cool stuff. I have cameras watching some animals and I've been working on real-time analytics for their behavior.

It looks like this is sending video signal off into the cloud? Are you sure people will be OK with this? Can I integrate it with local inference and lock it down?

Why can't this just run on a spare cellphone? Why the dedicated hardware?

I'd be curious to see some technical details on how you're routing b/w the user's prompt to the continuous monitoring. Are you purpose-building a tiny CV model for each prompt? Or are you running a big model continuously.