Latest / Omni Talk Retail / The Future Of Retail Robotics: How Simbe's Tally Is Transforming Store Operations | Spotlight Series

Transcript

The Future Of Retail Robotics: How Simbe's Tally Is Transforming Store Operations | Spotlight Series · Omni Talk Retail

0:00
Foreign.
0:08
This
0:08
retail
0:09
Technology
0:09
Spotlight
0:10
podcast
0:10
is
0:10
brought
0:10
to
0:11
you
0:11
by
0:11
the
0:11
Omnitalk
0:11
retail
0:12
Podcast
0:13
network.
0:13
Ranked
0:13
in
0:14
the
0:14
top
0:14
10%
0:14
of
0:14
all
0:15
podcasts
0:15
globally
0:16
and
0:16
currently
0:16
the
0:16
only
0:17
retail
0:17
podcast
0:18
ranked
0:18
in
0:18
the
0:18
top
0:18
100
0:19
of
0:19
all
0:20
business
0:20
podcasts
0:20
on
0:21
Apple
0:21
Podcasts.
0:22
The
0:22
Omnitalk
0:22
Retail
0:23
Podcast
0:23
network
0:24
is
0:24
the
0:24
network
0:24
that
0:24
we
0:25
hope
0:25
makes
0:25
you
0:25
feel
0:25
a
0:25
little
0:26
smarter,
0:26
but
0:27
most
0:27
importantly,
0:27
a
0:27
little
0:27
happier
0:28
each
0:28
week
0:28
too.
0:29
I'm
0:29
one
0:29
of
0:29
your
0:29
co
0:29
hosts
0:30
for
0:30
today's
0:30
interview,
0:30
Chris
0:31
Walton.
0:31
And
0:31
I'm
0:32
Anne
0:32
Mazinga.
0:33
And
0:33
Anne,
0:34
I've
0:34
been,
0:34
I've
0:35
been
0:35
spouting
0:35
my
0:36
mouth
0:36
off
0:36
for,
0:36
I
0:37
think
0:37
it's
0:37
been
0:37
probably
0:38
about
0:38
the
0:38
past
0:39
six
0:39
months
0:39
now
0:40
or
0:40
so,
0:40
maybe
0:40
even
0:41
longer,
0:41
about
0:41
why
0:42
2025
0:43
is
0:43
going
0:43
to
0:43
be
0:43
the
0:44
year
0:44
of
0:44
the
0:44
robot.
0:45
Yeah,
0:46
I
0:46
know,
0:47
right?
0:47
I
0:47
already,
0:48
we
0:48
already
0:48
did
0:48
our
0:49
top,
0:49
you
0:50
know,
0:50
our
0:50
top
0:51
retail
0:51
headlines
0:51
of
0:51
the
0:52
year.
0:52
I
0:52
was
0:52
already
0:53
going
0:53
2024.
0:54
It
0:54
was
0:54
my
0:54
retail,
0:55
it
0:55
was
0:55
my
0:55
store
0:56
technology
0:56
of
0:56
the
0:56
year.
0:57
So.
0:57
I
0:57
know,
0:57
and
0:58
I,
0:58
I
0:58
took
0:58
umbrage
0:59
on
0:59
that.
0:59
I
0:59
feel
0:59
like
0:59
I
0:59
suddenly
1:00
got
1:00
preempted.
1:01
But
1:01
anyway,
1:02
in,
1:02
in
1:02
true
1:03
Omnitalk
1:03
fashion,
1:04
we
1:04
are
1:04
kicking
1:05
off
1:05
2025
1:06
with
1:07
the
1:07
leading
1:07
in
1:08
store
1:08
retail
1:09
robotics
1:09
provider.
1:10
So
1:10
it
1:10
is
1:10
with
1:10
great
1:11
pleasure
1:11
that
1:11
we
1:12
introduce
1:12
today's
1:12
guest,
1:13
Brad
1:14
Bolia,
1:15
the
1:15
co
1:15
founder
1:15
and
1:15
CEO
1:16
of
1:16
simbi.
1:17
Brad,
1:17
welcome
1:17
to
1:17
omnitalk.
1:18
It
1:18
is
1:18
wonderful
1:19
to
1:19
have
1:19
you
1:19
with.
1:19
Us
1:20
today,
1:20
Chris,
1:21
and
1:21
thank
1:22
you
1:22
both
1:22
for
1:22
having
1:22
me.
1:23
Yeah,
1:24
this
1:24
is
1:24
going
1:24
to
1:24
be
1:24
such
1:25
a
1:25
good
1:25
conversation,
1:26
Brad,
1:26
like
1:26
Chris
1:26
said,
1:27
we've
1:27
been
1:27
so
1:27
excited
1:28
to
1:28
do
1:28
this.
1:28
Simbi
1:29
has,
1:30
excuse
1:30
me,
1:30
had
1:30
a
1:30
huge
1:31
year
1:31
in
1:31
2024
1:32
and
1:32
I
1:32
can't
1:33
wait
1:33
to
1:33
see
1:33
what
1:33
happens
1:33
in
1:34
2025.
1:34
But
1:35
for
1:35
those
1:35
who
1:36
might
1:36
be
1:36
new
1:36
to
1:37
OmniTalk
1:37
or
1:38
they
1:38
haven't
1:38
followed
1:38
our
1:39
coverage
1:39
of
1:39
robotics,
1:40
which
1:40
is
1:40
seemingly
1:41
impossible,
1:42
give
1:42
us
1:43
a
1:43
little
1:43
background
1:44
on
1:44
Simbi
1:45
and
1:45
specifically
1:46
how
1:46
it
1:46
came
1:46
to
1:46
be
1:47
and
1:47
what
1:47
it
1:47
does,
1:47
if
1:47
you
1:48
don't
1:48
mind.
1:49
Yes,
1:49
absolutely.
1:50
SIBI
1:51
was
1:51
founded
1:51
with
1:51
this
1:51
mission
1:52
of
1:52
really
1:52
digitizing
1:53
physical
1:53
stores
1:54
through
1:54
automation
1:55
and
1:55
computer
1:55
vision.
1:57
In
1:57
fact,
1:57
our
1:57
technical
1:58
team
1:58
came
1:58
out
1:58
of
1:59
a
1:59
world
1:59
renowned
1:59
robotics
2:00
and
2:00
computer
2:00
vision
2:01
think
2:01
tank
2:01
that
2:01
was
2:01
in
2:02
Silicon
2:02
Valley.
2:02
And
2:03
I
2:03
had
2:03
spent
2:04
the
2:04
years
2:04
prior
2:04
building
2:05
several
2:05
companies
2:06
in
2:06
the
2:06
energy
2:06
and
2:07
utility
2:07
space,
2:08
solving
2:08
a
2:09
very
2:09
similar
2:10
kind
2:10
of
2:10
instrumentation
2:11
challenge
2:12
where
2:12
utilities
2:13
wanted
2:14
to
2:14
know
2:14
what
2:15
was
2:15
going
2:15
on
2:15
across
2:16
the
2:16
grid.
2:17
And
2:17
so
2:17
we
2:17
came
2:17
together
2:18
with
2:18
this
2:18
shared
2:19
belief
2:19
that
2:19
there
2:20
was
2:20
a
2:21
way
2:21
to
2:21
create
2:21
a
2:21
better
2:21
retail
2:22
experience
2:22
for
2:23
all
2:23
by
2:24
actually
2:24
knowing
2:24
what
2:24
was
2:24
happening
2:25
on
2:25
store
2:25
shelves.
2:26
And
2:26
in
2:27
2019,
2:27
or
2:28
I'm
2:28
sorry,
2:28
in
2:28
2015,
2:29
we
2:30
announced
2:30
the
2:31
concept
2:31
of
2:31
tally,
2:32
the
2:32
world's
2:33
first
2:33
shelf
2:34
auditing
2:34
and
2:34
analytics
2:35
robot.
2:35
And
2:36
if
2:36
we
2:36
fast
2:36
forward
2:37
to
2:37
date,
2:38
we've
2:38
had
2:38
the
2:38
unique
2:39
opportunity
2:39
to
2:39
work
2:40
with
2:40
nearly
2:41
40
2:41
different
2:42
retail
2:42
banners
2:43
and
2:43
deploying
2:44
Tally
2:44
in
2:44
about
2:45
five
2:45
different
2:45
countries
2:47
and
2:47
have
2:47
raised
2:47
more
2:48
than
2:48
100
2:48
million
2:49
in
2:49
venture
2:49
capital
2:50
specifically
2:51
focused
2:51
on
2:51
this
2:51
problem.
2:52
Well,
2:53
Brett,
2:53
okay,
2:53
I
2:53
gotta
2:54
ask
2:54
you,
2:54
okay,
2:54
so,
2:55
but
2:55
how
2:55
did
2:55
you
2:56
pinpoint
2:56
retail?
2:57
Like,
2:57
we
2:57
go
2:57
back
2:58
to
2:58
me,
2:58
like,
2:58
were
2:58
you
2:58
guys
2:58
all
2:59
sitting
2:59
around,
2:59
like,
2:59
were
3:00
you
3:00
sitting
3:00
around
3:00
a
3:01
bar
3:01
and
3:01
you're
3:01
like,
3:01
hey,
3:02
we've
3:02
been
3:02
doing
3:02
this
3:03
thing,
3:03
let's
3:03
go
3:03
into
3:03
retail.
3:04
Like,
3:04
how'd
3:04
that
3:04
come
3:04
about?
3:05
Yes,
3:07
you
3:07
know,
3:07
it
3:08
really
3:08
came
3:08
about
3:09
because
3:09
we
3:09
were
3:10
interested
3:11
in
3:11
leveraging
3:11
robots
3:12
that
3:12
could
3:12
do
3:12
automated
3:13
data
3:13
capture.
3:14
In
3:14
the
3:14
early
3:15
days,
3:15
we
3:15
looked
3:15
at
3:15
a
3:16
number
3:16
of
3:16
markets,
3:17
ret
3:18
building
3:19
and
3:19
construction,
3:20
sort
3:20
of
3:21
health
3:22
care.
3:23
But
3:23
the
3:23
retail
3:24
sort
3:24
of
3:24
pain
3:24
point
3:25
really
3:25
stuck
3:25
out
3:26
to
3:26
us
3:26
just
3:27
personally,
3:28
you
3:28
know,
3:28
our
3:29
own
3:29
personal
3:29
experiences
3:30
of
3:30
going
3:30
to
3:30
stores
3:31
and,
3:31
you
3:31
know,
3:32
a
3:32
couple
3:32
items
3:32
on
3:32
your
3:32
list
3:33
aren't
3:33
on
3:33
store
3:33
shelf
3:34
or
3:35
you
3:35
walk
3:35
into
3:36
a
3:36
store
3:36
and
3:36
you're
3:36
like,
3:36
which
3:37
of
3:37
these
3:37
20
3:37
aisles
3:38
is
3:39
this
3:39
product
3:39
actually
3:40
sort
3:40
of
3:40
located?
3:41
And
3:41
it
3:42
became
3:42
clear
3:42
to
3:42
us
3:43
that,
3:43
you
3:43
know,
3:43
these
3:44
stores
3:44
were
3:44
such
3:45
deep
3:45
fabric
3:45
to
3:45
our
3:46
lives
3:46
that
3:47
this
3:47
was
3:47
the
3:47
place
3:48
to
3:48
apply
3:48
our
3:48
energy.
3:50
That
3:50
makes
3:50
sense.
3:50
I
3:51
mean,
3:51
Ann
3:51
and
3:51
I,
3:52
the
3:52
reason
3:52
I
3:52
asked
3:52
you
3:52
that
3:52
question
3:53
is
3:53
because,
3:53
you
3:53
know,
3:53
and
3:53
I
3:53
headed
3:54
up
3:54
Target
3:54
Store
3:54
the
3:54
future
3:55
project
3:55
for
3:55
a
3:55
number
3:56
of
3:56
years.
3:56
And,
3:57
and,
3:57
and
3:57
we
3:57
agree
3:58
because
3:58
we
3:58
realized
3:59
doing
3:59
that
3:59
work,
3:59
like
4:00
how
4:00
little
4:00
data
4:01
actually
4:02
exists
4:02
in
4:03
understanding
4:03
the
4:04
physical
4:04
store
4:04
experience,
4:05
especially
4:05
in
4:05
comparison
4:05
to
4:06
E
4:06
commerce,
4:06
you
4:06
know,
4:07
I
4:07
would
4:07
call
4:07
out
4:07
too,
4:08
and
4:08
so,
4:09
you
4:09
know,
4:09
but
4:10
trying
4:10
to
4:10
design
4:10
a
4:11
system
4:11
of
4:11
interconnected
4:12
technologies
4:13
to
4:13
change
4:13
that
4:13
is,
4:14
Is
4:14
really
4:14
complicated.
4:15
So,
4:15
so
4:16
you've
4:16
talked
4:16
about
4:16
it
4:17
a
4:17
little
4:17
bit,
4:17
but
4:17
so
4:17
how
4:17
do
4:18
you
4:18
view
4:18
that
4:18
issue?
