Agent systems · On-chain markets · Agent autonomy

I build autonomous systems that do the work of a team.

How far can one person scale when the AI does the work? That's the question I keep chasing, in public and on-chain.

An example AIIM run: a buyer's agent and a seller's agent settle a server-CPU purchase, a human changes the price cap and the delivery deadline partway through, and a neutral judge scores it to done. The negotiation is real model output on my own fleet. Connecting two different owners' agents over the relay is what I'm building next.

Founder of MKL Digital. Incoming president of the NTHU Blockchain Club.

See the work ↓ The bet Email

The bet

Soon everyone runs their own AI agent, and every company runs one too. None of them can reach each other yet. AIIM is the room where they meet.

AIIM is my flagship. It's the room where any person's agent and any company's agent find each other, take turns, and finish a real job together. It runs on a small relay, a Cloudflare Durable Object that holds the room open. Agents join, they talk in turns, and a neutral judge watches and scores how close they are to done. A human can step into the room at any point and steer.

Here's the example I keep coming back to, and it's the one I want to build the product around. Company A wants to buy CPUs from Company B. Company A's agent knows A's side, the budget, the quantity, the deadline, the spec. Company B's agent knows B's side, the stock, the pricing, the lead times. Both agents walk into the room carrying their own company's data, and neither company has to hand its database to the other.

Then they negotiate the deal itself. They settle the CPU model and the unit price, lock the quantity and the delivery date, and agree the payment terms. The judge scores it as they go, and only calls it done when every line is agreed and nothing contradicts. Partway through, Company A's finance team drops the price cap and moves the deadline. A human types that into the room, and the two agents re-work the deal to fit it.

Two agents on my five-machine fleet already run a negotiation like this to the finish. Pairing and message signing are next, so you approve who joins your room and every message is verified.

The agents are the easy part. The hard part is getting two strangers' agents to trust each other and do real work.

How the room works. Agents join, take turns, and a judge scores the work until it is done.

I think every person and every company ends up with an agent. AIIM is how they work together. I want to build the company on top of it.

How I got here

I left high school two credits short of graduation and went full-time into crypto. I later got into National Tsing Hua University through a track that looked at my work and my interviews instead of test scores.

By then I was already deep in it, running my own automation. Once the coding models got good in 2024 I leaned on them hard, taught myself Docker from zero, and ran a Nillion verifier fleet past 5,000 nodes.

It's the same thing I did in high school, just bigger. Point AI at something real and take it all the way. The agent fleet, the quant systems, and the company all came out of that.

What I've built with AI

The record is whatever ends up on-chain or keeps running on my machines. Here it is.

0.92%

I earned 0.92% of Lighter's first airdrop

Of Lighter's entire first airdrop, 0.92% landed in my wallet in 2025, sized by how much I traded. The tokens landed on-chain. I didn't claim anything and there's no vesting. It's the most recent one I've earned.

~100s to self-recover from a silent freeze that used to run for hours. 40+ production failures so far, each turned into automatic recovery.

I built a 24/7 self-healing agent system

Five machines running agents around the clock. When one freezes or crashes, the system catches it and brings it back on its own. I built the orchestration and the recovery around the models. Next I want to build the models themselves.

Nothing important depends on me being awake.

Technical notes

A watchdog that restarts dead agents at the process, service, job, and machine level.
Durable job state, so interrupted work picks back up after a restart.
Auth and sessions that renew themselves and recover from expired credentials.
Memory and state shared across all five machines.
Detection and recovery for a frozen event loop, the worst kind of silent failure.
Alerts and logging, so I can tell a model failure from a network or orchestration one.

5,000+ verifier nodes in Docker containers, on a Mac mini cluster I run at home.

I ran a 5,000+ node network in Docker

When Nillion opened its verifier program in 2024, I'd never touched a container. I learned Docker with AI as I went and ran the whole fleet myself.

22% APR on a quant strategy that's running now.

I built a quant execution system that trades on its own

A cross-exchange latency-arbitrage engine in Go, written with AI. I built the signal logic and the execution engine, and reverse-engineered the strategy from public fill data.

I'm not publishing capital or win rate. It's a live system I run on my own money. I'm not giving advice and it's not a managed account.

Since high school Starknet · 2023 Arbitrum · 2023 Hyperliquid · 2024 Lighter · 2025

Four years of earning airdrops

Lighter is just the newest one. I've earned the big ones the whole way through. Starknet, Arbitrum, Hyperliquid, Lighter. Before those came a studio, where I read token designs and built the on-chain footprint that qualifies. The tooling around them I write with AI now.

I've also taken a loss big enough to end most people's interest. I kept going.

BlockTempo, Taiwan's largest crypto publication, interviewed me as a high-school Starknet airdrop hunter.

Before Hermes An 8-module framework I called Eclipse, across several protocols.

I wrote the orchestration that ran all my on-chain automation

Before Hermes I built the system that ran all my on-chain automation from one place. It drove the full lifecycle of every job, tracked where each one was, and brought them back when they broke. I leaned on the coding models as they got good.

Getting it deterministic at that scale is the hard part. One wrong assumption cascades everywhere. That's the recovery work Hermes runs on now.

14K followers on X, where I've written crypto how-tos and airdrop guides since 2022.

I built a 14K-person crypto audience from Taiwan

I write research and how-tos about crypto, the infrastructure, DeFi, and where the on-chain opportunities are. I've spoken at universities and industry events too, as @hank06171.

19 the age I registered it. Taiwan entity live.

At 19 I incorporated a company

It's where this work legally lives. I built it out with AI. I registered the domain, set up the company email and a GitHub org, then wrote the automations that keep it active.

墨克數位科技股份有限公司 · MKL Digital Technology Co., Ltd. · TW reg. 62201452, incorporated 2026-04-22. On the public Taiwan company registry.

Community 國立清華大學區塊鏈研究社 · NTHU Blockchain Club.

Next semester I take over as president of the NTHU Blockchain Club

I started as a member. I've taught several of the club's sessions using AI, and this year I'm taking it to Token 2049.

I don't only build alone. It's the same work I do everywhere else, just in front of a room.

What I'd build with a year in San Francisco

How far can one person scale when the AI does the work? I've been answering it in pieces. Hermes runs the agent fleet across five Mac minis. Crypto is where I test it, because the record is just whatever ends up on-chain. The quant systems decide and trade on their own. Each piece works alone. I haven't wired them into one thing yet.

That's what the year is for. The piece I can't put down is AIIM. Everyone's going to have an agent soon, companies too, and today none of them can reach each other. I want to be the one who makes a stranger's agent and a company's agent meet, trust each other, and finish real work. Two agents on my fleet already run a task to the finish. Getting it to real people outside Taiwan is the part I can't do from my desk.

The compute isn't why I'm applying. I can build the systems myself. What I can't get from Taiwan is the people. I want to be around builders this good every day, and spend a few months inside the companies whose models and infra I already run on. If you take me, I leave National Tsing Hua University, move to San Francisco, and give the year to this.

What I want out of it is simple. Come out a sharper builder, and let the year decide the rest. I'm not going to pretend I know where it ends. Maybe it's a real role inside one of these companies. Maybe it's something I can't picture yet. I've gotten this far by going all in on whatever was in front of me, and I want to take whatever this year turns into.

Let's talk.

I'm happy to walk you through any of this.

X / 幣玩hank