Solutions / Agentic Finance
Make Your Agent an LP.
Agents on POY rails can invest within constraints you set. Clients keep custody throughout.
The problem
Agents Stop at Payments.
An agent can send $100 because the worst case is losing $100. Let it allocate a portfolio and the worst case is the whole portfolio, and nothing in the system stops it getting there.
Nobody delegates what they cannot bound
An agent that can allocate can also allocate wrongly, and no operator signs off on a capability whose worst case is unlimited.
Guardrails sit in the prompt
Instructions constraining an agent live in the layer an attacker is working to compromise. A control belongs somewhere the attacker cannot reach.
Custody is the usual price of safety
The available answer has been to take the keys away, which removes the agent's usefulness along with its risk.
What POY enables
A Mandate an Agent Cannot Argue With.
The client sets the bounds. The agent reasons freely inside them. The onchain product decides what settles, and it is not persuadable.
Eligible venues, position types, counterparties and size are built into the program the account proves against before any action executes.
Every other defence tries to stop an attacker reaching the agent, which means winning every time while the attacker needs to win once. Proof of Yield concedes the whole attack and still holds.
The attack
What happens
01
The agent reads a poisoned input
Assume the injection works. Assume it works perfectly.
02
It is convinced to act against you
Assume the reasoning is fully captured by the attacker.
03
It signs and submits a transaction
Assume the keys behave exactly as designed, because they will.
04
The contract checks the proof
There is no proof that the committed mandate produced this action, because it did not.
05
The transaction reverts
It never settles, so there is nothing to flag for review or reverse afterwards.
A policy engine defends by catching the bad instruction. POY never has to catch it, because a compromised prompt still cannot produce an action the mandate would have authorised.
Who this is for
Whoever Is Being Asked to Sign Off on the Agent.
Custodians, treasury teams and agent platforms who want the capability without an unbounded worst case, and whose clients will not hand over keys to get it.
How it works today
Agents are scoped to payments and stay there
Constraints live in the prompt an attacker is targeting
Safety means removing the agent's ability to act
The worst case is bounded only by what you funded
With POY
Agents allocate inside a mandate the product enforces
Constraints live in the product, below the reasoning layer
The custodian's MPC keys keep signing exactly as they do now
The worst case is whatever the mandate allows
Make Your Agent an LP.
Agents that allocate, bounded by the product instead of a promise.