Skip to main content
In plain terms: Here is the whole life of one decision, start to finish. Suppose a yard is reviewing a fuel system layout for a new build, and wants to know whether it meets the current Coast Guard fuel-line clearance requirements.

The walkthrough

1

Trigger

The reviewing engineer opens the fuel system design and asks Forge for a “rule applicability assessment.”
2

The system gathers what it needs

Forge pulls the relevant USCG sections, the current fuel-line geometry (as actual measurements, not guesses), the prior similar systems on this vessel class, and the yard’s own internal standards.
3

It drafts a proposal

The AI drafts an assessment: which USCG sections apply, which measurements support the clearance claim, and which prior decisions on similar systems it is relying on as precedent.
4

Confidence check

If the AI is not confident enough (for example, it cannot find a measurement for a critical clearance), it stops and asks the engineer to supply the missing data. It does not guess. This is working as intended.
5

The verification ladder runs, cheap checks first

The proposal then passes through an ordered set of checks. The cheap ones run first and catch most problems; the expensive ones run last. in action:
GateQuestion it asksCost
T1Does every claim cite a source?Cheap
T2Does the output match the required structure and policy?Cheap
T3Are the cited sources actually applicable to this vessel and jurisdiction?Moderate
T4Does every numeric clearance claim cite a measurement that really exists?Moderate
T5Run it against a sample of past similar cases. Consistent results?Higher
T6Human review by the responsible engineerHighest
6

Decision signed

Once the human approves at T6, the assessment becomes a recorded decision with an , and the full reasoning behind it is preserved.
7

Outcome observed

Months later, when the vessel is in production, the real outcome is captured. Did the assessment hold up during the USCG inspection? Did the clearance match the as-built measurement? That outcome becomes a learning signal for the next time.

If any gate fails

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

Why the cheap-first order matters

Running the cheap, automatic checks first means most weak proposals are caught early, before anyone spends expensive human review time on them. The one place a human is always required is the final gate for anything touching class or USCG compliance. That review is never skipped.