AXLEKEYSBETAAxle Keys is being built in public, one practical layer at a time. The goal is not to promise every possible CAD feature at once — it is to prove a focused workflow and make it work reliably for a small number of object families before expanding.
The platform is live and working. The current focus is making the full model lifecycle work end to end — choose a System, create or import a model, configure it, organise parts, review outputs, and move it forward. Once that loop works reliably for a small number of object families, the rest of the platform becomes easier to build.
The Studio works. The platform is live. The infrastructure is in place.
This is the phase that proves the model. One strong System workflow is more valuable than many unfinished ones.
This phase succeeds when a model can move from Studio into a public surface without feeling disconnected.
A few principles that guide what gets built and in what order.
One complete, working, well-documented System is worth more than five half-built ones. The product should prove the model before expanding broadly. Phase 02 exists entirely to prove the core loop.
Every decision about what the platform can and cannot do is a product decision. Systems work because they have rules. A good configurator exposes the decisions that matter and protects the technical relationships underneath.
Every feature is evaluated against whether it makes the platform more callable — by people in Studio, by developers via API, and by agents via MCP. Callability is the long-term product. Agents are more useful when they work inside structure.
The roadmap will keep changing as the Systems become stronger and real users push models from idea to output. That is the point of building it in public.