... Great question, this is core to making it usable. NeuralAgent doesn't just fire actions blindly: a reasoning model supervises execution, so when an action doesn't produce the expected result, it can detect that and recover or replan rather than charging ahead. The fast model handles the rapid execution; the supervisor is there to catch and correct. It's an area we're continually hardening, mistake recovery is honestly one of the hardest and most important parts of computer ... ... permission modes: Ask First , where it pauses and asks for your confirmation before sensitive actions, and Act Without Asking for when you want it to run uninterrupted. So you stay in control of what needs a human check versus

... then add tasks to your list and let AI plan your day around your symptoms and energy/focus levels. If things aren't going well later on (as it often happens!) you can click the "I'm struggling" button to replan your day based on your current energy and focus. Sometimes it may suggest that you push some tasks to tomorrow so you don't burn out, and will schedule in lots of breaks and wind-down time. Check ...

... Comment from Ghost Kitty(@ghost-kitty-9542159): Comment Deleted Comment from Pablo Campina(@pcampina): Hello everyone, I finally submitted the iOS version (which was not originally planned) because Apple didn't accept my standalone watchOS version. I replanned the project as they asked to have a companion iOS/watchOS app; I now have an iOS version tested and available on TestFlight . Regarding the watchOS version, it is failing during the upload process with error codes 65 or 70. This doesn ...