Pilache
Verified case
CASE04
Pilache
Storefront AI / Visit trendsJapan

Visits differed 2.6× between peak and quiet hours

The studio measured more than 1,800 monthly visits and used hourly demand to schedule classes and staff.

1,800+01

visits measured per month

2.6x02

peak vs quiet-hour visit gap

01Footfall
02By hour
03By day

Class times and staffing were set by feel

The studio set class times and staffing by feel, with no clear view of when people actually came in across the day and week. Quiet hours and peak hours blurred together, which made it hard to place classes and staff where demand really was.

Footfall broken down by hour and day to reveal demand

SpaceVision measured footfall at the studio and broke it down by hour and day. The result is a simple read of when visits cluster and when they thin out, running on-device with no personal data stored.

Classes and staffing now follow hourly visit demand

The studio scheduled classes and staff against hourly visit counts and now reviews the same metric in regular operating decisions.

Hour-by-hour visit data became the basis for operating calls

01

Scheduling

Places classes in the hours where demand actually is.

02

Staffing

Sets staff against busy and quiet hours as they really run.

03

Standing input

Uses the same visit data as a regular input for operating decisions.

Storefront AI