4:19
Like,
4:19
how
4:19
do
4:19
you
4:19
solve
4:19
that
4:20
problem?
4:21
Absolutely.
4:22
I
4:22
mean,
4:22
we
4:22
see
4:22
the
4:23
shelf
4:23
and
4:24
again,
4:24
the
4:24
shelf
4:24
is
4:24
where
4:25
the
4:25
vast
4:25
majority
4:25
of
4:25
consumers
4:26
are
4:26
making
4:26
their
4:26
purchasing
4:27
decisions.
4:28
But
4:28
we
4:28
see
4:28
this
4:29
as
4:29
kind
4:29
of
4:29
like
4:29
the
4:29
last
4:30
major
4:31
data
4:31
desert
4:32
in
4:32
the
4:32
world
4:32
of
4:33
physical
4:33
retail.
4:34
Right.
4:34
And
4:35
this
4:35
desert
4:35
is
4:36
not
4:36
just
4:36
affecting
4:37
retailers
4:38
themselves,
4:39
but
4:39
store
4:40
teams,
4:41
brands,
4:42
online
4:42
delivery
4:42
players.
4:43
And
4:44
as
4:44
a
4:44
business,
4:44
we
4:45
view
4:45
the
4:45
shelf
4:45
as
4:46
like
4:46
the
4:46
linchpin
4:47
to
4:47
the
4:47
whole
4:47
supply
4:47
chain.
4:49
So
4:49
with
4:49
the
4:49
advent
4:49
of
4:50
technology
4:51
like
4:51
autonomous
4:52
mobile
4:52
robots
4:53
and
4:53
you
4:53
know,
4:53
full
4:54
stack
4:54
sort
4:54
of
4:54
computer
4:55
vision,
4:55
we
4:56
have
4:56
this
4:56
world
4:57
where
4:57
we
4:57
can
4:57
actually
4:58
provide
4:58
true
4:58
visibility
4:59
and
4:59
know,
5:00
you
5:00
know,
5:00
precisely
5:02
the
5:02
XYZ
5:03
coordinates
5:03
of
5:03
every
5:04
product
5:04
in
5:04
a
5:04
store.
5:06
Are
5:06
products,
5:06
you
5:07
know,
5:07
properly
5:07
stocked?
5:08
Are
5:08
they
5:08
in
5:08
the
5:09
right
5:09
place?
5:10
Are
5:11
prices
5:11
in
5:11
promos
5:12
sort
5:12
of
5:12
accurate?
5:13
And
5:13
Using
5:14
this
5:14
newly
5:15
derived
5:15
data
5:16
set
5:16
fused
5:17
with
5:18
any
5:18
retailer
5:19
back
5:19
office
5:19
data,
5:20
right?
5:20
Their
5:20
inventory
5:21
data,
5:21
their
5:21
price
5:22
system
5:22
data,
5:22
their
5:22
point
5:23
of
5:23
sale
5:23
data.
5:24
This
5:24
combined
5:25
becomes
5:25
an
5:25
incredibly
5:26
powerful
5:26
lens
5:27
through
5:27
which
5:28
to
5:28
look
5:28
at
5:28
their
5:29
business.
5:30
But
5:31
Brett,
5:31
so
5:32
the
5:32
next
5:32
obvious
5:32
question
5:33
though
5:33
is
5:33
like,
5:34
how
5:34
do
5:34
you
5:35
expect
5:35
retailers
5:36
to
5:36
actually
5:36
use
5:37
that
5:37
data?
5:37
So
5:37
you're
5:37
collecting
5:38
all
5:38
this
5:38
data
5:38
from
5:39
the
5:39
data
5:39
desert
5:39
that
5:40
previously
5:40
was
5:40
the
5:41
shelf,
5:41
but
5:41
you
5:41
have
5:41
tally
5:41
going
5:42
on
5:42
in
5:42
the
5:42
store,
5:43
running
5:43
the
5:43
store,
5:44
seeing
5:44
what's
5:44
on
5:44
shelf.
5:45
How
5:45
do
5:45
you
5:45
expect
5:45
the
5:45
retailers
5:46
to
5:46
actually
5:46
use
5:46
the
5:46
data?
5:47
Because
5:47
that's
5:47
a
5:47
different
5:48
unlock
5:48
that
5:48
has
5:48
to
5:49
be
5:49
accomplished,
5:49
I
5:49
would
5:49
imagine.
5:50
Yeah,
5:51
absolutely.
5:51
And
5:52
the
5:52
data
5:52
that
5:52
we
5:52
collect,
5:53
I
5:53
mean,
5:53
there's
5:53
certainly
5:53
a
5:53
data
5:54
tsunami
5:54
here,
5:54
but
5:55
our
5:55
job
5:55
is
5:56
to
5:56
really
5:56
help
5:56
derive
5:57
intelligence
5:58
and
5:58
sort
5:58
of
5:58
action
5:59
out
5:59
of
5:59
it.
6:00
What
6:00
we
6:00
focus
6:00
on
6:01
first
6:01
is
6:01
really
6:02
empowering
6:03
the
6:03
front
6:04
line
6:04
of
6:05
workers,
6:05
you
6:05
know,
6:06
store
6:06
teams
6:06
that
6:06
are
6:06
actually
6:07
on
6:07
the
6:07
ground.
6:08
So
6:09
instead
6:09
of
6:09
them
6:10
looking
6:10
for
6:10
problems,
6:11
right,
6:11
performing
6:12
shelf
6:12
audits,
6:13
understanding
6:14
which
6:14
products
6:14
they
6:14
may
6:15
have
6:15
backstock
6:15
for
6:16
on
6:16
a
6:16
secondary
6:16
display,
6:17
etc,
6:18
these
6:18
are
6:18
all
6:18
things
6:19
we
6:19
automate
6:19
for
6:20
them.
6:21
So
6:21
which
6:22
products
6:22
should
6:23
they
6:23
put
6:23
on
6:23
a
6:23
pool
6:23
list?
6:25
Which
6:25
price
6:25
tag
6:26
should
6:26
they
6:26
go
6:26
change?
6:28
You
6:28
know,
6:28
where
6:28
are
6:28
there
6:28
sort
6:29
of
6:29
planogram
6:29
discrepancies
6:30
in
6:30
the
6:30
store
6:30
with
6:31
sort
6:31
of
6:31
changes?
6:32
So
6:32
we
6:32
start
6:32
with
6:32
the
6:33
store
6:33
teams
6:33
first,
6:35
but
6:35
the
6:35
layers
6:35
continue
6:36
to
6:36
bubble
6:36
up.
6:37
So
6:37
we
6:38
give
6:38
store
6:38
leadership
6:39
teams
6:39
sort
6:39
of
6:39
a
6:39
dashboard
6:40
where
6:41
really
6:41
for
6:41
the
6:41
first
6:41
time
6:42
in
6:42
their
6:42
history,
6:42
they
6:43
actually
6:43
know
6:43
what
6:43
their
6:44
true
6:45
on
6:45
shelf
6:45
availability
6:46
rates
6:46
are
6:47
and
6:48
how
6:48
their
6:48
stores
6:49
actually
6:49
stack
6:50
up
6:50
to
6:51
other
6:51
stores
6:52
throughout
6:52
the
6:53
chain.
6:53
And
6:53
then
6:54
it
6:54
continues
6:54
to
6:54
go
6:54
on
6:54
from
6:55
there.
6:55
I
6:55
mean,
6:55
certainly
6:56
this
6:56
data
6:56
is
6:57
bubbled
6:57
up
6:57
at
6:57
a
6:57
corporate
6:58
level
6:59
so
6:59
they
7:00
can
7:00
see
7:00
how
7:00
stores
7:01
across
7:01
the
7:01
chain
7:02
are
7:02
performing
7:03
and
7:03
leveraging
7:04
this
7:04
as
7:04
a
7:04
new
7:05
performance
7:05
sort
7:05
of
7:05
benchmark
7:07
sort
7:07
of
7:07
tool.
7:08
And
7:09
it
7:09
goes
7:09
beyond
7:09
that,
7:10
right.
7:10
As
7:10
retailers
7:11
have
7:11
begun
7:11
to
7:11
sort
7:11
of
7:11
scale
7:12
this
7:12
technology
7:13
across
7:13
their
7:13
footprint,
7:14
we
7:15
see
7:15
them
7:15
making
7:16
this
7:16
data
7:16
available
7:17
to
7:17
their
7:17
merchant
7:17
partners
7:19
and
7:19
others
7:19
within
7:19
their
7:20
ecosystem
7:20
as
7:20
well.
7:22
Well,
7:22
Brad,
7:22
I
7:23
have
7:23
to
7:23
ask
7:23
you,
7:23
and
7:23
I
7:24
know
7:24
you
7:24
might
7:24
be
7:24
a
7:24
little
7:25
biased
7:25
because
7:26
you
7:27
started
7:27
and
7:28
you're
7:28
running
7:28
a
7:29
robotics
7:29
company
7:30
right
7:30
now,
7:30
but
7:31
there
7:31
are,
7:31
there
7:31
are
7:32
a
7:32
lot
7:32
of
7:32
other
7:33
technologies
7:33
out
7:34
there,
7:34
a
7:34
lot
7:34
of
7:34
companies
7:35
who
7:35
agree
7:35
with
7:36
this
7:36
idea
7:37
that
7:37
you
7:37
have,
7:38
you
7:38
know,
7:38
like
7:38
that
7:39
the,
7:39
the
7:39
shelves
7:40
are
7:40
really
7:40
the
7:40
desert.
7:41
So
7:42
why
7:42
robotics?
7:43
Like,
7:43
can
7:44
you
7:44
dive
7:44
a
7:44
little
7:44
bit
7:44
more
7:45
specifically
7:46
into
7:46
why
7:46
you
7:47
think
7:47
that
7:47
that's
7:48
the
7:48
best
7:48
answer
7:49
for
7:49
really
7:50
improving
7:50
the
7:50
data
7:51
quality
7:51
that
7:51
retailers
7:52
can
7:52
get
7:52
out
7:53
of
7:53
their
7:53
stores?
7:54
And
7:54
then
7:54
even
7:55
more
7:55
examples,
7:56
I
7:56
guess,
7:56
because
7:57
I
7:57
think
7:57
that's
7:57
always
7:58
the
7:58
important
7:58
part
7:58
to
7:58
hear
7:59
is
7:59
like,
7:59
what
7:59
is
7:59
this
8:00
actually
8:00
changing
8:01
for
8:01
the
8:01
stores,
8:01
for
8:02
the
8:02
store
8:02
associates
8:03
too?
8:04
Sure,
8:05
absolutely.
8:06
You
8:06
know,
8:06
we'd
8:06
say
8:06
from
8:07
our
8:07
experience,
8:08
you
8:08
know,
8:08
what
8:09
we've
8:09
been
8:09
able
8:09
to
8:09
prove
8:09
to
8:10
the
8:10
market
8:10
is,
8:11
you
8:11
know,
8:11
the
8:11
largest
8:12
number
8:12
of
8:12
chain
8:12
wide
8:13
adoptions
8:13
of
8:13
this
8:13
type
8:14
of
8:14
technology
8:15
and
8:15
sort
8:15
of
8:15
a
8:15
proven
8:16
ROI
8:16
model
8:17
that
8:17
sort
8:17
of
8:18
comes
8:18
with
8:18
it.
8:19
We
8:19
do
8:19
believe
8:20
strongly
8:20
that
8:21
robotics
8:21
are
8:21
sort
8:22
of
8:22
the
8:22
most
8:22
accurate,
8:22
comprehensive
8:23
and
8:23
cost
8:24
effective
8:24
way
8:25
to
8:25
drive
8:25
this
8:25
level
8:26
of
8:26
intelligence.
8:27
So
8:27
if
8:27
we
8:27
get
8:27
into
8:28
the
8:28
specifics,
8:29
we've
8:29
kind
8:29
of
8:29
compared
8:30
this
8:30
technology
8:31
head
8:31
to
8:31
head
8:31
to
8:32
back
8:33
office
8:33
AI
8:33
that
8:34
looks
8:34
at,
8:34
you
8:35
know,
8:35
point
8:35
of
8:35
sale
8:36
data
8:36
signals.
8:37
We've
8:37
compared
8:38
this
8:38
to
8:38
E
8:38
commerce
8:39
data
8:39
and
8:40
sort
8:40
of
8:40
mispicks.
8:41
We've
8:42
compared
8:42
this
8:42
to
8:43
employee
8:43
driven
8:44
whole
8:44
shoots,
8:44
employee
8:45
driven
8:45
photo
8:46
capture
8:47
and
8:47
sort
8:47
of
8:47
standalone
8:48
sort
8:48
of
8:48
fixed
8:48
cameras.
8:49
And
8:50
what
8:50
we
8:50
found
8:51
is
8:51
sort
8:51
of
8:51
the
8:52
accuracy,
8:53
the
8:53
frequency
8:54
and
8:54
the
8:54
fidelity.
