Don't get me wrong, I love the idea. Installed it day one, played with skills, even wrote a few custom ones.
But on my actual messy desktop (20 Chrome tabs, 3 Office apps, VPN, weird folder structures), it fails ~40% of the time. Not because the model is dumb because the execution layer has no tolerance for real-world chaos.
A popup appears -> agent freezes
File name typo -> agent gives up
App not in foreground -> click misses
I know I could write more robust skills, but that defeats the voice and forget promise.
Two weeks ago I was in an off-site meeting when the client asked for a file on my office PC. I opened WhatsApp and texted my own computer: 'Find the Q1 projections and send it here.' Two minutes later it was in my chat.