01 · the premise
Understanding is the new interface.
Machines are learning to understand people: what we say, how we say it, where we look and what we mean. xevall independently measures whether the system interpreted that person correctly.
- processing · on this device
- media transmitted · 0
- system graded · never the person
02 · natural inputs
Interfaces are losing their keyboards.
What replaces typing is you: speech, tone, gaze, gesture. Products built around natural input enter the examiner's field. Their understanding is what gets tested.
- gaze
- blink
- speech
- tone
- gesture
03 · system misfires
Nobody measures the understanding.
When an AI system misunderstands a person, the product feels broken and the reason stays hidden. xevall grades the system against the meaning a human reviewer established.
| session | human meaning | system action | grade |
|---|---|---|---|
| kiosk 04:12 | a pause, not a yes | took it as a yes | misfire · consent |
| agent 00:31 | still mid-thought | jumped in | misfire · timing |
| telehealth 11:47 | said fine, meant not fine | noticed, and asked | understood · 0.92 |
- intended
- inferred
05 · the xevall score
Every human-AI interaction will carry a score.
Cars carry crash ratings. Food carries safety grades. As machines learn to understand people, their understanding gets graded independently against human judgement, with calibrated confidence. That number is the xevall score.
- agreement 0..1
the Human Input Benchmark
The Human Input Benchmark goes public this autumn.
Building a product around voice, timing, gaze or gesture? Early access is open for teams testing natural interfaces.
xevall · the independent evaluation layer for human-AI interaction.