8:57
The
8:58
other
8:58
solutions
8:59
aren't
8:59
really
8:59
sort
8:59
of
9:00
comparable
9:01
because
9:02
we're
9:02
actually
9:02
seeing,
9:03
sensing
9:03
and
9:04
decoding
9:04
what's
9:05
actually
9:05
happening
9:05
on
9:06
you
9:06
know,
9:06
these
9:07
physical
9:07
store
9:08
shelves
9:09
at
9:09
a
9:09
very
9:10
sort
9:10
of
9:10
frequent
9:10
basis.
9:11
It's
9:11
not
9:12
depending
9:12
on
9:12
labor,
9:13
it's
9:13
not
9:13
depending
9:14
on
9:14
sort
9:15
of
9:15
a
9:15
planogram
9:16
to
9:16
sort
9:16
of
9:16
perform
9:16
analysis.
9:18
We're
9:18
decoding
9:19
every
9:20
barcode,
9:21
every
9:21
piece
9:21
of
9:22
optical
9:22
data
9:22
that's
9:22
on
9:23
a
9:23
shelf
9:23
tag,
9:24
identifying
9:25
every
9:25
product,
9:26
every
9:26
hole
9:27
that's
9:28
sort
9:28
of
9:28
in,
9:28
in
9:28
the
9:29
space.
9:29
So
9:30
you
9:30
know,
9:30
we've
9:31
really
9:31
had
9:31
the
9:31
chance
9:31
to
9:31
kind
9:32
of
9:32
put
9:32
this
9:32
head
9:32
to
9:32
head
9:33
against
9:33
everything
9:34
in,
9:34
in
9:35
sort
9:35
of
9:35
industry
9:35
sort
9:35
of
9:36
out
9:36
there.
9:36
And
9:37
I
9:37
think
9:37
what
9:38
further
9:38
emphasizes
9:39
this
9:39
point
9:40
is,
9:40
you
9:40
know,
9:40
we've,
9:41
we've
9:41
stepped
9:41
into
9:42
stores
9:42
that
9:42
have
9:42
been
9:42
around
9:42
for
9:43
decades,
9:44
right?
9:45
And
9:45
by
9:45
stepping
9:45
into
9:46
these
9:46
stores
9:46
and
9:47
reducing
9:47
out
9:47
of
9:47
stocks
9:48
by
9:48
like
9:48
60%,
9:50
reducing
9:51
price
9:51
errors
9:51
by
9:51
90%,
9:53
you
9:53
know,
9:54
having
9:54
this
9:54
level
9:54
of
9:55
impact
9:55
for
9:56
stores
9:56
that
9:56
have
9:56
tried,
9:57
you
9:57
know,
9:58
all
9:58
of
9:58
these
9:58
different
9:59
sort
9:59
of
9:59
technologies,
10:01
there's
10:01
really,
10:02
really
10:02
deep
10:03
benefit
10:03
there.
10:04
And
10:06
you
10:06
know,
10:07
we've
10:07
been
10:07
able
10:07
to
10:08
demonstrate
10:08
proven
10:09
results,
10:09
not
10:10
just
10:10
help
10:10
you
10:11
identify
10:11
the
10:11
out
10:11
of
10:11
stocks
10:12
and
10:12
the
10:12
pricing
10:12
errors,
10:13
but
10:13
act
10:13
on
10:14
them.
10:15
So
10:15
verify
10:15
that
10:15
action's
10:16
really
10:16
being
10:17
taken.
10:18
And
10:18
not
10:18
only
10:19
that
10:19
action's
10:19
being
10:20
taken,
10:20
but
10:20
what
10:20
does
10:21
this
10:21
mean
10:22
as
10:23
a
10:23
benefit
10:23
to
10:23
the
10:23
business
10:24
from
10:24
things
10:24
like
10:24
a
10:24
margin
10:25
standpoint?
10:27
Brad,
10:27
there's
10:28
a
10:28
couple
10:28
of
10:28
things
10:28
I
10:28
want
10:28
to
10:28
call
10:28
out
10:29
that
10:29
you
10:29
just
10:29
said
10:29
there
10:29
that
10:29
I
10:30
think
10:30
are
10:30
really
10:30
important
10:31
for
10:31
our
10:31
audience
10:31
to
10:31
make
10:31
sure
10:32
that
10:32
they
10:32
hear.
10:33
One
10:33
is
10:33
that
10:34
you're
10:34
basically
10:34
saying
10:35
that
10:35
from
10:36
an
10:36
accuracy
10:36
perspective,
10:37
robotics
10:37
are
10:38
the
10:38
best
10:38
solution
10:39
in
10:39
your
10:39
mind.
10:40
And
10:40
also
10:40
from
10:40
a
10:42
capital
10:42
cost
10:43
standpoint,
10:43
Also
10:43
one
10:43
of
10:44
the
10:44
most
10:44
cost
10:44
effective
10:45
solutions
10:45
as
10:45
well.
10:46
But
10:46
the
10:46
other
10:47
piece
10:47
of
10:47
it
10:47
that
10:48
you
10:48
said
10:48
that
10:48
I
10:48
want
10:48
you
10:48
to
10:49
talk
10:49
about
10:49
more
10:49
because
10:50
this
10:50
was
10:50
the
10:50
unlock
10:51
for
10:51
me
10:51
when
10:52
I
10:52
think
10:52
a
10:52
mutual
10:52
friend
10:53
of
10:53
ours
10:53
opened
10:54
my
10:54
eyes
10:54
to
10:54
this
10:55
when
10:55
he
10:55
said
10:56
the
10:56
beauty
10:56
of
10:56
the
10:56
robot
10:57
too
10:57
is
10:57
that
10:58
unlike
10:58
other
10:59
systems,
11:00
it
11:01
goes
11:01
into
11:02
a
11:02
store
11:02
and
11:03
it
11:03
does
11:03
it
11:03
the
11:03
same
11:04
way
11:04
every
11:05
single
11:05
time.
11:06
There's
11:06
no
11:06
human
11:07
intervention
11:08
that
11:08
mucks
11:09
with
11:09
the
11:09
system
11:10
design
11:10
of
11:11
that
11:11
data
11:11
capture.
11:12
Can
11:12
you
11:12
explain
11:13
what
11:13
that
11:13
means?
11:15
Absolutely.
11:16
So
11:17
one
11:17
of
11:17
the
11:17
beauties
11:18
of
11:18
leveraging
11:19
sort
11:19
of
11:19
an
11:19
autonomous,
11:20
autonomous
11:20
mobile
11:21
robot
11:21
platform
11:22
is
11:22
it
11:22
can
11:22
keep
11:23
up
11:23
with
11:23
things
11:23
like
11:24
changes
11:25
in
11:25
sort
11:25
of
11:25
the
11:25
store
11:26
layout
11:26
or
11:26
store
11:27
environment.
11:29
So
11:29
as
11:29
an
11:29
aisle
11:29
or
11:30
move
11:30
or
11:31
whether
11:31
what
11:32
products
11:32
are
11:32
on
11:32
a
11:32
shelf
11:33
may
11:33
change,
11:34
these
11:34
are
11:34
dynamic
11:35
sort
11:36
of
11:36
changes
11:36
that
11:36
this
11:37
type
11:37
of
11:37
technology
11:37
keeps
11:38
up
11:38
with.
11:38
It's
11:39
much
11:39
just
11:39
like
11:39
a
11:40
self
11:40
driving
11:40
sort
11:40
of
11:40
car
11:41
on
11:41
the
11:41
road.
11:42
So
11:42
that's
11:42
one
11:42
of
11:42
the
11:42
biggest
11:43
benefits
11:44
for
11:44
this
11:44
type
11:45
of
11:45
environment.
11:45
The
11:46
other
11:46
is
11:46
you're
11:47
largely
11:48
managing
11:48
sort
11:49
of
11:49
a
11:49
single
11:49
device
11:50
versus
11:51
thousands
11:52
of
11:53
cameras.
11:54
In
11:55
addition,
11:55
it's
11:56
not
11:56
sort
11:56
of
11:56
planogram
11:57
dependent.
11:58
I
11:59
think
11:59
we
11:59
all
11:59
recognize
12:00
that
12:00
planogram
12:01
level,
12:01
sort
12:01
of
12:02
execution
12:03
accuracy
12:03
in
12:03
the
12:04
industry
12:04
can
12:04
vary
12:04
immensely.
12:06
So
12:07
you're
12:07
kind
12:07
of
12:07
starting
12:07
off
12:08
on
12:08
the
12:08
wrong
12:08
foot
12:09
if
12:09
you're
12:09
depending
12:10
on
12:10
sort
12:10
of
12:10
a
12:10
product
12:11
location
12:11
model
12:11
that
12:12
doesn't
12:12
actually
12:12
represent
12:13
reality,
12:14
which
12:15
many
12:15
of
12:15
the
12:15
other
12:15
technologies
12:16
we
12:16
talked
12:17
about,
12:17
you
12:18
know,
12:18
do
12:18
depend
12:19
on.
12:19
On
12:19
that
12:20
sort
12:20
of
12:20
model,
12:21
we're
12:21
actually
12:21
analyzing
12:22
what
12:22
we
12:22
see
12:23
and
12:23
certainly
12:24
we'll
12:24
ingest
12:24
a
12:25
planogram
12:25
or
12:26
authorized
12:26
products
12:27
list
12:27
to
12:28
know
12:28
what
12:28
we
12:28
should
12:28
expect
12:29
to
12:29
be
12:29
in
12:29
store.
12:30
But
12:30
we're
12:30
really
12:31
sensing,
12:31
you
12:32
know,
12:32
what's
12:32
actually
12:32
happening
12:33
on,
12:33
on
12:33
physical
12:34
store
12:34
shelves.
12:35
Right.
12:35
Which
12:36
is
12:36
very
12:36
different
12:36
than
12:36
like
12:36
say
12:37
the
12:37
model
12:37
where
12:37
the
12:37
employees
12:38
are
12:38
using
12:38
their
12:38
device
12:39
to
12:39
take
12:39
a
12:39
picture
12:39
and
12:40
capture
12:40
this.
12:40
Because
12:40
then
12:40
the
12:41
employees
12:41
are
12:41
doing
12:41
it
12:41
differently
12:42
every
12:42
store,
12:43
every
12:43
hour
12:43
of
12:43
the
12:43
day,
12:44
depending
12:44
on
12:44
who
12:44
the
12:44
employee
12:45
is.
12:45
And
12:45
there's
12:45
a
12:45
turnover
12:46
in
12:46
retail
12:46
as
12:46
well.
12:47
So
12:47
it's
12:47
a
12:47
very
12:48
key
12:48
point.
12:48
But
12:49
you
12:49
know,
12:49
with
12:49
all
12:49
that
12:49
said
12:50
too,
12:51
it's
12:52
not,
12:52
it's.
12:52
Is
12:52
it
12:53
all
12:53
about
12:53
robotics?
12:54
Because
12:54
like
12:55
the
12:55
robotics
12:55
can
12:55
also
12:56
work
12:56
in
12:56
concert
12:57
with
12:57
other
12:57
technologies
12:58
or
12:58
other
12:58
systems
12:58
that
12:59
you've
12:59
already
12:59
talked
12:59
about.
12:59
So.
13:00
So
13:00
how
13:00
do
13:00
you
13:00
think
13:00
about
13:01
that
13:01
question?
13:03
Absolutely.
13:04
So
13:04
when
13:04
we
13:04
brought
13:05
TALLY
13:05
technology
13:06
to
13:07
market,
13:07
you
13:07
know,
13:08
we're
13:08
very
13:08
focused
13:09
on
13:09
sort
13:09
of
13:09
fast
13:09
moving
13:10
consumer
13:10
goods
13:11
stores
13:11
sort
13:11
of
13:11
initially,
13:12
but
13:13
we
13:13
were
13:13
getting
13:13
a
13:13
lot
13:13
of
13:14
outreach
13:14
from
13:14
environments
13:15
like
13:15
sporting
13:16
goods
13:16
or
13:17
environments
13:17
that
13:18
had
13:19
packaged
13:19
goods,
13:20
plus
13:20
sort
13:21
of
13:21
soft
13:21
lines
13:22
that
13:22
may
13:22
have
13:22
been
13:22
leveraging
13:23
rfid.
13:25
So
13:26
over
13:26
the
13:26
last
13:26
couple
13:26
years,
13:27
we
13:27
have
13:27
announced
13:27
a
13:27
version
13:28
of
13:28
Tally
13:28
that's
13:28
either
13:29
RFID
13:29
only
13:30
or
13:30
computer
13:30
vision
13:31
plus
13:31
RFID
13:32
as
13:32
well.
13:33
When
13:33
you
13:34
think
13:34
about
13:35
the
13:35
core
13:35
TALLY
13:36
platform
13:37
today,
13:38
our
13:38
goal
13:38
is
13:38
also
13:39
to
13:39
make
13:39
a
13:39
lot
13:39
of
13:39
these
13:40
systems
13:40
better.
