How do you prove an AI model is really running locally? Task Manager shows the CPU spike and Windows Machine Learning profiling in VS Code confirms it — Foundry Local runs Phi-4-mini on a Developer Optimized Windows 365 Cloud PC to generate a meeting-summary app, and the finished app runs on the same local model, with zero cloud tokens spent to code it or to run it. ▶ Full episode: https://youtu.be/MK-hCq7Su1w ▶ Get started: https://aka.ms/windows365 #Shorts #Windows365 #FoundryLocal #CloudPC #MicrosoftMechanics