What does it take to go from a complex aerospace specification document to a validated, physics-correct simulation model - without writing a single line of code by hand? In this live webinar, we demonstrate the Dyad Agent capability using one of aerospace engineering's most richly documented benchmark vehicles: the NASA HL-20 lifting-body Personnel Launch System.
The HL-20, a hypersonic re-entry vehicle designed for crewed Space Station missions, comes with decades of NASA technical documentation spanning aerodynamics, inertias, guidance and control laws, and simulation trim cases. It is precisely the kind of complex, multi-domain system that exposes the limits of general-purpose AI code generation. In this webinar, we'll show how the Dyad Agent ingests that specification and autonomously constructs a validated Dyad model, enforcing physical correctness at every step through Dyad's compiler-backed constraint system - catching unit inconsistencies, conservation law violations, and type errors before simulation ever runs.
You'll see firsthand how agentic AI can reason over a real engineering document, select appropriate causal and acausal modeling strategies, and iterate toward a verified result - all without manual trial and error. We'll walk through what the agent does, where it self-corrects, and how the resulting model holds up against NASA's own published trim and dynamic check cases.
Whether you're an aerospace engineer, a simulation architect, or simply curious about where AI-assisted model-based engineering is headed, this session will give you a concrete look at what autonomous physical modeling can do today.
Key takeaways:
How the Dyad Agent interprets and ingests complex engineering specifications
Why constrained, compiler-verified modeling is essential for AI-generated physical models
A live demonstration of end-to-end model creation from NASA HL-20 documentation
How to validate AI-generated models against published reference data
