ty·Tony Yang

AI solutions architect & independent builder

Selected work / 2026

Hi, I’m Tony.
I build systems around AI.

Portrait of Tony Yang

I architect enterprise AI systems and build independent products. Coding agents help me move quickly; I own the specs, data boundaries, evaluations, and failure paths.

Explore my work Download résumé ↓
Independent apps, open-source tools, and ongoing experiments.New York, NY · open to relocating

01 / Selected work

Ideas, made real.

AI systems, open-source tools, and products
that started with a problem worth solving.

My Little Zoo Planet interactive 3D globe with 24 wildlife habitats01 / Live web app · mylittlezooplanet.org

My Little Zoo Planet

An interactive pixel-art planetarium and educational wildlife web app featuring 24 habitats across 7 continents and 71+ animals. Built with a Three.js 3D globe, animated Canvas 2D habitats, Kokoro TTS narration, WCAG AA accessibility, and a local-first, zero-tracking architecture.

Three.jsCanvas 2DKokoro TTSLocal-firstWCAG AA
BeeQuill official website showing its local-first meeting workspace01 / Official website · In development

BeeQuill

An early macOS app for bot-free meeting capture. It transcribes audio locally and stores notes in SQLite, with an offline workflow using Whisper and Ollama. Public downloads are still in development.

macOSLocal-firstWhisperSQLite
Whiskey Sensei official website with a prompt challenge and AI feedback02 / Official website · In development

Whiskey Sensei

An online learning product for prompt engineering and agent systems. I’m building hands-on lessons with rubric-guided AI feedback. Public signup is still in development.

AI learningAgent frameworksRubric feedback
security-audit: local scan with an example redacted finding03 / Local scan · Redacted findings

security-audit

An installable skill for coding agents that scans repositories locally. It checks 44 secret and vulnerability patterns, redacts findings before review, and exports Markdown, JSON, or SARIF.

Local scanRedacted findingsSARIFOpen source
Table Tennis SB live scoreboard with green and blue player panelsTable Tennis SB match history and set scoresTable Tennis SB player statistics, win rate, and achievements
04 / Official App Store screenshots

Table Tennis SB

Built for my child, who plays table tennis, to score matches and follow progress on iOS. I shipped it to the App Store using React, TypeScript, Firebase, and Capacitor for the iOS build, with Cursor supporting development.

iPhone & iPadLive scoringMatch analytics

02 / How I build

Start with the spec.
Design for real use.

I use coding harnesses to build applications and agents from clear specs, then check the data, tools, evaluations, and failure paths around them.

Make every boundary
explicit.

I own the architecture decisions: what an agent may read or change, how its output is checked, and how the workflow recovers when a dependency fails. Coding agents help implement and test those decisions.

How I build01 — 03

Define the user task and what success looks like.

Explore the steps ↑
01

Specify the job

Define the user task and acceptance criteria before choosing an agent or model.

02

Constrain access

Map data flows, limit tool permissions, and add approval before consequential actions.

03

Test the failure paths

Evaluate outputs, make errors visible, and preserve work for retry when services fail.

Coding harnessesAgent workflowsData boundariesEvaluationsFailure recovery

03 / The person behind the work

Curiosity is the
common thread.

I’m Tony. I’m most at home connecting a messy problem to a system that makes someone’s day a little easier.

My personal projects follow that curiosity: a better way to remember meetings, tools for reviewing code, and a scorekeeper for the sport my family loves. This site is about those independent projects, not my employment.

I write the specs and direct coding agents through implementation. I review the architecture, test the edge cases, and keep refining what fails.

NEXT CHAPTERNew York, NY · open to relocating

Open to AI architecture & product conversations

Have something
worth building?

Let’s make it real.