The reply can begin quickly while the useful thing still arrives late.
A different clock
Voice products commonly measure how quickly sound starts coming back. That matters, but it can reward an immediate sentence that merely narrates work still waiting to happen.
We now look at the full interval: approval to executed action, background job to delivered result, open loop to closed loop and tool call to usable answer.
The tail is where trust goes
The operating view uses the median and the slow tail rather than one flattering average. A result that usually arrives in seconds but occasionally disappears for a day is not dependable.
This is an internal measure, not a public performance claim. Its purpose is to make the uncomfortable waits visible to the people building the product.
Language is part of latency
The shortest route to meaning is sometimes a systems improvement and sometimes an edited sentence. “Two things need you” can be more useful than a fast inventory of everything SA‑NT checked.
That is why voice presence, comfortable silence and operational latency belong to the same design problem.