13:41
So
13:41
when
13:41
you
13:41
think
13:42
about
13:42
your
13:42
average
13:43
grocery
13:43
environment
13:43
that
13:44
has
13:44
a
13:45
computer
13:46
assisted
13:46
ordering
13:47
system
13:47
or
13:47
computer
13:48
generated
13:48
ordering
13:49
system,
13:49
this
13:50
stream
13:50
of
13:50
data
13:50
is
13:51
only
13:51
going
13:51
to
13:51
make
13:51
those
13:52
types
13:52
of
13:52
systems
13:53
sort
13:53
of
13:53
much
13:53
better.
13:55
But
13:56
continuing
13:56
on
13:56
this
13:57
journey,
13:58
one
13:58
of
13:58
the
13:58
things
13:58
that
13:59
Simbi
13:59
is
13:59
actually
13:59
announcing
14:00
today
14:01
is
14:01
sort
14:01
of
14:01
this
14:01
concept
14:02
of
14:03
a
14:03
multimodal
14:03
store
14:04
intelligence
14:04
platform.
14:05
And
14:05
what
14:05
that
14:06
means
14:06
is
14:07
we're
14:07
moving
14:07
beyond
14:08
just
14:09
the
14:10
physical
14:10
robot,
14:10
but
14:11
also
14:11
including
14:11
a
14:12
fixed
14:12
sensor
14:12
called
14:13
Talispot,
14:14
which
14:14
is
14:14
currently
14:15
in
14:15
field
14:16
trials
14:16
at
14:16
a
14:16
number
14:16
of
14:17
large
14:17
retailers.
14:18
Although
14:19
the
14:19
robot
14:20
sort
14:20
of
14:20
covers
14:20
the
14:20
full
14:21
store
14:21
today,
14:22
what
14:22
Tally
14:23
Spot
14:24
really
14:24
opens
14:24
us
14:24
up
14:24
to
14:25
do
14:25
is
14:26
capture
14:26
a
14:27
couple
14:27
select
14:27
areas
14:28
within
14:28
a
14:28
store
14:29
at
14:29
sort
14:30
of
14:30
a
14:30
greater
14:30
frequency.
14:32
So
14:32
those
14:32
are
14:32
often
14:33
areas
14:33
like
14:34
your
14:34
rotisserie
14:35
chicken
14:35
hot
14:36
hole
14:36
that
14:36
you
14:36
might
14:36
have
14:37
a
14:37
lot
14:37
of
14:37
high
14:38
churns
14:38
sort
14:38
of
14:38
throughout
14:39
the
14:39
day.
14:40
It
14:40
might
14:40
be
14:41
areas
14:41
like
14:41
high
14:42
shrink
14:42
sections
14:43
that
14:44
you
14:44
might
14:44
have
14:44
in
14:44
particular
14:45
environments
14:45
where
14:46
you
14:46
might
14:47
actually
14:47
not
14:47
want
14:48
to
14:48
do
14:48
restocking
14:49
activity
14:50
until
14:50
a
14:50
few
14:51
units
14:51
come
14:51
off
14:51
the
14:51
shelf.
14:52
Right.
14:53
Other
14:54
areas
14:54
are
14:54
like
14:55
bottom
14:55
basket
14:55
detection,
14:57
so
14:57
it's
14:58
easy
14:58
to
14:58
miss.
14:59
And
14:59
of
15:00
course
15:00
when
15:00
a
15:00
card
15:00
is
15:01
is
15:01
going
15:01
out
15:02
out
15:02
if
15:02
there's
15:03
something
15:03
on
15:03
the
15:03
bottom.
15:04
So
15:05
this
15:05
really
15:05
all
15:05
ties
15:06
back
15:06
to
15:06
Simbi's
15:07
vision
15:07
of
15:08
providing
15:08
perpetual
15:09
instrumentation
15:10
really
15:10
across
15:11
the
15:11
environment.
15:13
Well,
15:13
Brad,
15:14
I'm
15:14
sure
15:15
that
15:16
a
15:16
lot
15:16
of
15:16
our
15:16
listeners
15:17
have
15:18
seen
15:18
who've
15:18
been
15:18
following
15:19
Omnich
15:19
for
15:19
a
15:19
while.
15:19
They've
15:20
seen
15:20
our
15:20
video
15:21
down
15:21
at
15:21
Schnooks
15:22
with
15:22
Tally
15:23
roaming
15:23
the
15:24
aisles,
15:25
being
15:25
touted
15:25
as
15:26
like
15:26
another
15:27
associate
15:28
friend
15:28
of
15:28
the
15:29
team
15:29
working
15:29
in
15:29
that
15:30
store.
15:30
But
15:31
I
15:31
love
15:31
for
15:31
you
15:31
to
15:32
share
15:32
a
15:32
little
15:32
bit
15:33
about
15:33
what
15:33
you've
15:33
just
15:33
been
15:34
talking
15:34
about.
15:34
Like
15:35
can
15:35
you
15:35
dive
15:35
into
15:36
a
15:36
few
15:36
other
15:37
examples
15:37
that
15:38
might
15:38
not
15:38
be
15:38
on
15:39
people's
15:39
radar
15:39
yet
15:40
of.
15:41
Of
15:41
like
15:41
some
15:41
of
15:41
the
15:42
implementations
15:42
that
15:42
you've
15:43
put
15:43
into
15:43
place
15:44
in
15:44
some,
15:45
some
15:45
retailers
15:46
around
15:46
the
15:46
country?
15:47
Yeah,
15:48
absolutely.
15:49
Some
15:49
of
15:49
the
15:49
other
15:49
retailers
15:50
that
15:50
have
15:50
shared
15:51
publicly
15:52
sort
15:52
of
15:52
our
15:52
work
15:53
include
15:53
folks
15:53
like
15:53
Spartan
15:54
Ash.
15:54
Okay.
15:55
Where
15:55
they
15:56
reduced
15:57
their
15:57
out
15:57
of
15:57
stocks
15:58
in
15:58
stores
15:58
by
15:58
about
15:59
60%.
16:00
They
16:00
were
16:00
also
16:00
able
16:01
to
16:01
reduce
16:02
backroom,
16:02
controllable
16:03
sort
16:03
of
16:04
inventory
16:04
about
16:05
80%
16:05
in
16:05
their
16:06
initial
16:06
field
16:06
trials.
16:07
This
16:08
data
16:08
was
16:08
also
16:08
highlighted
16:09
at
16:09
Grocery
16:10
Shop
16:11
about
16:11
a
16:12
year
16:12
back.
16:13
In
16:13
addition,
16:14
we've
16:14
done
16:14
further
16:15
expansion
16:15
work
16:15
with
16:15
Wakefern.
16:17
You
16:17
know,
16:17
Largest
16:18
cooperative
16:18
grocer
16:19
in
16:19
the
16:19
U.S.
16:20
some
16:20
of
16:20
the
16:20
highest
16:20
volume
16:21
stores
16:21
in
16:21
the
16:21
country.
16:22
They
16:23
have
16:23
grocery
16:23
stores,
16:23
you
16:24
know,
16:24
doing
16:24
2
16:24
to
16:24
3
16:25
million
16:25
a
16:25
week.
16:25
I
16:26
mean
16:26
it's
16:26
just
16:26
wild.
16:28
You
16:28
know
16:28
we've
16:28
helped
16:28
them
16:29
reduce
16:29
out
16:29
of
16:29
stocks
16:30
in
16:30
a
16:30
number
16:30
of
16:30
their
16:30
environments
16:31
by
16:31
about
16:31
50%
16:32
and
16:33
you
16:33
know,
16:33
the
16:33
ability
16:33
to
16:34
repurpose
16:34
labor
16:35
of
16:36
about
16:36
50
16:36
hours
16:37
of
16:37
manual
16:37
scan
16:38
time
16:38
to
16:38
sort
16:39
of
16:39
more
16:39
important
16:39
tasks.
16:41
Certainly
16:41
BJ's
16:42
wholesale
16:43
is,
16:43
has
16:43
been
16:43
an
16:44
incredible
16:44
partner
16:45
as
16:45
well.
16:46
It
16:46
was
16:47
a
16:47
different
16:47
environment
16:47
for
16:48
us
16:48
stepping
16:48
from
16:48
grocery.
16:50
Yeah,
16:50
right.
16:51
Saw
16:52
a
16:52
significant
16:52
improvement
16:53
in
16:53
sort
16:53
of
16:54
their
16:54
restocking
16:54
activities.
16:56
Understanding
16:56
what's
16:57
up
16:57
in
16:57
the
16:57
steel,
16:59
where
16:59
it's
16:59
at
17:00
in
17:00
the
17:00
steel
17:01
when
17:01
you
17:01
think
17:01
about
17:02
your
17:02
sort
17:02
of
17:02
back
17:03
sock
17:03
or
17:03
excess
17:03
inventory
17:04
and
17:04
then
17:05
given
17:05
the
17:05
size
17:05
of
17:06
their
17:06
boxes,
17:07
leveraging
17:08
our
17:08
up
17:08
to
17:08
date
17:09
product
17:09
location
17:10
and
17:10
availability
17:11
information
17:12
to
17:12
massively
17:13
decrease
17:14
their
17:14
sort
17:14
of
17:14
pick
17:14
times
17:15
in
17:15
stores.
17:16
And
17:16
you
17:17
know
17:17
they're
17:17
spread
17:17
across
17:17
20
17:18
states.
17:20
And
17:20
so
17:20
with
17:20
functionality
17:21
like
17:21
our
17:22
virtual
17:23
tour
17:23
capabilities,
17:25
you
17:25
know,
17:25
their
17:25
operational
17:26
leaders
17:26
can
17:26
step
17:26
into
17:27
sort
17:27
of
17:27
any
17:27
of
17:27
their
17:28
clubs
17:28
any
17:28
day
17:29
and
17:29
sort
17:29
of
17:29
walk
17:30
their
17:30
environment.
17:30
So
17:31
those
17:31
are
17:31
some
17:31
of
17:32
the
17:32
examples
17:32
certainly
17:33
you
17:33
know,
17:33
the
17:33
schnooks
17:34
example,
17:35
well,
17:36
where
17:36
they've
17:37
not
17:37
only
17:37
reduced
17:37
their
17:38
out
17:38
of
17:38
stocks
17:39
but
17:39
leverage
17:40
this
17:40
data
17:40
actually
17:41
heavily
17:41
to
17:41
build
17:42
the
17:42
initial
17:42
business
17:43
case
17:43
for
17:43
their
17:43
ESLs
17:45
and
17:45
have
17:45
now
17:45
moved
17:46
on
17:46
to
17:46
leveraging
17:47
this
17:47
data
17:47
set
17:48
to
17:48
drive
17:49
greater
17:49
transparency
17:50
and
17:50
accountability
17:50
with
17:51
their
17:51
merchant
17:51
partners
17:52
as
17:52
well
17:52
as
17:53
build
17:53
monetization
17:53
strategies
17:54
around
17:54
it.
17:55
So
17:55
you
17:55
can
17:55
see
17:55
how
17:56
sort
17:57
of
17:57
the
17:57
value
17:57
case
17:59
for
17:59
this
18:00
level
18:00
of
18:01
technology
18:01
just
18:02
continues
18:02
to
18:02
build.
18:03
Brad,
18:04
I
18:04
have
18:05
to
18:05
ask
18:06
some
18:06
pretty
18:06
remarkable
18:07
statistics
18:08
and
18:08
examples
18:09
that
18:09
you
18:09
just
18:09
threw
18:10
at
18:10
us,
18:10
but
18:11
is
18:11
there
18:11
something
18:12
that
18:12
you
18:12
feel
18:12
like
18:12
is
18:13
the
18:13
most
18:14
maybe
18:14
consistent
18:15
theme
18:15
that
18:15
you're
18:16
hearing
18:16
from
18:16
some
18:16
of
18:17
these
18:17
retailers
18:17
that
18:17
you
18:17
deployed
18:18
with?
18:19
What
18:20
is
18:20
it
18:20
that's
18:21
really
18:21
the
18:21
linchpin
18:22
for
18:22
them?
18:22
Is
18:22
there
18:23
one
18:23
thing
18:23
or
18:24
maybe
18:24
a
18:24
hierarchy
18:25
of
18:25
things
18:25
that
18:25
they're
18:26
saying
18:26
like
18:26
okay,
18:27
we
18:27
were
18:27
maybe
18:28
this
18:28
is
18:28
a
18:28
big
18:28
investment
18:29
for
18:29
us,
18:29
but
18:29
this
18:30
is
18:30
why
18:30
it's
18:31
make
18:31
it
18:31
makes
18:31
sense
18:32
and
18:32
this
18:32
is
18:32
why
18:33
we're
18:33
going
18:33
to
18:33
continue
18:33
to
18:34
work
18:34
with
18:34
you.
18:35
Yeah,
18:36
I
18:36
think
18:36
there
18:36
have
18:36
been
18:36
a
18:36
number
18:37
of
18:37
factors
18:38
today,
18:39
but
18:39
I
18:39
think
18:39
it's
18:39
come
18:40
down
18:40
to
18:40
just
18:40
this
18:41
rationalization
18:42
of
18:43
the
18:43
value
18:44
of
18:44
perpetually
18:44
instrumenting
18:45
the
18:45
store
18:46
and
18:46
what
18:46
that
18:46
means
18:47
to
18:47
their,
18:47
their
18:48
business.
