WordGyms (wordgyms.com) solo and end to end: problem definition, UX, engineering, launch, and user acquisition. The stack includes Claude / OpenAI / Gemini APIs, prompt engineering and evaluation, MCP, agent workflows, Google OAuth, and Cloudflare.
The key finding: The hard part was not only model quality, but product economics: token cost affects margin, and bad output affects trust. AI lowered the cost of building, but it did not lower the cost of being wrong.
The result: WordGyms is live with real users. Standing on the API customer and developer side gave me a concrete view of what ecosystem partners need from a platform: docs, cost, model performance, integration experience, and commercial viability have to work together.

My AI Operating System

The problem: I am not an engineer, but I wanted to understand how far a commercial operator could move strategy, research, content, product experiments, and delivery forward with AI.
What I did: I built my own AI operating system: collaboration rules, task decomposition, cross-conversation memory, workflows, and automation skills that help move ideas faster toward validation.
The result: The system lets me independently move product prototypes, content architecture, and site delivery, turning AI from a tool list into a manageable execution system.

SMARD1 Rare Disease Care Hub

Non-profit · Pro bono

Roughly 60 confirmed cases worldwide. The real number may be far higher — many sudden infant deaths could be SMARD1 that was never genetically tested.

The problem: An ultra-rare disease has no commercial value, so nobody builds the information site — and the non-profits have no budget. Yet families need answers the moment the diagnosis lands, and almost nothing exists in Chinese.
My role: Pro bono. I used the skills I have to fill the gap the non-profit could not fund.
What I did: Thirty bilingual care articles — content, architecture, and SEO all my own — connecting two communities: rare-disease families and tracheostomy families.
The result: smard1.org is live and fully indexed by Google, reachable by Chinese- and English-speaking families worldwide.

Also: a Chinese astrology chart site, and this website itself (bilingual, self-deployed).

I don't stop at strategy. I build the systems - and increasingly, the products - that make it real

Get in touch