I build AI software real teams rely on every day — not demos. A minimalist who subtracts until only the idea is left.
What I do
Build AI agents that don't fall over.
Software that decides and acts on its own — with safety rules enforced in code, not just hopeful prompts — so it's safe for money and compliance steps.
Ship whole products end-to-end.
From database to interface to billing, often solo or as the first engineer — multi-tenant systems that survive big rewrites.
Keep AI fast and affordable.
Predictable speed and cost through caching, model routing, and tested failure modes — not hype.
Teach it.
I design and run cohort courses on AI-assisted building. My rule of thumb: natural language is the source code.
Selected work
AI Agent Architect
May 2026 — PresentEngram
Recruited onto Anthropic's partner-architect track — an AI surfaced my open-source work as the recommendation, and the founder confirmed it publicly.
Founding Principal Engineer
Oct 2025 — PresentGAVIGO
I own the 'intelligence layer' of an app-launch platform, built ~98% solo across 353 commits. Apps open in under a millisecond.
Senior Full-Stack Engineer & Website Lead
Jul 2025 — PresentShe Sharp
Rebuilt New Zealand's largest women-in-tech platform (2,200+ members) from scratch, 86% solo and with zero broken links — then added AI mentor-matching on top.
Chief Technology Officer
Mar 2025 — PresentFemTech Weekend
Sole engineer behind China's first FemTech organisation's website — built it twice as it grew. Now powering their 2026 Shanghai summit (16 speakers).
AI Instructor & Mentor
Apr 2026 — PresentTechNest
Designed and solo-teach a 12-week AI course; students ship a real, working AI app by week 8.
Earlier — AI/ML lead at Sanicle (took it to an IBM Silver Partnership), CTO of period-equity startup FreePeriod, backend at ByteDance, and the #1 contributor on a New Zealand construction field app.
Things I've built
Recognition
UN CSW 69 Speaker
United Nations HQ, New York — presented Sanicle AI; drew IBM pilot interest
Outstanding Mentor Award
AI Hackathon Festival 2025 — 1 of 14 expert mentors, guided 11 teams (80+ people)
FemTech Excellence Award
FemTech China — plus UN Women FemTech Hackathon Outstanding Performer
Master's with Distinction
Master of Applied Computing, Lincoln University NZ — Dean's List, top 5%
What others say
Frequently asked
Who is Chan Meng?
Chan Meng is an AI Agent Architect & Full-stack Engineer based in Auckland, New Zealand. She builds production AI agents and full-stack platforms end-to-end — for paying customers, sensitive health data, and regulated work, not demos — and teaches AI-assisted building. She holds a Master of Applied Computing with Distinction from Lincoln University.
What does Chan Meng build?
She builds AI agents that act safely on their own, with guardrails enforced in code rather than hopeful prompts, and ships whole products from database to interface to billing — often solo or as the first engineer. Recent work includes a Māori-culture AI coach, an AI career agent, and a LangGraph storytelling agent.
What is Chan Meng's tech stack?
Her core stack is AI agents — Claude Code, Model Context Protocol (MCP), LangGraph, CopilotKit, and RAG — with TypeScript, Python, and Go. On the full-stack side she uses React, Next.js, and React Native on the front end, and Node.js, PostgreSQL, Drizzle, Redis, Cloudflare, Docker, and Stripe on the back end.
What are Chan Meng's most notable projects?
She rebuilt She Sharp, New Zealand's largest women-in-tech platform (2,200+ members), roughly 86% solo, and shipped one of the first Google News MCP servers just 35 days after the standard launched. Other flagship builds include Tam-AI-Ti, FanFic Lab, and Vitex — an AI career agent that scores a résumé against a job in under 30 seconds.
Is Chan Meng available for work or collaboration?
Yes. She takes on AI agent and full-stack development, technical consulting, speaking, and mentorship, with a focus on FemTech, cultural technology, and early-stage startups. Reach her at [email protected] or book a 30-minute call at cal.com/chan-meng/30min; she typically responds within 24–48 hours.
Where is Chan Meng based?
Chan Meng is based in Auckland, New Zealand, and works with teams across New Zealand, China, and the remote US. She is bilingual in English and Chinese, and spoke at UN CSW 69 at the United Nations headquarters in New York in March 2025.
Let's build
something
Hiring, collaboration, or AI-tooling advice — email [email protected] or grab a time below.