18:49
I
18:49
would
18:49
say
18:50
there
18:50
have
18:50
been
18:50
lots
18:50
of
18:50
pillars,
18:51
right.
18:51
People
18:51
have
18:52
seen
18:52
the
18:52
out
18:52
of
18:52
stock
18:53
or
18:53
OSA
18:54
benefit,
18:54
the
18:54
price
18:54
and
18:55
promotional
18:55
benefit,
18:56
the
18:56
labor
18:56
benefit.
18:57
But
18:57
as
18:58
time
18:58
goes
18:58
on,
18:58
what
18:58
they've
18:59
continued
18:59
to
18:59
see
18:59
is
19:00
how
19:00
does
19:00
this
19:00
Data
19:01
tie
19:01
back
19:01
to
19:01
retail
19:02
media?
19:02
How
19:02
does
19:02
this
19:03
data
19:03
tie
19:03
back
19:04
to
19:04
online
19:05
grocery
19:06
and
19:06
other
19:06
omnichannel
19:07
sort
19:07
of
19:07
initiatives?
19:08
And
19:09
they're
19:09
really
19:10
starting
19:10
to
19:10
see
19:10
this
19:10
as
19:10
a
19:11
platform
19:11
technology
19:14
that's
19:14
helping
19:15
them
19:15
evolve
19:15
their
19:15
efficiency
19:16
and
19:16
effectiveness.
19:17
And
19:18
I
19:18
think
19:19
any
19:19
retailer
19:20
today
19:20
is
19:20
thinking
19:21
about
19:21
how
19:21
they
19:22
leverage
19:22
automation
19:23
and
19:23
AI
19:23
to
19:24
improve
19:24
their
19:25
operating
19:25
model.
19:26
Yeah,
19:26
that
19:27
was
19:27
going
19:27
to
19:27
be
19:27
my
19:27
question
19:28
too.
19:28
You
19:28
know,
19:28
similar
19:29
to
19:29
Ann,
19:29
it
19:29
was
19:29
going
19:29
to
19:29
be
19:29
like,
19:30
I
19:30
can't.
19:30
I
19:30
mean,
19:30
the
19:31
reason
19:31
we're
19:31
so
19:31
big
19:32
on
19:32
robotics
19:32
is
19:32
we
19:33
can't
19:33
think
19:33
of
19:33
another
19:33
technology
19:34
that
19:34
creates
19:35
so
19:35
many
19:35
different
19:36
value
19:36
streams.
19:37
And
19:37
so
19:37
to
19:37
your
19:38
point,
19:38
just
19:38
so
19:38
everyone
19:38
gets
19:39
that
19:39
it
19:39
really
19:40
isn't
19:40
about
19:40
one,
19:41
it's
19:41
probably,
19:42
what
19:42
I'm
19:42
reading
19:42
between
19:42
the
19:42
lines
19:43
here
19:43
is
19:43
it's
19:43
probably
19:43
retailer
19:44
dependent
19:44
to
19:44
decide
19:45
which
19:45
one
19:45
is
19:45
the
19:46
most
19:46
important
19:46
to
19:46
them,
19:47
but
19:47
really
19:47
it
19:48
is,
19:48
yes
19:48
to
19:48
all
19:49
of
19:49
them.
19:49
And
19:49
therefore
19:50
it
19:50
is
19:50
a
19:50
platform
19:51
play
19:51
here
19:51
that
19:51
gives
19:51
you
19:52
the
19:52
data
19:52
to
19:52
understand
19:53
what's
19:53
happening
19:53
in
19:53
your
19:53
store.
19:54
Is
19:54
that.
19:54
That's
19:54
right,
19:54
Brad?
19:55
Absolutely.
19:56
And
19:57
in
19:57
further
19:57
that
19:58
point,
19:58
we've
19:58
seen
19:58
different
19:59
executive
20:00
champions
20:00
across
20:01
these
20:01
businesses
20:02
carry
20:02
this
20:02
technology
20:03
forward.
20:03
I
20:03
mean,
20:03
out
20:03
of
20:04
the
20:04
gate.
20:04
Most
20:05
people
20:05
assume
20:05
it's
20:06
a
20:06
CIO
20:06
or
20:06
CTO
20:07
taking
20:07
technology
20:08
forward.
20:08
But
20:08
we've
20:09
had
20:09
a
20:09
lot
20:09
of,
20:10
you
20:10
know,
20:10
head
20:10
of
20:11
store
20:11
champions,
20:12
we've
20:12
had
20:13
chief
20:13
supply
20:13
chain
20:14
officer
20:14
champions,
20:15
we've
20:15
even
20:15
had
20:15
head
20:16
of
20:16
finance
20:17
see
20:17
the
20:18
cross
20:18
functional
20:19
value
20:19
of
20:19
this
20:20
technology
20:20
and
20:20
really
20:21
champion
20:21
it
20:21
to
20:22
take
20:22
it
20:22
forward.
20:23
When
20:24
you
20:24
got
20:24
the
20:24
head
20:24
of
20:24
finance
20:25
singing
20:26
your
20:26
praise
20:26
so
20:26
you
20:26
know
20:26
you're
20:27
doing
20:27
something
20:27
well.
20:29
Well,
20:29
that,
20:29
that's
20:30
a
20:30
great
20:30
segue
20:30
too,
20:30
because
20:30
that
20:30
gets
20:31
me
20:31
to
20:31
my
20:31
next
20:31
question
20:32
that
20:32
we
20:32
wanted
20:32
to
20:32
ask
20:32
you,
20:32
which
20:33
is,
20:33
you
20:33
know,
20:34
what
20:34
are
20:34
some
20:34
of
20:34
the.
20:35
Because
20:35
we've
20:35
seen
20:35
a
20:35
lot
20:36
over
20:36
the
20:36
course
20:36
of
20:37
the
20:37
last
20:37
10
20:38
years
20:38
or
20:38
so,
20:38
we've
20:38
seen,
20:39
we've
20:39
seen
20:39
some
20:40
starts
20:40
and
20:40
stops
20:40
as
20:41
it
20:41
comes
20:41
to
20:41
robotics
20:42
and
20:42
robotics
20:42
deployments.
20:43
And
20:43
what
20:44
I
20:44
always
20:44
say
20:44
to
20:44
them
20:45
is,
20:45
like
20:45
whenever
20:45
I
20:46
hear
20:46
those
20:46
is
20:46
I
20:47
think
20:47
those
20:47
executives
20:48
that
20:48
are
20:48
stopping
20:48
just
20:49
haven't
20:49
figured
20:49
out
20:49
how
20:50
to
20:50
deploy
20:50
them
20:50
correctly
20:51
to
20:51
get
20:51
the
20:52
value.
20:52
So,
20:53
so
20:53
what
20:53
are
20:53
some
20:54
best
20:54
practices
20:55
that
20:55
you
20:55
can
20:55
share
20:56
for
20:56
maybe
20:56
those
20:56
retailers
20:57
that
20:57
are
20:57
thinking
20:57
about
20:57
it
20:57
that
20:58
haven't
20:58
quite
20:58
deployed
20:59
them
20:59
successfully
21:00
to
21:00
this
21:00
point.
21:01
What
21:01
are
21:01
some
21:01
best
21:02
practices
21:02
you
21:02
can
21:02
share
21:02
to
21:03
ensure
21:03
that
21:03
those
21:03
deployments
21:04
go
21:04
well?
21:05
Yeah,
21:05
Chris,
21:06
I
21:06
think
21:06
with
21:06
your
21:06
first
21:07
point,
21:07
I
21:08
would
21:08
state
21:08
that
21:08
maybe
21:09
not
21:09
all
21:09
shelf
21:09
intelligence
21:10
technologies
21:11
or
21:11
partners
21:12
are
21:12
created
21:12
equal.
21:12
I
21:13
mean,
21:13
we
21:13
talked
21:13
about
21:13
this
21:14
a
21:14
little
21:14
bit
21:14
earlier,
21:15
but
21:16
I
21:16
think
21:16
there's
21:17
some
21:17
retailers
21:17
that
21:18
step
21:18
down
21:18
a
21:18
path
21:19
with
21:19
a
21:19
particular
21:20
partner,
21:20
maybe
21:21
they
21:21
were
21:21
early
21:21
in
21:21
their
21:22
journey
21:22
or
21:23
their
21:23
technology
21:23
development
21:24
sort
21:24
of
21:24
life
21:25
cycle.
21:25
And
21:25
so
21:26
that
21:26
has
21:26
put
21:26
sort
21:27
of
21:27
a
21:27
bad
21:27
stamp
21:27
on
21:28
the
21:28
space.
21:29
And
21:30
it
21:30
presents
21:30
the
21:30
exact
21:31
question
21:31
which
21:31
you
21:31
just
21:32
raised
21:32
is,
21:32
you
21:32
know,
21:32
why
21:33
is
21:33
this,
21:33
you
21:33
know,
21:33
why
21:34
is
21:34
this
21:34
working
21:35
for
21:35
others?
21:37
I
21:37
think
21:37
internal
21:38
alignment
21:39
is
21:39
one
21:40
of
21:40
the
21:40
biggest
21:40
pieces.
21:41
We
21:42
do
21:42
see
21:42
that
21:42
sometimes
21:43
innovation
21:44
teams
21:44
can
21:44
grab
21:44
hold
21:45
of
21:45
this
21:45
technology
21:45
but
21:46
not
21:46
have
21:46
the
21:46
core
21:47
support
21:47
of
21:48
really
21:48
the
21:48
rest
21:48
of
21:49
the
21:49
capital
21:49
committee
21:49
or
21:50
the
21:50
rest
21:50
of
21:50
the
21:50
leadership
21:51
team.
21:51
And
21:52
so
21:52
as
21:52
we
21:52
talked
21:53
about
21:53
earlier,
21:54
this
21:54
technology
21:54
really
21:55
touches
21:55
everyone
21:55
in
21:56
the
21:56
business.
21:57
So
21:57
making
21:57
sure
21:58
folks
21:58
are
21:58
aligned
21:59
on
21:59
what
22:00
does
22:00
the
22:00
proof
22:00
of
22:00
technology
22:01
phase
22:01
look
22:02
like
22:02
or
22:02
what
22:02
is
22:02
the
22:03
proof
22:03
of
22:04
value
22:04
or
22:04
proof
22:04
of
22:04
economics?
22:05
We
22:05
typically
22:06
see
22:06
like
22:07
these
22:07
one
22:08
to
22:08
two
22:08
chapters
22:09
sort
22:09
of
22:09
early
22:09
in
22:09
this
22:10
sort
22:10
of
22:10
partnership
22:10
journey.
22:11
And
22:11
then
22:12
once
22:12
we've
22:12
nailed
22:12
sort
22:13
of
22:13
proof
22:13
of
22:13
value
22:13
and
22:14
proof
22:14
of
22:14
economics,
22:15
it's,
22:15
it's
22:15
sort
22:15
of
22:15
really
22:16
all
22:16
about
22:16
scaling,
22:18
but
22:18
making
22:18
sure
22:19
that
22:19
communication
22:19
and
22:20
sort
22:20
of
22:20
alignment
22:21
is
22:21
key.
22:22
I'd
22:22
say
22:22
the
22:22
other
22:23
point
22:23
that's
22:23
really
22:23
important
22:24
is
22:25
this
22:25
is
22:25
really
22:26
like
22:26
the
22:26
country's
22:26
first
22:27
introduction
22:27
to
22:28
sort
22:28
of
22:28
robotics.
22:29
Right,
22:29
right.
22:30
What
22:30
most
22:31
consumers
22:31
know
22:31
about
22:32
robotics
22:32
is
22:32
kind
22:33
of
22:33
what
22:33
they
22:33
see
22:33
in
22:33
the
22:34
movies.
22:34
Or
22:36
you
22:36
know,
22:36
they
22:36
might
22:36
have
22:36
a
22:37
vacuum
22:37
cleaner
22:37
at
22:37
home
22:38
now
22:38
if
22:38
they
22:38
live
22:38
in
22:39
Silicon
22:39
Valley
22:39
or
22:40
these
22:40
types
22:40
of
22:40
places,
22:41
or
22:41
they
22:41
have
22:41
a
22:42
Tesla,
22:42
they
22:42
might
22:42
be
22:42
experimenting
22:43
with
22:44
you
22:44
know,
22:44
sort
22:44
of
22:44
self
22:45
driving.
22:46
But
22:46
it's,
22:47
it's
22:47
really
22:47
important
22:47
for
22:48
retailers
22:48
to
22:49
I
22:49
think
22:50
both
22:51
recognize
22:51
which
22:52
partners
22:52
are
22:52
making
22:53
this
22:53
technology
22:54
really
22:54
intuitive
22:55
and
22:56
in
22:56
a
22:56
way
22:57
that
22:57
can
22:57
really
22:57
kind
22:58
of
22:58
coexist
22:58
with
22:59
kind
22:59
of
22:59
shoppers
23:00
and
23:00
store
23:00
teams.
