The perceived latency starts from keydown, not keyup. Redefining latency to start at keyup reduces measured latency, not perceived latency, and delaying the visual display to keyup makes perceived latency strictly worse, not better. Even sticking with the keyup definition, just displaying the result as soon as it is available gives the possibility of negative (defined) latency.

What you said might be true and yet what OPs AI agent did wasn't measure latency of the service nor calculated a p99 for it.