MenuClose
Intelligence that
never sees the cloud
Models that understand the design, not just the file in front of them.
No third-party frontier model ever sees your design. The models that touch IP are ours, and they run on your hardware.
IP-sensitive teams will not send RTL to a cloud service, whatever the model behind it. That is not a preference we accommodate - it is the precondition the whole architecture was built around.
Frontier models are used where they are safe to use: at the interface, for natural-language intent and explanation. They never receive the design. Everything that reads your RTL, constraints, power intent or netlists is proprietary and local.
Models per tool, not one for all
Each engine has a model trained on its own domain and its own deterministic feedback, so the advice is specific rather than generic.
Frontier models at the surface only
The CLI uses frontier models for natural-language intent and explanation. Routing, redaction and egress stay under our control.
Advisory is never signoff
AI output is architecturally separated from deterministic results. It is labelled, it is auditable, and it never enters a CI gate by default.
An assistant bolted onto a text editor sees one file at a time
Ours sits on top of 50 tools that already produce structured, machine-readable context about the design - netlists, clock domains, constraints, power intent, timing outcomes. The models act on that context rather than on raw text.
Every deterministic run is training signal.
Because the suite is ours end to end, every run produces a labelled, reproducible outcome the models can learn from. A wrapper over someone else’s software never gets that.
What is live, and what is not
The deterministic suite
All nine engines, built and functional. The design-partner beta ships deterministic only, with no AI in the initial release.
The ML layer
The models and the shared context they run on, across the suite. This is the layer currently being built.
We would rather ship a deterministic tool an engineer can trust than an AI feature they have to check. The order is deliberate.