Trusted by
Every other AI guardrail asks you to trust it: that it ran, that it wasn't bypassed, that the operator's word is good. PreFlight checks every agent action against your rules before it runs, blocks the ones that break them, and turns that trust into a receipt anyone can verify.
Try it risk free today | no credit card required | MCP enabled.
Built on the security foundations of cryptography and formal methods. Our peer-reviewed work spans verifiable inference and post-quantum commitments, presented at zkSummit and PQ Crypto 2026, featured at the NY Fed's Innovation Conference, and covered on the Zero Knowledge Podcast.
The agents can already draft, file, pay, and negotiate. The ceiling is trust: nobody can enforce, and then prove, that an agent followed the rules on the work that matters.
PreFlight does not recognize attacks. It checks the action against your policy. Model error, hallucinated clause, prompt injection, drifting agent: all fail the same check. It blocks the action the attack was for.
The wrong action never runs, and the receipt proves it.
The agent states what it wants to do, in the action text.
Your plain-English policy is translated to formal logic, checked for contradictions, and battle-tested before going live.
The agent's action either satisfies the policy or it does not. The decision is deterministic, not probabilistic.
A cryptographic, zero-knowledge proof is generated and verifiable in under a second, even across thousands of checks.
Every governance platform promises you can scale AI with confidence. Read the mechanism, and there is a human reading a dashboard inside it.
The agent runs at machine speed; the organization approves at the pace of inboxes. The gap between the two is work you cannot delegate.
The solver checks every action before it runs, at the speed the agent works, and the receipt proves it. Humans keep the two jobs that were always theirs: writing the rules, and judging the exceptions the rules route to them.
The volume of work you can govern stops being the volume a person can review.
PreFlight blocks the action, then hands you a receipt that leaves your trust boundary. A log is a statement your system makes about itself. The receipt is a statement the math makes about your system. Your auditor can argue with the first. Nobody argues with the second.
To believe a "deny" in your log, an outsider has to believe five separate things at once:
Self-attestation at machine speed is still self-attestation.
A mathematical artifact that cannot exist unless the computation happened:
A rule decides, not a model, and a gateway can stop the action before it runs. Several platforms now offer this, and it is the right foundation.
The system records that the rule fired. That record is generated, held, and presented by the operator, inside the operator's own infrastructure.
A third party checks the math themselves: no API key, no account, no access to your systems, on any stack, without ever seeing your policy or your data. This is the rung the receipt occupies.
Intent is fixed as a checkable predicate at the root. Every downstream agent, from the orchestrator to each sub-agent, proves conformance. One broken link surfaces before any action lands.
A variant of IVC · Incremental Verifiable Computation✓ The predicate propagates untampered. Every upstream agent stays clean. Only the drifting node fails.
Actions are only half of what agents produce. Verbatim is the same discipline for the words. Every price, date, and policy claim compiles into a decoding grammar, so the model is physically unable to generate a fact outside your spec. Not instructed not to. Unable to.
Ask about itDeterministic by construction, not by prompt.
"The domestic wire fee is $35.00."
Every character traced to a policy span.
Compile a policy, check an agent action, get a verdict and a receipt. No subscription, and public proof verification needs no API key.
Read the docsBring the policy stuck in review. We will count the rules that are checkable facts versus genuine judgment calls and scope a pilot from there.
Book a call