23:01
So
23:01
I
23:01
wouldn't
23:02
underestimate,
23:03
I
23:03
think
23:03
the
23:03
design
23:05
component
23:05
here
23:06
is
23:06
as
23:06
well
23:07
because
23:08
it
23:08
is
23:08
so
23:08
important.
23:10
I
23:10
love
23:10
that,
23:10
Brad.
23:11
I
23:11
think
23:12
that's
23:12
a
23:12
great
23:12
segue
23:13
also
23:14
again
23:15
into
23:15
our
23:16
next
23:16
question,
23:16
which
23:17
is
23:17
about
23:18
that
23:18
I
23:19
think
23:19
the
23:19
biggest
23:20
concern
23:20
people
23:21
haven't
23:21
seen
23:21
robotics.
23:22
And
23:22
when
23:22
they
23:22
hear
23:22
the
23:23
word
23:23
robot,
23:23
they
23:24
get
23:24
concerned
23:24
that
23:25
it's
23:25
taking
23:25
the
23:26
place
23:26
of
23:27
human
23:27
labor.
23:29
And
23:29
what's
23:29
it
23:29
going
23:29
to
23:30
be
23:30
like
23:30
interacting
23:31
with
23:31
a
23:31
robot
23:31
in
23:31
store
23:32
versus
23:33
what
23:33
they're
23:33
used
23:34
to
23:34
in
23:34
their
23:34
traditional
23:35
shopping
23:35
experience?
23:36
So
23:36
I'd
23:37
love
23:37
to
23:37
hear
23:38
specifically
23:39
like,
23:39
what
23:39
does
23:40
this,
23:40
what
23:40
is
23:40
this
23:41
doing
23:41
for
23:42
the
23:42
store
23:42
associates
23:43
in
23:43
the
23:43
retailers
23:44
that
23:44
have
23:44
deployed
23:45
these
23:45
robots
23:46
and
23:47
what
23:47
does
23:47
that
23:47
mean
23:48
for
23:48
kind
23:48
of
23:48
the
23:48
bottom
23:49
line
23:49
of
23:50
both,
23:50
you
23:50
know,
23:51
employee
23:51
happiness
23:52
and
23:52
satisfaction
23:53
at
23:53
work
23:53
and
23:53
then
23:53
also
23:54
what
23:54
it's
23:55
doing
23:55
for
23:55
retailers?
23:58
Absolutely.
23:59
So
23:59
our
23:59
goal
24:00
with
24:00
store
24:01
teams
24:01
and
24:01
technology
24:01
like
24:02
Tally
24:02
is
24:02
to
24:02
really
24:03
be
24:03
a
24:03
power
24:03
tool
24:03
to
24:04
them.
24:04
And
24:05
most
24:05
Store
24:06
teams
24:06
have
24:06
really
24:06
recognized
24:07
this.
24:07
In
24:07
fact,
24:08
you
24:08
know,
24:08
we
24:08
do
24:08
a
24:08
lot
24:08
of
24:09
store
24:09
survey
24:10
work,
24:10
retailer
24:11
survey
24:11
work,
24:11
NPS
24:12
type
24:12
work,
24:12
and
24:13
90%
24:14
of
24:14
store
24:14
teams
24:15
today,
24:15
actually,
24:16
once
24:16
they
24:17
experience
24:17
tally,
24:18
actually
24:19
don't
24:19
want
24:19
to
24:19
do
24:19
their
24:19
jobs
24:20
without
24:20
tally
24:21
sort
24:21
of
24:21
anymore
24:22
because
24:22
it's
24:22
taking
24:23
them
24:23
in
24:23
such
24:23
a
24:24
big
24:24
step
24:24
forward
24:25
of,
24:25
wait,
24:26
I
24:26
no
24:26
longer
24:26
have
24:27
to
24:27
look
24:27
for
24:27
problems.
24:28
This
24:28
thing
24:28
just
24:29
tells
24:29
me,
24:30
and
24:30
it
24:30
helps
24:31
me
24:31
to
24:31
really
24:32
identify
24:32
root
24:33
cause.
24:33
So
24:34
when
24:34
the
24:34
regional
24:34
director
24:35
sort
24:35
of
24:35
steps
24:36
into
24:36
store
24:36
and
24:36
is
24:37
like,
24:37
hey,
24:37
what's
24:38
going
24:38
on
24:38
with
24:38
these
24:38
shelf
24:39
conditions?
24:39
They
24:39
can
24:40
sort
24:40
of
24:40
point
24:40
and
24:40
say,
24:40
hey,
24:41
look,
24:41
this
24:42
is
24:42
a
24:42
warehouse
24:43
issue,
24:43
or
24:43
this
24:43
is
24:43
sort
24:43
of
24:43
a
24:44
DSD
24:44
issue,
24:44
sort
24:45
of,
24:45
et
24:45
cetera.
24:46
This
24:46
level
24:47
of
24:47
sort
24:47
of
24:47
root
24:47
cause
24:48
and
24:48
accountability
24:48
up
24:49
and
24:49
down
24:50
the
24:50
chain
24:51
has
24:51
been
24:51
sort
24:51
of
24:52
really
24:52
empowering
24:53
to
24:53
these
24:54
store
24:54
teams.
24:55
Well,
24:56
I,
24:56
I
24:56
know,
24:57
Chris,
24:57
you
24:57
remember
24:57
when
24:58
we
24:58
interviewed
24:58
Kim
24:59
Anderson
24:59
at
24:59
Schnooks,
25:00
and
25:00
we
25:00
were
25:01
asking
25:01
her,
25:01
because
25:01
she's
25:02
head
25:02
of
25:02
store
25:02
operations
25:03
there,
25:03
she
25:03
was
25:04
like,
25:04
we're
25:04
like,
25:04
what
25:04
do
25:04
you.
25:05
What
25:05
do
25:05
your
25:05
teams
25:05
think
25:06
about
25:06
this?
25:06
Do
25:06
you
25:06
remember
25:07
what
25:07
she
25:07
said?
25:08
Yeah,
25:08
she
25:08
said
25:08
something
25:08
like,
25:09
if
25:09
I
25:09
were
25:09
to
25:09
remove
25:09
the
25:09
robot,
25:10
the
25:10
first
25:10
thing
25:10
I'd
25:11
have
25:11
to.
25:11
They'd
25:11
have
25:11
to,
25:11
like,
25:12
I,
25:12
I.
25:13
She
25:13
said
25:13
they'd
25:13
rather.
25:14
I
25:14
don't.
25:14
It
25:14
was
25:14
something
25:15
crazy.
25:15
Right?
25:15
And
25:15
like,
25:15
she
25:16
said,
25:16
they'd
25:16
rather
25:16
take.
25:17
It
25:17
out
25:17
of
25:17
store.
25:18
Yeah,
25:19
they'd
25:19
rather.
25:19
They'd
25:19
rather
25:20
see
25:20
her
25:20
leave
25:20
than
25:21
take
25:21
the
25:21
robot
25:21
out
25:21
of
25:21
the
25:21
store
25:22
or
25:22
something
25:22
like
25:22
that.
25:22
I
25:22
was
25:22
trying
25:23
to
25:23
see.
25:23
I
25:23
don't.
25:24
She
25:24
said
25:24
it
25:24
more
25:24
colorfully
25:25
than
25:25
that.
25:25
I
25:25
was
25:25
trying
25:25
to
25:25
figure
25:26
out
25:26
what,
25:26
what
25:26
it
25:26
was.
25:27
But,
25:27
I
25:27
mean,
25:27
I
25:27
think
25:28
the
25:28
whole
25:28
purpose
25:28
is
25:28
exactly
25:29
what
25:29
Brad
25:29
was
25:29
saying
25:30
is,
25:30
like,
25:30
it
25:30
really
25:30
has
25:31
become
25:31
a
25:32
tool
25:32
that
25:32
can,
25:32
like,
25:33
do
25:33
the
25:33
stuff
25:33
that
25:33
the
25:34
associates
25:34
don't
25:35
want
25:35
to
25:35
do.
25:36
And
25:36
we
25:36
saw
25:36
firsthand
25:37
when
25:37
we
25:37
were
25:37
in
25:37
Schnooks,
25:37
like,
25:38
then
25:38
that
25:39
associate
25:39
who
25:39
would
25:40
be
25:40
stocking
25:40
shelves,
25:41
who
25:41
would
25:41
be
25:41
doing
25:41
other
25:42
things,
25:42
is
25:42
interacting
25:43
with
25:43
customers
25:44
there
25:44
and
25:45
in,
25:46
specifically
25:46
around
25:47
customers.
25:47
What.
25:48
What
25:48
are
25:48
customers
25:49
doing
25:49
when
25:49
they
25:49
see
25:50
these
25:50
robots
25:50
in
25:50
store?
25:51
Like,
25:51
what's
25:51
their
25:51
response
25:52
been?
25:52
And
25:52
what
25:53
have
25:53
you
25:53
heard
25:53
from
25:53
the
25:53
retailers
25:54
that
25:54
you're
25:54
working
25:54
with
25:55
about
25:55
how
25:56
they,
25:56
how
25:57
they
25:57
work
25:57
alongside
25:58
people
25:58
shopping
25:59
in
25:59
the
25:59
stores?
26:00
I
26:00
mean,
26:00
we've
26:00
had
26:01
such
26:01
a
26:01
unique
26:02
opportunity,
26:02
and,
26:02
I
26:03
mean,
26:04
you
26:04
know,
26:04
more
26:04
than
26:04
a
26:05
half
26:05
a
26:05
billion
26:05
consumers
26:06
go
26:06
into
26:06
grocery
26:07
stores
26:07
every
26:08
week
26:08
to
26:08
get,
26:08
you
26:08
know,
26:08
milk,
26:09
bread,
26:09
juice,
26:10
essentials.
26:11
So
26:11
the
26:12
fact
26:12
that
26:12
we've
26:13
had
26:13
this
26:13
opportunity
26:14
where
26:14
they
26:14
can
26:14
kind
26:14
of
26:14
look
26:15
over
26:15
their
26:15
shoulder
26:15
and
26:16
sort
26:16
of
26:16
seeing
26:17
a
26:17
robot
26:17
has
26:17
just
26:18
been
26:18
like
26:18
so
26:19
exciting.
26:20
And
26:20
in
26:20
fact,
26:20
what
26:20
we
26:21
found
26:21
is
26:21
the
26:21
majority
26:21
of
26:22
shoppers
26:22
actually
26:23
favor
26:23
stores
26:24
with
26:24
robots
26:24
because
26:25
they
26:25
clearly
26:25
understand
26:26
what
26:26
it's
26:26
doing.
26:27
Yeah.
26:27
And
26:28
it's
26:28
actually
26:28
driving
26:29
a
26:29
better
26:30
customer
26:30
experience.
26:32
You
26:32
know,
26:32
obvious
26:33
things
26:33
that,
26:33
that
26:34
we've
26:34
found
26:35
being
26:35
out
26:35
in
26:35
the
26:36
field
26:36
is,
26:36
you
26:36
know,
26:36
kids
26:37
certainly
26:37
love
26:37
tally.
26:38
We've
26:39
actually
26:39
found
26:40
families
26:41
with
26:41
children
26:42
spend
26:42
a
26:43
substantial
26:44
more
26:44
amount
26:45
more
26:45
time
26:45
in
26:45
stores.
26:46
Price.
26:47
Yeah.
26:47
Which
26:48
is,
26:48
which
26:48
is
26:48
sort
26:48
of
26:48
certainly
26:49
interesting.
26:51
And
26:51
yeah,
26:52
so
26:52
it's
26:52
been
26:52
a
26:52
really
26:53
positive
26:53
sort
26:53
of
26:53
experience,
26:55
you
26:55
know,
26:55
overall.
26:57
Yeah,
26:58
I
26:58
loved
26:58
your
26:58
point
26:58
you
26:58
made
26:59
too,
26:59
about
26:59
the
26:59
store
26:59
director
27:00
and
27:00
the
27:00
store
27:00
visit
27:01
to
27:01
a
27:01
given
27:01
store
27:02
too,
27:02
because
27:03
that
27:03
can
27:03
be
27:04
such
27:04
a
27:04
unproductive
27:05
exercise
27:06
if
27:06
people
27:07
don't
27:07
have
27:07
the
27:07
same
27:08
data
27:08
that
27:08
they're
27:09
all
27:09
looking
27:09
at
27:09
and
27:10
talking
27:10
about
27:10
together.
27:11
And
27:11
so
27:11
thinking
27:11
about
27:12
it
27:12
in
27:12
that
27:13
way
27:13
is
27:14
just
27:14
really
27:14
powerful
27:14
too.
27:15
BRAD
27:16
just
27:16
on
27:17
that
27:17
one
27:17
really
27:17
quick,
27:19
I
27:19
think
27:19
it
27:19
goes
27:20
both
27:20
ways.
27:20
In
27:21
fact,
27:22
you've
27:22
spent
27:22
enough
27:22
time
27:23
in
27:23
stores
27:24
that
27:24
you
27:24
often
27:25
have
27:25
a
27:25
hint
27:26
of
27:26
when
27:26
these
27:27
activities
27:27
are
27:27
happening,
27:29
whether
27:29
you
27:29
should
27:29
know
27:30
or
27:30
not.
