Skip to main content
In plain terms: Forge is being built in stages. Each milestone lands a specific set of capabilities, and each one builds the clean data and the trust the next one needs. This page shows the roadmap and where we are on it.

​
The milestones

MilestoneThemeWhat lands
M0FoundationsDatabase schemas, per-yard isolation everywhere, source registry, event/audit logs, decision ledger schema, capability catalog schema, isolation tests
M1Rules & RetrievalABS / USCG ingestion pipeline, citation manager, basic rules retrieval, prior-vessel memory ingestion, structured UI skeleton
M2Governed DecisionsDecision ledger writes, rule applicability decisions, capability-gated agents, rule supersession events, re-evaluation queue
M3Geometry BaselineCAD metadata import, STEP / IGES geometry service, measurement records, simple clash and clearance checks
M4Verification & EvalOrdered verification gates, confidence filter, numeric geometry grounding, evaluation thresholds, isolation tests at scale
M5DesignOS PilotObserve-only deployment with a partner yard, build-readiness checklist, change-impact workflow, issue export, structured feedback
M6CAD-Aware IDEVisual model viewer, annotations, structured approval flows, ShipConstructor / AutoCAD exports where permitted

​
Where we are

M0 is in flight now. M5 is the first real-customer milestone.Keep this status line current as milestones complete. The Research Log tracks the week-to-week progress within each milestone.

​
How the path is ordered

The rollout follows the same logic as How Forge Fits: start where the leverage is highest and the risk lowest, then expand.
  • M0 to M2 establish the foundation: trustworthy sources, per-yard isolation, the data model, rules ingestion, the decision ledger, the capability catalog, and a basic UI.
  • M3 to M5 add geometry, enforce that numeric claims are grounded, route rule changes, and stand up the build-readiness workflows for a first pilot.
  • M6 and beyond add the CAD-aware IDE, connectors to existing CAD tools, local model fine-tuning, and the outcome-driven learning flywheel.
Throughout, the trust principle holds: the AI can retrieve, compare, draft, flag, and propose, but it never becomes the design authority. Structured human approval stays authoritative.