From Hypersonics to AI Workflows: How Ursa Major Is Scaling Rocket Production

Engineering & simulationClaude Code2x or 3x output

Used to rapidly prototype and implement new slicer features, such as part-specific hatch patterns, by generating code from natural language prompts and editing the repository directly.

“I can go plug that paper into Claude code. I can give it our slicer repo, and say, hey, go and build this function in the, in our repo, and then I'll go test it out, so they'll go and build it, you know, uh, we'll verify that works.”

Engineering & simulationClaude CodeBuilt in one week

Used to build a full data fusion workflow and web monitor by pulling machine data via EOS APIs, creating a database, and generating a frontend interface without human software engineering assistance.

“this was 100% build with AI. So no real software engineer has helped. Um, but, uh, we're rebuilding this. for real now. Um, but I was able to prototype everything that we wanted and all the different functions and things like that.”

Engineering & simulationClaude Code

Used to train a machine learning model to detect specific defects, such as short feeds, in powder bed images to automate quality review processes.

“So I trained, uh, an ML model with Claude to detect short feeds, for example. Um, and so now, eventually, when that becomes more robust, now we can just automatically review every build and flag any short feed, and, you know, the operator can come in and check that.”

Engineering & simulationClaude Code

Used to analyze academic papers on scan strategies and generate corresponding code functions within the existing slicer repository to test new thermal management algorithms on hardware.

“So one is, you know, we talked about the Placer Development. A, you can use it to develop algorithms. And design of experiments and new functions. Very rapidly that we can go and test out. So I might say, hey, I read a paper about this new scan strategy.”