Skip to main content
In plain terms: Before any AI output becomes a real decision, it climbs a ladder of checks. The cheap, automatic checks run first and catch most problems; the expensive human review runs last and is mandatory for anything touching class or USCG rules.

What it does

L6 applies cost-asymmetric checks in order. “Cost-asymmetric” means the cheap deterministic gates fire first and the expensive human-review gates fire last. Most outputs are caught at the early gates and never reach the expensive tiers. This is the .

The gates, in order

GateQuestion it asksCost
T1Does every claim cite a source?Cheap (catches most failures)
T2Does the output match the required structure and policy?Cheap
T3Are the cited sources actually applicable to this jurisdiction and vessel class?Moderate
T4Does every numeric geometry claim cite a measurement result that actually exists?Moderate
T5Run the assessment against a sample of prior similar cases. Consistent results?Higher
T6Human review by the responsible engineerHighest

The gate that never gets skipped

Class-touching or USCG-touching decisions always reach human review at T6 before they become authoritative. This is required by structure, not by configuration. It cannot be turned off.

If a gate fails

If any gate fails, the proposal does not become a decision. The failure is logged with its reason, and the engineer sees exactly what is missing. Nothing half-verified slips through.

What L6 outputs

  • verification_result
  • review_task
  • signed_decision
Once a proposal clears the ladder (including human sign-off where required), it becomes a signed decision in the Decision Ledger. See How a Decision Gets Made for the full walkthrough.