27:30
You
27:31
know,
27:31
having
27:31
the
27:31
ability
27:32
to
27:32
look
27:32
at
27:32
a
27:32
store
27:33
24
27:34
by
27:34
7,
27:35
365
27:35
has
27:35
been
27:36
sort
27:36
of
27:36
really
27:36
eye
27:37
opening,
27:38
you
27:39
know,
27:39
from
27:39
a
27:39
corporate
27:39
perspective.
27:41
And
27:42
you
27:42
know,
27:42
we
27:42
like
27:42
that
27:43
we
27:43
can
27:43
provide
27:43
that
27:43
level
27:44
of
27:44
functionality
27:45
where
27:45
people
27:45
in
27:45
the
27:45
home
27:45
office
27:46
can
27:46
dial
27:46
in
27:47
anytime.
27:48
Yeah.
27:48
And
27:49
it's,
27:49
and
27:49
it's
27:50
valuable
27:51
both
27:51
before
27:51
the
27:52
visit
27:52
and
27:53
during
27:53
the
27:53
visit.
27:53
Right.
27:54
And
27:54
then
27:54
probably
27:54
after
27:54
the
27:55
visit
27:55
from
27:55
an
27:55
accountability
27:56
perspective
27:57
as
27:57
well
27:57
too.
27:57
Right.
27:58
So
27:58
you
27:58
get,
27:58
you
27:58
get
27:59
all
27:59
three
27:59
of
27:59
those
27:59
things
27:59
which
28:00
you
28:00
know,
28:00
again,
28:01
how
28:01
stores
28:01
are
28:02
traditionally
28:02
run,
28:02
you
28:02
just
28:02
don't
28:03
have
28:03
that
28:03
data
28:03
clarity
28:04
across
28:04
all
28:04
three
28:04
of
28:05
those
28:05
steps.
28:05
So.
28:06
All
28:06
right,
28:06
Brad.
28:06
Well,
28:07
I
28:07
want
28:07
to,
28:07
I
28:07
want
28:07
to.
28:08
Ann
28:08
and
28:08
I
28:08
wanted
28:08
to
28:08
put
28:09
you
28:09
on
28:09
the
28:09
spot
28:09
here
28:10
because
28:10
you
28:11
know,
28:11
we
28:11
like
28:11
to
28:11
make
28:11
good
28:12
on
28:12
our
28:12
claims.
28:12
BRAD
28:13
we
28:13
like
28:13
to,
28:13
we
28:14
like
28:14
to
28:14
make
28:14
good
28:14
on
28:14
our
28:15
claims
28:15
and
28:16
we've
28:16
said
28:16
on
28:16
record
28:17
and
28:17
I
28:17
guess
28:17
has
28:17
now
28:18
said
28:18
2024,
28:19
but
28:19
I
28:19
guess
28:20
2025
28:21
is
28:21
the
28:21
year
28:21
of
28:21
the
28:21
robot.
28:22
So
28:23
what
28:23
needs
28:23
to
28:23
happen
28:24
for
28:25
that
28:25
prediction
28:26
to
28:26
come
28:26
true?
28:27
What
28:27
needs
28:27
to
28:27
happen
28:27
for
28:28
us
28:28
to
28:28
make
28:28
good
28:28
on
28:28
that
28:29
prediction?
28:29
Brad?
28:30
Absolutely,
28:31
Chris.
28:31
I
28:31
mean,
28:31
certainly
28:32
we're
28:32
seeing
28:33
increased
28:33
narrative
28:34
from
28:34
all
28:35
the
28:35
retailers
28:35
we're
28:36
talking
28:36
to
28:38
about
28:38
how
28:38
they
28:38
can
28:39
leverage
28:39
kind
28:39
of
28:40
automation
28:40
and
28:40
AI
28:42
to
28:42
improve
28:42
their
28:43
operating
28:43
model
28:43
and
28:44
efficiency
28:44
and
28:45
sort
28:45
of
28:45
effectiveness
28:45
with
28:46
these
28:46
store
28:46
environments.
28:47
Like
28:47
this
28:47
is
28:47
board
28:48
level
28:48
discussion
28:48
that's
28:49
happening.
28:50
I
28:50
would
28:51
say
28:51
there's
28:51
sort
28:51
of
28:51
this
28:51
ChatGPT
28:52
moment.
28:53
So
28:53
what
28:53
gives
28:54
me,
28:54
you
28:54
know,
28:54
continued
28:55
confidence
28:56
of
28:56
this
28:56
type
28:57
of
28:57
sort
28:57
of
28:57
automation
28:58
becoming
28:58
more
28:58
ubiquitous.
29:00
You
29:00
know,
29:00
we
29:00
actually
29:01
signed
29:01
more
29:02
new
29:02
logos
29:02
in
29:03
2024
29:04
than
29:04
we
29:04
did
29:05
almost
29:05
in
29:05
sort
29:05
of
29:05
all
29:06
of
29:06
our
29:06
history.
29:07
And
29:07
in
29:07
fact,
29:08
we
29:08
continue
29:09
to
29:09
see
29:09
a
29:09
lot
29:09
of
29:09
tier
29:10
one
29:10
momentum.
29:11
So
29:11
I
29:11
think
29:11
maybe
29:11
a
29:12
sub
29:12
bullet
29:13
to
29:13
2025
29:14
being
29:15
the
29:15
year
29:15
of
29:15
the
29:15
robot
29:16
is
29:17
we'll
29:17
probably
29:18
see
29:18
our
29:18
first
29:19
sizable
29:20
sort
29:20
of
29:20
tier
29:20
one
29:21
grocery
29:21
deployments
29:22
of
29:22
this
29:22
technology
29:23
as
29:23
well.
29:23
So
29:24
some
29:24
of
29:24
the
29:24
largest
29:25
players,
29:26
obviously,
29:26
given
29:27
their
29:27
position
29:27
in
29:27
the
29:28
market,
29:29
have
29:30
taken
29:30
a
29:30
little
29:30
bit
29:30
of
29:31
approach
29:31
of
29:31
sort
29:31
of
29:31
wait
29:32
and
29:32
see
29:32
sort
29:33
of
29:33
up
29:33
until
29:33
now.
29:34
But
29:34
there's
29:35
very
29:35
aggressive
29:36
sort
29:36
of
29:36
initiatives,
29:37
you
29:37
know,
29:37
certainly
29:37
sort
29:37
of
29:38
across
29:38
the
29:38
board
29:39
in
29:39
a
29:39
number
29:39
of
29:39
those
29:40
different
29:40
players.
29:40
What
29:41
we're
29:41
also
29:41
seeing
29:42
is
29:43
this
29:43
type
29:43
of
29:44
technology
29:44
ending
29:45
up
29:45
in
29:45
sort
29:45
of
29:46
formats
29:46
adjacent
29:47
to
29:47
grocery.
29:48
So
29:48
over
29:49
the
29:49
last
29:49
18
29:49
months,
29:50
we
29:50
went
29:51
from
29:51
grocery
29:52
also
29:52
into
29:52
club,
29:53
mass,
29:53
alcohol,
29:55
farm
29:55
and
29:55
home,
29:56
doing
29:56
more
29:56
active
29:57
work
29:57
in
29:59
hardware
29:59
and
29:59
home
30:00
improvement
30:02
and
30:03
continual
30:03
amount
30:03
of
30:03
sort
30:04
of
30:04
international
30:04
interest.
30:05
Right.
30:05
If
30:05
you
30:06
look
30:06
at
30:06
environments
30:07
like
30:07
Canada,
30:07
western
30:08
Europe,
30:08
sort
30:08
of
30:08
Australia,
30:09
they
30:09
look
30:10
very
30:10
much
30:10
like
30:10
the
30:11
US
30:11
today.
30:13
So
30:13
we
30:13
do
30:13
believe
30:14
strongly
30:14
that
30:15
this
30:16
type
30:16
of
30:16
technology
30:16
will
30:17
become
30:17
much
30:17
more
30:17
ubiquitous
30:18
next
30:18
year.
30:19
And
30:20
Brad,
30:20
where
30:21
does
30:21
the
30:21
product,
30:21
specifically,
30:22
where
30:22
does
30:22
the
30:22
Simbi
30:23
product
30:23
need
30:23
to
30:24
go
30:24
next
30:24
to
30:24
keep
30:25
evolving
30:25
so
30:25
that
30:26
2025
30:27
is
30:27
the
30:27
year
30:27
of
30:27
the
30:27
robot
30:28
and
30:28
then
30:28
we
30:28
see
30:28
more
30:28
and
30:29
more
30:29
26
30:29
and
30:29
beyond?
30:31
Absolutely.
30:32
So
30:32
we're
30:32
always
30:32
keeping
30:32
pace
30:34
with
30:35
sort
30:35
of
30:35
innovation
30:36
using
30:36
the
30:37
latest
30:37
in
30:37
sort
30:37
of
30:37
sensing
30:38
and
30:38
sort
30:38
of
30:38
compute
30:39
technology.
30:39
But
30:40
obviously
30:40
we've
30:40
done
30:40
a
30:41
lot
30:41
of
30:41
chain
30:41
wide
30:41
adoptions
30:42
with
30:42
where
30:42
the
30:43
product
30:43
sits
30:43
today.
30:44
So
30:45
so
30:45
much
30:45
of
30:45
our
30:45
energy
30:46
is
30:46
focused
30:46
more
30:47
on
30:47
additional
30:48
value
30:48
realization.
30:50
So
30:50
how
30:50
do
30:50
we
30:50
continue
30:51
to
30:51
take
30:51
all
30:52
the
30:52
great
30:52
data
30:52
that
30:52
we're
30:52
deriving
30:53
from
30:53
these
30:53
stores
30:54
and
30:54
more
30:54
deeply
30:55
fuse
30:55
it
30:55
with
30:55
all
30:56
the
30:56
data
30:56
that's
30:56
in
30:56
a
30:56
retailer's
30:57
back
30:57
office?
30:59
In
31:00
addition,
31:00
some
31:00
of
31:00
the
31:00
other
31:01
examples
31:02
we're
31:03
focused
31:03
on
31:03
is
31:04
how
31:04
do
31:04
you
31:04
deploy,
31:05
you
31:05
know,
31:05
foundationary
31:06
models
31:06
or
31:07
large
31:07
language
31:07
models
31:08
on
31:08
top
31:09
of
31:09
this
31:09
data
31:10
to
31:10
make
31:10
this
31:11
type
31:11
of
31:11
data
31:11
more
31:11
accessible
31:12
to
31:13
facet
31:13
it
31:14
in
31:14
different
31:15
ways.
31:15
You
31:16
know,
31:16
just
31:16
being
31:16
able
31:16
to
31:16
ask
31:17
questions
31:18
against
31:18
the
31:18
data,
31:19
which,
31:19
which
31:20
stores
31:20
are
31:20
having
31:20
the
31:21
deepest
31:21
challenges,
31:21
which,
31:22
which
31:22
have
31:22
the
31:22
best
31:23
restock
31:23
rates,
31:24
you
31:24
know,
31:24
which
31:25
merchants
31:26
or
31:26
sort
31:26
of
31:26
categories
31:27
are
31:27
most
31:27
problematic,
31:28
these
31:29
types
31:29
of
31:29
things.
31:30
We're
31:30
also
31:31
seeing
31:31
a
31:31
lot
31:31
of
31:31
advancements
31:33
in
31:34
sort
31:34
of
31:34
core
31:34
computer
31:35
vision
31:35
that
31:35
allows
31:37
retailers
31:37
to
31:38
unlock
31:38
some
31:38
of
31:38
the
31:39
more
31:39
challenging
31:40
shelf
31:40
situations
31:41
at
31:41
scale.
31:43
So
31:43
some
31:44
of
31:44
those
31:44
examples
31:45
include
31:45
things
31:45
like
31:46
plugs
31:46
and
31:46
spreads,
31:47
so
31:48
where
31:48
you
31:48
may
31:48
be
31:48
out
31:49
of
31:49
a
31:49
specific
31:49
flavor
31:50
or
31:50
sku
31:50
of
31:51
a
31:51
product
31:52
but
31:52
you
31:52
have
31:53
another
31:53
in
31:53
that
31:53
family
31:54
adjacent
31:54
to
31:54
it,
31:55
so
31:55
you
31:55
sort
31:55
of
31:55
face
31:55
that
31:56
over.
31:57
We
31:57
see
31:57
a
31:57
lot
31:58
of
31:58
scenarios
31:58
in
31:59
stores
31:59
where
32:00
that
32:00
original
32:00
product
32:01
that
32:01
was
32:01
out
32:01
of
32:01
stock
32:02
stays
32:02
out
32:02
for
32:02
a
32:03
very
32:03
long
32:03
time
32:06
and
32:06
certainly
32:07
cost
32:07
the
32:07
retailer
32:08
both
32:08
from
32:08
sort
32:08
of
32:09
a
32:09
top
32:09
line
32:09
and
32:09
margin
32:10
standpoint,
32:10
even
32:10
inclusive
32:11
of
32:11
switching
32:12
and
32:12
substitution.
