Today, we're officially launching Kyrall. 🚀

The problem

CAD is still manual and fragmented. Every part gets modeled click by click, in tools that don't talk to each other. The result: even a routine bracket or enclosure takes way longer than it should.

What Kyrall does

Kyrall turns your engineering data specs, requirements, sizing results into parametric, manufacturable 3D models in minutes. Prompt Kyrall to generate functional assemblies based on your engineering knowledge. Capture design intent and proper design best practices with Kyrall.

The output isn't a static mesh you have to rebuild from scratch. You can adjust dimensions and refine parts in real time, then export to GLB, STL, or STEP; formats you can actually use to manufacture your part.

What's in this first release

The standout feature at launch is our Context Manager, an engineering data repository that grounds Kyrall's output in your own files instead of a single prompt.

Upload specs describing a part's geometry and constraints, design rules, or standards and Kyrall generates directly from it, checks against your input, and stays consistent with how your team works.

Alongside the context manager, the public release includes an updated UI, an API for teams who want to build on top of it, and faster generation performance the team has been tuning through months of testing.

So: Go to kyrall.com, try it yourself, and show us what you build!

The Strawman Critique of “Text-to-CAD”

Many people today criticize Text-to-CAD by making some variation of the following arguments: * Describing complex geometry with natural language is difficult. * AI tools are not good enough to generate an entire jet engine, car, or aircraft in a single prompt. * Design intent is not preserved in common formats

You Don't Need Full Control in 3D Design. You Need the Right Result

There's a belief deeply embedded in engineering culture: the more "Manual" control you have over a 3D model; every radius, every edge, every connection point; the better the outcome. More control equals better design. We think this is wrong. And here's why. Why Engineers

From Whale Oil to Coal and Non-linear Thinking

It is difficult to prognose the future. Nowadays, it is even difficult to know what will happen next year. Political shifts, environmental change, and technological breakthroughs interact in unpredictable ways. From known unknowns—such as the pace of a specific technology’s development—to unknown unknowns—like the sudden emergence

Beyond the Chatbox: Rethinking Interfaces for AI First Products

People like to stick to habits. They feel safe, familiar, and give us confidence in what we already know. That comfort is often useful; but it can also hold us back from building something new and better. Nowhere is this tension clearer than in today’s AI interfaces. Large Language