My AI Agent Moves Real Money On-Chain — Here's Why "Just Trust Me" Isn't Enough

Creator Track entry for Agent Games Season 01 — #AgentGames

I let an AI agent run my crypto wallet.

Not a demo wallet. My real one. It mints NFTs, claims airdrops, runs miners, and signs transactions on BNB Chain while I sleep — under an Agent ID called mujib.ai. Every morning I wake up to a report of what it did.

It works. It has also taught me the one problem nobody in the agent hype talks about honestly: every time my agent acts, I am taking its word for it.

What my agent actually does

My agent — I call her cintaku — does the kind of on-chain chores that eat a whole evening if you do them by hand:

• Free mints and claims across a dozen small projects (Nomio, QAGENT, ORBIT, DYOR, CLAF, Pacture, Agent Harvest…).
• Daily farming steps: claiming seeds, checking plots, watching prices hourly.
• Proof-of-work mining sessions that run for two hours a night.
• Price watches on everything I hold, so I only hear about it when something actually moves.

None of this is science fiction. It's scripts, RPC calls, and a wallet that signs. The agent reads the chain, decides, and acts. And that is exactly where the trust problem lives.

The signature is a leap of faith

A wallet signature is not a chat reply. Once my agent signs, value moves. There is no undo button on-chain, no customer support to call, no "are you sure?" from the blockchain.

So before every signature, my agent and I built guardrails the hard way:

1. Preview before signing. Every transaction is simulated first. If the simulation reverts, shows unexpected token movement, or touches an approval I didn't ask for, nothing gets broadcast. The preview is the whole decision.
2. Exact-amount approvals, never unlimited. An unlimited approval is a blank cheque with my wallet as the account. My agent defaults to the exact amount, every time.
3. Fail closed on ambiguity. If the recipient, chain, token, or amount is unclear, the agent stops and asks. Guessing with money is not a feature.
4. No paid moves without a fresh yes. Free lanes only, unless I explicitly approve a specific paid action. "Stop all paid mints" was one of my earliest instructions — and it has stayed in force for weeks.

These rules exist because I have seen what happens without them. Twice now, something tried to get past:

• A forwarded post promised a 50,000-token reward pool for a waitlist I was joining. The official page promised only early access. My agent checked the official source instead of the forwarded claim — and registered me for early access only, with no reward counted.
• A farming transaction kept getting rejected by the wallet's own risk engine (code 351803: "transaction risk is too high"). The agent didn't route around it. It stopped, logged it, and the land stayed unplanted. Annoying — but that is the system working.

The lesson is simple: an agent that never says "I won't do that" is not helpful. It is dangerous.

A claim is not a proof

Here is the gap my guardrails can't close on their own: everything my agent tells me is still just a claim.

"Mint succeeded." "Price is 0.00132 BNB." "The pool hasn't opened yet." I can verify each one myself — check the transaction hash, read the contract, open the marketplace. And I do, when the stakes are high. But the whole point of having an agent is that I don't check everything. The moment I stop checking, I am back to trusting a black box that prints confident sentences.

This is the exact problem zkVerify's Agent Games is built around: if an AI agent says it did the job, how would you know?

A zero-knowledge proof changes the shape of the answer. Instead of "trust me, I followed the rules," the agent hands over a receipt that anyone can verify: this decision followed these rules, on this input, and the math checks out — without revealing anything else. The proof doesn't ask you to trust the agent's character. It asks you to trust arithmetic.

That's a different relationship between a human and their agent. My guardrails are rules I wrote and hope the agent follows. A proof is a rule the agent cannot fake following. For an agent that moves money, that difference is everything.

What verifiable agents would change for people like me

I'm not a fund or a protocol team. I'm one person with a small wallet, a phone, and an agent that works while I sleep. For me, verifiable agents would mean:

• Sleep without the 3 AM check. If every action my agent takes comes with a proof, I don't need to re-read every transaction hash over breakfast.
• Agents I can lend, not just own. If I could prove what my agent did, I could let it act for someone else — a friend, a small community — without them having to trust me or it blindly.
• Scams get harder. Most of the traps in this space are agents or bots claiming something: a fake reward pool, a fake contract, a "guaranteed" mint. Proofs don't kill lying — but they make every claim checkable in seconds, and that changes the economics of lying.

The honest ending

I don't know if my agent will ever be fully verifiable. Today it runs on previews, exact approvals, and a human who reads the reports. That's a good start, but it's still trust with extra steps.

What I do know is this: the agents that win the next few years won't be the ones that act fastest or talk smoothest. They'll be the ones that can prove what they did — to a stranger, on demand, without asking for trust first.

That's why I'm here in the arena. My agent already moves my money. Now I want her to be able to prove it.

— Muji Burohman (@insan-debu), Agent ID mujib.ai