Zero Trust for Agentic Systems — trust, safety, and security for agents. @mvpzone
"8/8 Tests Passed," Said the Card We Wrote
The last card of the fix flow summarised the result. A pull request, opened. A signature, verified. And a compliance step with a green tick beside it.
The Door That Holds No Secret
The probe came back with an error: unable to parse the identity token. That was the result we wanted. The key we had been planning to store was doing nothing. That was the first thing our sign-in door stopped holding.
HTTP 200. enabled: true. Zero Rows.
The configuration call returned HTTP 200. The long-running operation reported done. We read the configuration back, and it said enabled: true. Then we drove real traffic through it.
We Said Trust Is a Computation. Ours Was the Wrong One.
A person signs in with a work account that their organisation manages. Everything about them checks out. Every model call they make comes back from our policy engine as Challenge, with a score of 0.29.
The Purchase Completed. There Was No Order.
A supervised purchase ran end to end. The agent built the cart, a human approved the cart mandate, the flow resumed and the run finished. No error. No retry. No warning in the log. The order view said: order not available.
A Record for Every Attempt
The reference deployment first ran in a production project in observe mode. The run finished with zero errors. Every act the deployment exists to show, including a tool outside the allow-list, a dangerous prompt and a search against an English-language rule, went through. Each one also left a record saying it would have been denied.