What you say, what you show and exactly where you point stay attached in one task packet, ready for your agent.
Building the interaction standard between people and AI agents.
Intent, evidence and exact reference, and timing arrive already attached. The agent is ready for the work, not another round of context reconstruction.
The agent receives what you mean, not only the sentence captured in that moment.
Screens, text, motion and notes arrive inside the same task they explain.
The exact region stays attached, so the target is visible without another description.
Source and evidence, time and speech keep the moment they belonged to.
The agent receives one ready packet containing what you said, what you showed and what you meant.
Speak it. Capture the evidence. Send the whole task.
Get early access