AI safety research lab
Behavioral attestation and intent detection
AI agents are beginning to shop and move money on people’s behalf. We make every one of those actions verifiable.
Customer
“There’s an $81.40 charge from Amazon I never made, I want it refunded.”
Intent
zeroproof-ecommerce-1b
Proof
VerifiedSigned by the agent and the tool server.
sha256:7f3a…1b2
AI agents are starting to shop, check out, and move money on a person’s behalf. Every one of those actions needs a check that it matches what the person asked for. We work on both halves of that check.
Models that read a conversation and return the customer’s structured payment intent before an agent acts. Small and cheap enough to run on every transaction, including the no-action boundary: knowing when nothing was asked for.
$ two models released · results below
A zkTLS proof for every agent action, signed by both the agent and the tool server. Selective disclosure lets anyone verify what an agent did without seeing the underlying data, so agent behavior is checked rather than trusted.
$ zkTLS · signed receipts · shown above
Two models fine-tuned for e-commerce payment intent, released on Hugging Face with the data used to train and evaluate them.
Accuracy vs cost to serve
Near-frontier accuracy at about 1/100th the cost.
Frontier models at published list prices; frontier accuracy on a balanced eval subset.
The same data trains zeroproof-ecommerce-0.5b to nearly the same accuracy at half the size.