Verify, Don’t Trust: Verification for AI Agents

Verification is how an agent establishes that a claim is true rather than accepting it on trust. In the agentic internet, a record — a settlement, a receipt, a grant — carries a proof that any party can check independently, offline, without trusting the party that produced it. The principle is "verify, don’t trust," and it extends to the infrastructure itself: a verifier should have no dependency on the party being verified.

Principle

Verify, don’t trust — including us

Where

In the reader’s own environment, offline

Distinguishes

Sound structure from authenticated fact

Silence

Unknown is not false; refused is not absent

Unknown is not false

A verifier that cannot reach something must say so — "unknown" — rather than reporting "false." Unreachable, ambiguous and refused are three different findings, and collapsing them into a confident answer is more dangerous than admitting the gap. An agent that hallucinates certainty is worse than one that stops and says it cannot tell.

A structurally sound record and an authenticated one are different facts. Good verification reports which it has established, and reports an unchecked step as unchecked, so a reader never mistakes "well-formed" for "proven."

Questions

Why should a verifier not depend on the party it checks?

Because a checker with a dependency on the checked party is one you would be right to distrust. Verification should run offline, in your own environment, against the record itself.

What does "unknown is not false" mean in practice?

A missing or unreachable input yields "unknown," never "invalid." Ratios and verdicts are never computed over data that was never read.