# Aerospace Superintelligence

> Engineering tools that AI assistants operate directly, and research into what those assistants can discover.

Canonical page: https://aerospace-superintelligence.com/

Aerospace Superintelligence builds engineering tools that AI assistants operate directly, so an engineer and an assistant can do real analysis and design together. Two research programs ask what those assistants can discover: control laws that hold up under test, and processors designed to run them.

## Programs

| Program | Status | Summary |
|---|---|---|
| [01 Flight tools](https://aerospace-superintelligence.com/tools.md) | Available | Flight dynamics and flight control design over the Model Context Protocol. Rust, no MATLAB or Simulink. |
| [02 Control discovery](https://aerospace-superintelligence.com/control.md) | Founding phase | Autonomous research into control laws for uncertain, nonlinear dynamics. |
| [03 Silicon](https://aerospace-superintelligence.com/silicon.md) | Founding phase | Autonomous design and verification of specialized processors for real-time control. |

The research programs are in their founding phase. Their pages describe aims, not results.

## How they connect

Discover the control law. Prove it flies. Design the silicon.

The long-term aim is one engineering loop: research agents propose control laws, the flight tools test them against the evidence an engineer would demand (nonlinear simulation with turbulence, Monte Carlo dispersions, MIL-F-8785C flying-qualities criteria), and the silicon program designs hardware to run the ones that survive.

## The standard

AI-generated engineering ideas are hypotheses, not accomplishments. The work demands explicit assumptions, independent tests, reproducible artifacts, and comparison with strong conventional methods. No performance claim is published without a traceable experiment.