
Physical AI
Skill never dies. It compounds.
Evelyn Mora
We Are French Touch – Paris
Tech can’t scale without
Fashion, Art and Entertainment.



We further fine-tune our data with select consented expert data.
We build and capture the world.
Then the skill within it.
The world’s most guarded rooms are our training data.






VLGE · Spatial and human intelligence for physical AI
Retail runs on how people move.

- MerchandisingWhat gets picked up, compared and bought, through to the transaction
- RetailTraffic flow, dwell time, conversion by zone
- Interior designLayouts tested in the world before they are built
- Floor plansHot zones, dead zones, the paths people actually take
Brands fund the worlds and get the analytics · VLGE licenses the anonymized data
Robotics is a systems problem.
Factories and warehouses
- Robots rented by the hour
- Optimized for throughput and unit cost
- The bottom line decides
Art, luxury, entertainment
- Judged on execution and taste
- Every output carries a brand
- Experts define what good means
Harvey put lawyers in the loop of legal AI.
Physical AI needs the same for craft.
VLGE · We Are French Touch
Taste makes something ugly, silly, beautiful.
Illustrative. After the aesthetic triad (Chatterjee & Vartanian, 2014) and the arousal curve (Berlyne, 1971).
Tomorrow, value lives in branded data.
Spaces
Museums, stores, homes
Behavior
How people move, decide, buy
Expertise
The skill of a dancer, an artist, a craftsman
Branded data
The taste and essence of one named expert. Consented, attributed, licensed like IP.
Generic data trains capability · branded data trains taste
Timing, balance, expression.
Wrist IMU
Gaze · spotting
Joint angles
Floor contact
Pointe pressure
- BodyFull-body joint angles, balance, weight transfer
- ContactFoot, pointe and hand pressure on the floor
- TimingEvery movement locked to the music
- Gaze and effortSpotting in turns, EMG, breath
Consented demonstration → structured multimodal data
Pressure, angle, color judgment.
VLGE expert capture · retail luxury, makeup store
Consented demonstration → structured multimodal data
The judgment behind the hand.

Shared capture schema · vision, kinematics, physiology, context · 415 fields
Instrument the person, the task, the space.
Pink human reference · orange agent
One expert. A thousand runs.
run 1
run 2VLGE human-grounded agents · trained on real human behavior
One capture. Three ways to train.
Capture once. License, train and benchmark many times.
VLGE Human-Grounded Benchmark · real human capture as the reference
We Make Talent Profitable1/2
Expert talent
Real-world scenarios.






Immortal and
Licensable
in Perpetuity
From Experts, To Prime Agents.


attention
fingers
activity
Expert to Agents






Shared Capture Schema(applied to all domains)
Zd(t), Sd(t), …]
- W= world & object state
- B= body pose
- H= hand kinematics
- A= action stream
- Z= gaze & attention
- S= spatial sensors
- …= additional streams
- 𝒟= set of domains
- Sshared= shared schema
space (415 fields)
Shared extracted features(applied to all domains)
- trajectory smoothness
- speed profile
- dwell time
- action frequency
- ⋮
Skill-specific derived signals(domain-specific)
- blade speed
- cut angle
- grasp stability
- eye-before-cut
- …
- CoM rate
- route-read latency
- grip force
- slip risk
- …
different skill signals φchefskill ≠ φsportskill
With Human Prime Ground Truth Benchmark
to capture Branded IP and Copyright2/2
Proprietary human data
Real-world context.
Expert IP
Human expertise becomes
structured, reusable intelligence
fusion
representation
modeling
to machine capability.
Licensable intelligence
for AI & robotics
human behavior
on expert skills
machines and environments
Real-world impact.
Skill never dies.
It compounds.
Evelyn Mora · evelyn@vlge.com · vlge.com