Let your AI agents pay their own way.Safely.
I'm Edward Zhou, a full-stack engineer of 13 years. I help teams design and build on-chain payments and spending controls for AI agents.
SERVICES
What I do
Prototyping
A working prototype of one agent-payment use case in 2–4 weeks.
DeliverableTODO: Running prototype, source code and a short handover document
Architecture review
What your agent can spend, what it can do, and what happens when it fails.
DeliverableTODO: Written review with prioritised risks and recommended controls
Technical due diligence
An independent read on a project's contracts and architecture, for investors or teams.
DeliverableTODO: Due-diligence report with findings and a clear verdict
WORK
In progress
In progress
An agent wallet with spending limits and an audit log. The agent pays on its own, gets stopped when it goes over budget or out of scope, and every payment is traceable.
- Budget limits per agent, per task and per time window
- Payments outside budget or scope are blocked before they settle
- Every payment lands in an audit log you can trace end to end
ABOUT
About
I've built software in Australia for many years, across front end, back end and production operations. Yunshu AI is my independent practice. I take on a small number of technically demanding projects, and work in both English and Chinese.
Stack
- TypeScript
- Solidity
- Node.js
- React
- PostgreSQL
- AWS
- x402
- ERC-8004
CONTACT
Got an idea? Let's talk for 20 minutes.
No charge, and you'll get short written notes afterwards.
- hello [at] yunshu.ai
- GitHub
- github.com/edxzh
- linkedin.com