An Indiana aerospace shop got CAM programming from ~2 hours to 23 minutes
MSP Manufacturing in Bloomington, Indiana, uses an AI CAM plug-in to draft most of each program, with experienced programmers finishing and proving out the first run.
Evidence: Vendor-published Q&A with named company president. Source date: not stated · Checked 2026-10-23 · Tech: AI CAM plug-in (CloudNC CAM Assist), Mastercam-style CAM workflow
The problem
They couldn't hire enough skilled CNC programmers locally. Programming became the bottleneck, lead times grew, and they lost quotes.
What they did
Starting in July 2024, they put two of their best programmers on CAM Assist. The AI proposes operations and toolpaths, and the programmer reviews, edits and certifies the first part.
Reported results
The president says the AI handles 70-90% of programming on their low-quantity build-to-print work and that programmers can now handle at least five times as many jobs per day. His example: a part that took 1.5-2 hours was 80% done in 7 minutes, then finished in another 15.
Our take
This is the pattern we see in credible AI stories: AI as a first draft, a skilled human signs off. He's candid that it isn't perfect. The gains are biggest on one-off jobs where programming time dominates the cost. It's a vendor-published story, so ask any vendor to run your own recent parts in a trial.
Try this on Monday: Time your last ten programs. If programming is more than a third of the hours on short runs, an AI CAM trial is worth a look.
Brian Roemmele reports wiring an AI agent into an existing flexographic carton-box printing line, with small local models watching the machine and cameras feeding it visual data.
Evidence: Self-reported by the builder on X. Early, no independent verification yet. · via @BrianRoemmele
Brian Roemmele showed a Raspberry Pi with an attached camera running the open LLaVA 1.5 model locally to describe and recognize what passed in front of it.
Evidence: Hobbyist demo shared on X (2023). Not a factory deployment. · via @BrianRoemmele
Neo Industries, a small machine shop in Colleyville, Texas, used automatic production monitoring to see how much of each cycle every tool was responsible for, then optimized tool by tool.
Evidence: Vendor-published customer story with named shop owner.