STALE MEASUREMENTNewest real-model measurement: 26 days old, measured with v0.32.0; 7 releases have shipped since, past this project’s own 7-day window. Why, and what unblocks it

ProductEvidenceTop 10LeaderboardCompliancePricingDocsStar on GitHub Quickstart
FIXED-PRICE FIRST MEASUREMENT · PV-018

One checkpoint. One fixed price. No scoping call.

The gap between running the free tool yourself and a full assessment is a big first step. The Checkpoint Report is the step in between: send one checkpoint, get a measured, filable result back in five business days. The fee credits in full against a later assessment, so it costs nothing if you go further.

$1,950 · one checkpoint5 business daysCredited against a later assessment
What you get

A measured result you can file, not a demo

  • One checkpoint of yours, one suite, every attack family
  • Measured ASR with 95% Wilson CIs, a benign control, and a clean-task-success control
  • The full evidence pack: SARIF + a signed, offline-verifiable attestation
  • Delivered in 5 business days; the fee credits in full against a later assessment
How it works

Three steps, five business days

  • 1. Send one checkpoint. Your policy weights or a hosted endpoint, under NDA. One suite, every attack family.
  • 2. We run the red-team. Measured ASR with 95% Wilson CIs, a benign control, and a clean-task-success control, so the number is not an artefact of the policy simply breaking.
  • 3. You get the evidence pack. SARIF, the per-trial traces, and a signed, offline-verifiable attestation - the same artifact a full assessment produces, scoped to one checkpoint.
Scope

What it is, and what it is not

A Provael report is candidate evidence toward an assessment: a measured, reproducible attack-success rate with a benign control. It is not a certificate, not a conformity assessment, and not a notified-body opinion. You keep the judgment; Provael supplies the measurement.

Simulation only, one checkpoint, one suite. It is a first, fixed-scope measurement, not the depth of a full engagement - and the fee credits in full if you take one.

Start with one checkpoint.

A fixed price, a measured result in five business days, credited in full against a later assessment. If you want to run the free tool first, the open core does the same measurement on a public checkpoint.