78/78
scoring cells matched exactly to the canonical engine
0
variance across repeated runs (deterministic output)
468
facial landmarks tracked per face
Minutes
footage deleted; only aggregate numbers are kept
What you can rely on today
Five things are true right now, each stated at the strength the evidence supports.
A reliable, reproducible engine
The shipped scoring core matches the canonical engine on 78 of 78 cells, exactly, and returns identical output on repeated runs. Run the same footage, get the same read, every time.
We measure the room, not the person
The read is aggregate attention, energy, and synchrony at the group level. No individual is ever scored, and the engine infers no emotion. It reads behaviour and geometry, never feelings.
Private by construction
Your footage is processed and deleted as soon as the analysis finishes. No faces are retained, only the derived aggregate numbers, so there is no individual record because none is ever created.
Grounded in the science
The attention, energy, and synchrony signals are built on cited behavioural-science literature and 468-landmark facial measurement, not invented metrics.
In step with the regulators
The engine infers no emotion, consistent with the EU AI Act position that emotion recognition lacks a scientific basis, and it fails closed on any emotion-framed output.
Held to an honest bar
Proof of Impact measures how a room responds. We hold the word impact to a pre-registered validation program rather than claim it before it is earned, and we publish the full record in the open, failures and all. That is the point of the name: proof you can check.