A multimodal voice companion creates an awkward product tension: users want to ask “What am I looking at?” without granting an AI system indefinite access to their camera.
The easiest implementation—forwarding frames continuously—also creates hidden costs. It increases data transfer and model work, makes visual context harder to reproduce, and leaves users unsure when the companion is actually observing them. It can also produce a subtler correctness bug: the model answers from an old frame while speaking as if it can see the present.
A better default for many companion experiences is one-shot visual context:
The user deliberately shares one frame.
The application records when and why it was captured.
