Skip to main content
In plain terms: Forge is organized as a stack of layers, each with exactly one job. Lower layers handle trusted inputs and the model of the ship; higher layers handle reasoning, checking, and learning. This page is the map; each layer has its own page.

Three operating principles

Every layer below exists to serve one of these three principles:
  1. Sources have authority. Every claim cites. Nothing the system asserts is ungrounded.
  2. Decisions are first-class objects, not log lines. Every decision is recorded with its full reasoning context and is replayable.
  3. AI proposes; humans decide; the gate is structural. Anything touching class, USCG, or safety always reaches a human.
See Where Humans Stay in Control for the plain-language version.

The layer stack

Forge is organized as layers, each with one responsibility:
LayerNameWhat it does
L0Source & Authority RegistryClassifies every input by authority, version, access policy, and ownership
L1Ingestion & NormalizationTurns PDFs, CAD metadata, BOMs, rules, and prior files into traceable objects
L2Maritime Design OntologyThe connected model of vessels, systems, rules, drawings, materials, and evidence
L2.5Engineering Decision LedgerThe queryable record of why every decision was made
L3CAD & Geometry World ModelDeterministic geometry: measurements, clashes, clearances, tolerances
L4Rules & Applicability EngineApplies ABS, USCG, IACS, IMO, owner, and yard rules with citations
L5Capability Catalog & AgentsThe versioned menu of moves the AI is allowed to make
L5.5(within L5) Confidence & AbstentionLow-confidence outputs abstain, gather more context, or route to a human
L6Verification LadderOrdered checks from citation to class/USCG review and final sign-off
L7Outcome ObserverCaptures real outcomes, rework, supersession, and improvements
A useful way to read the stack: L0 to L2.5 is about getting trustworthy data in and modeling it. L3 and L4 compute facts and apply rules. L5 to L7 govern what the AI does, check it, and learn from the results.

The two clocks, mapped to layers

The Two-Clock Problem shows up directly in the architecture:
  • The state clock (“what exists today?”) lives across CAD and the ontology (L2, L3).
  • The event clock (“why is it this way?”) lives in the decision ledger (L2.5).
Both are required to answer questions like “are we still compliant under the new rule version?”

A note on the diagram

The full system has a detailed architecture diagram (Forge DesignOS v0.2). If the visual diagram and this written spec ever disagree, the written spec is canonical; the diagram is a simplification.