32:14
So
32:14
leveraging
32:14
these
32:15
types
32:15
of
32:15
advanced
32:16
capabilities
32:17
to
32:18
detect
32:18
some
32:18
of
32:18
these
32:18
scenarios.
32:19
Got
32:20
it.
32:20
So
32:21
I
32:21
want
32:21
to
32:21
ask
32:21
you
32:21
just
32:21
to
32:21
make
32:21
sure,
32:22
because
32:22
I
32:22
think
32:22
you
32:22
said
32:22
a
32:22
couple
32:22
words
32:23
there
32:23
that
32:23
I'm
32:23
not
32:23
sure
32:23
audience
32:23
is
32:24
not
32:24
familiar
32:24
with.
32:24
Plugs
32:25
and
32:25
spreads.
32:25
So
32:26
basically
32:26
you're
32:26
meaning
32:27
the
32:27
practice
32:27
of
32:28
the
32:28
store
32:28
manager,
32:29
the
32:29
store
32:29
team,
32:29
making
32:30
sure
32:30
that
32:30
their
32:30
planograms
32:31
still
32:31
look
32:31
good
32:31
and
32:32
shoppable
32:33
despite
32:33
their
32:33
inventory
32:34
not
32:34
being
32:34
fully
32:35
available
32:35
on
32:35
this
32:36
shelf,
32:36
which
32:36
is
32:36
a,
32:37
which
32:37
is
32:37
a
32:37
hot
32:37
button
32:38
issue
32:38
right
32:38
now,
32:38
because
32:38
I
32:38
was
32:39
talking
32:39
to.
32:39
I
32:39
won't
32:39
name
32:39
the
32:40
retailer,
32:40
but
32:40
it's
32:41
one
32:41
that's
32:41
very
32:41
near
32:41
and
32:41
dear
32:42
to
32:42
both
32:42
Anna
32:42
and
32:42
I's
32:42
heart,
32:43
where
32:43
they're
32:43
actually
32:44
potentially
32:45
instructing
32:45
their
32:45
teams
32:46
not
32:46
to
32:46
flex.
32:48
Flex
32:48
is
32:48
another
32:49
word
32:49
you
32:49
hear
32:49
for
32:49
it
32:49
versus
32:50
plug
32:50
and
32:50
spread.
32:51
Flex
32:51
their
32:51
inventory
32:52
to
32:52
cover
32:52
the
32:52
outs.
32:53
Because,
32:53
you
32:53
know,
32:53
generally
32:54
speaking,
32:54
that
32:54
was
32:54
the
32:54
mark
32:55
of
32:55
a
32:55
good
32:55
store
32:55
manager,
32:56
was
32:56
somebody
32:56
that
32:57
always
32:57
kept
32:57
their
32:57
store
32:57
looking
32:58
beautiful.
32:58
And
32:59
you're
32:59
saying
32:59
that
32:59
may
32:59
be
33:00
a
33:00
good
33:00
thing,
33:00
but
33:00
you
33:01
want
33:01
the
33:01
data
33:01
to
33:01
back
33:02
up
33:02
whether
33:02
it
33:02
is
33:03
or
33:03
is
33:03
not.
33:04
Is
33:04
that
33:04
right?
33:05
So
33:05
what
33:05
we're
33:05
actually
33:06
saying
33:06
is
33:06
it's
33:06
actually
33:07
a
33:07
bad
33:07
thing,
33:08
but
33:08
we
33:09
don't
33:09
think
33:09
when
33:09
it's
33:09
happening.
33:10
So
33:10
what
33:10
we've
33:11
been
33:11
able
33:11
to
33:11
prove
33:12
in
33:12
many
33:12
cases
33:13
is,
33:14
you
33:14
know,
33:15
that
33:15
particular
33:15
skewer
33:16
flavor
33:17
isn't
33:17
in
33:17
that
33:17
store
33:17
environment.
33:18
And
33:18
that
33:18
traditional
33:19
skewer
33:19
flavor
33:20
has
33:20
a
33:20
traditional
33:21
sales
33:21
velocity.
33:22
And
33:22
when
33:22
you
33:23
start
33:23
looking
33:23
at
33:23
that
33:24
data,
33:24
even
33:24
inclusive
33:25
of
33:25
things
33:26
like
33:26
substitution
33:26
and
33:27
switching,
33:28
you
33:28
start
33:28
to
33:28
see
33:29
that
33:29
many
33:30
plugs
33:30
and
33:30
spread
33:30
scenarios
33:31
are
33:32
actually
33:33
sort
33:33
of
33:33
detrimental
33:34
to
33:35
both
33:35
top
33:35
line
33:35
and
33:35
sort
33:35
of
33:36
bottom
33:36
line.
33:37
So
33:37
these
33:37
are
33:37
some
33:37
of
33:37
the
33:38
things
33:38
that
33:38
this
33:38
type
33:38
of
33:39
technology
33:39
has
33:39
uncovered.
33:40
You
33:40
step
33:40
into
33:41
a
33:41
retailer
33:41
that's
33:42
like,
33:42
hey,
33:43
we
33:43
think
33:43
we
33:43
have
33:43
a
33:43
very
33:43
efficient
33:44
operation.
33:45
We're
33:45
only
33:46
a
33:46
2%
33:46
out
33:47
on
33:47
shelf
33:47
rate.
33:48
What's
33:48
like,
33:48
hey,
33:49
let's
33:49
double
33:49
click
33:50
on
33:50
that.
33:50
Yeah,
33:51
and,
33:52
you
33:52
know,
33:52
see
33:52
what's
33:53
sort
33:53
of
33:53
really
33:53
there.
33:54
And
33:54
certainly,
33:55
you
33:55
know,
33:55
we
33:55
often
33:55
find
33:56
opportunities
33:56
and
33:57
it's,
33:57
it's
33:57
not
33:57
the
33:57
store
33:58
team's
33:58
fault,
33:58
as
33:59
you
33:59
said,
33:59
Chris,
34:00
many
34:00
times
34:00
they're
34:00
instructed
34:01
to
34:01
do
34:01
this.
34:03
But
34:04
what,
34:04
where
34:04
we're
34:05
seeing
34:05
the
34:05
opportunity
34:06
is
34:06
let's
34:06
get
34:06
the
34:07
right
34:07
product
34:07
back
34:08
on
34:08
shelf
34:09
because
34:09
it
34:09
was
34:10
supposed
34:10
to
34:10
be
34:10
there
34:10
from,
34:11
you
34:11
know,
34:11
the
34:11
original
34:12
planogram
34:12
design.
34:13
Right.
34:13
And
34:13
I
34:14
would
34:14
imagine
34:14
Brad,
34:14
that
34:15
that
34:15
gets
34:15
back
34:15
to
34:15
your
34:15
earlier
34:16
questions
34:16
of
34:16
understanding
34:17
where
34:18
the
34:18
problem
34:19
is.
34:19
Is
34:19
it
34:19
supply
34:20
chain,
34:20
like
34:20
you
34:20
didn't
34:21
have
34:21
the
34:21
product
34:21
to
34:22
restock
34:22
or
34:23
you
34:23
know,
34:23
like
34:23
what,
34:24
what's
34:24
the
34:24
solution
34:25
that
34:25
we
34:25
can
34:25
look
34:26
at
34:26
when
34:26
our
34:26
regional
34:27
manager
34:27
is
34:27
in
34:28
store?
34:28
We
34:28
could
34:28
talk
34:29
address
34:29
this.
34:30
We
34:30
can
34:30
get
34:30
through
34:30
and
34:30
like
34:31
have
34:31
some
34:32
consistency
34:33
in
34:33
what
34:33
we're
34:33
looking
34:33
at
34:34
to
34:34
try
34:34
to
34:34
get
34:34
to
34:34
the
34:34
root
34:35
of
34:35
the
34:35
problem.
34:36
Exactly.
34:37
And
34:37
we
34:37
see
34:38
we
34:39
actually
34:39
have
34:39
this
34:40
internal
34:40
forum
34:41
at
34:41
Simbi,
34:41
we
34:41
call
34:42
it
34:42
Skew
34:42
stories.
34:43
But
34:43
we
34:43
get
34:44
these
34:44
incredible
34:45
quotes
34:46
from
34:47
our
34:47
customer
34:47
success
34:48
team,
34:48
from
34:48
our
34:48
sales
34:49
teams
34:49
almost
34:50
daily
34:50
from
34:51
stores
34:51
all
34:51
across
34:52
the
34:52
country
34:52
and
34:53
sort
34:53
of
34:53
globe
34:54
with
34:54
these
34:54
types
34:54
of
34:55
scenarios.
34:57
And
34:57
perhaps
34:58
this
34:58
is
34:58
something
34:59
we
34:59
should
34:59
find
34:59
ways
35:01
to
35:02
share
35:02
with
35:02
the
35:02
world
35:03
because
35:03
it
35:03
helps
35:03
to
35:04
highlight
35:04
just
35:04
the
35:05
type
35:05
of
35:05
shelf
35:06
execution
35:06
challenges
35:07
retailers
35:08
and
35:08
brands
35:08
deal
35:08
with
35:09
all
35:09
the
35:09
time.
35:10
I
35:11
would
35:11
say
35:11
another
35:11
big
35:12
area
35:12
of
35:12
focus
35:12
that
35:12
we've
35:13
seen
35:13
with
35:13
retailers
35:14
really
35:14
operationalizing
35:15
this
35:15
data
35:16
themselves
35:16
is
35:17
a
35:17
big
35:17
focus
35:17
on
35:17
dsd.
35:19
So
35:20
the
35:20
direct
35:20
to
35:20
store
35:21
delivery
35:21
partners,
35:22
milk,
35:22
bread,
35:23
soda,
35:23
juice
35:23
folks.
35:25
Because
35:25
when
35:25
a
35:25
consumer
35:26
comes
35:26
into
35:26
a
35:26
store
35:27
they
35:27
don't.
35:29
They
35:30
attribute
35:30
that
35:31
product
35:31
to
35:31
sort
35:31
of
35:31
the
35:32
retailer.
35:32
Right.
35:32
100%.
35:34
Yeah,
35:34
they
35:34
have.
35:34
They
35:35
would
35:35
have
35:35
never
35:35
have
35:36
any
35:36
idea
35:36
that
35:36
that's
35:36
how
35:37
it
35:37
gets.
35:37
They're
35:37
not
35:37
blaming
35:37
Coke
35:38
for
35:38
not
35:38
being
35:39
there.
35:39
Yeah,
35:39
right.
35:40
Yeah,
35:40
yeah.
35:41
So
35:41
this
35:41
data
35:42
is
35:42
often
35:42
used
35:42
to
35:43
optimize
35:43
truck
35:43
rolls
35:44
into
35:44
your
35:44
point
35:45
earlier,
35:45
Chris,
35:46
what
35:47
does
35:47
the
35:47
shelf
35:47
look
35:48
like
35:48
before
35:48
they
35:48
come
35:48
in
35:49
and
35:49
what
35:49
does
35:49
it
35:49
look
35:49
like
35:50
after?
35:50
Right.
35:51
Yeah,
35:52
it's
35:52
really,
35:52
it's
35:53
really
35:53
interesting
35:53
too.
35:53
Like
35:54
when
35:54
I
35:54
think
35:54
about
35:54
this,
35:54
like
35:55
from
35:55
having
35:55
been
35:56
a
35:56
district
35:56
manager,
35:56
a
35:57
store
35:57
manager,
35:57
like
35:58
you
35:58
know,
35:58
what
35:58
is
35:58
the
35:58
size
35:59
of
35:59
the
35:59
out
35:59
that
35:59
I'm
36:00
having
36:00
to
36:00
talk
36:00
about
36:00
too?
36:01
And
36:01
like
36:01
having
36:02
that
36:02
information
36:02
before
36:03
I
36:03
make
36:03
the
36:04
decision
36:04
on
36:04
what
36:04
to
36:05
do,
36:05
do
36:05
I
36:05
flex
36:05
it,
36:06
do
36:06
I
36:06
leave
36:06
it
36:06
open?
36:07
You
36:07
know,
36:08
that's
36:08
just
36:08
information
36:09
that
36:09
should
36:09
be
36:10
discussed
36:10
which
36:10
historically
36:11
has
36:12
not
36:12
been.
36:12
And
36:13
there's
36:13
probably
36:13
not
36:14
one
36:14
right
36:14
answer
36:15
for
36:15
every
36:15
situation
36:16
to
36:16
do
36:16
the
36:17
same
36:17
thing
36:17
either.
36:18
And
36:18
that's
36:18
the
36:18
beauty
36:19
and
36:19
art
36:19
of
36:20
retail,
36:20
which
36:20
is
36:20
why
36:20
we
36:21
need
36:21
to
36:21
bring
36:21
data
36:21
to
36:22
it.
36:22
Yes.
36:23
And
36:23
that's
36:23
where
36:23
we
36:23
help
36:23
them
36:24
prioritize
36:25
like
36:25
in
36:25
our
36:25
mobile
36:25
app
36:26
directly,
36:27
we
36:27
will
36:27
help
36:28
them
36:28
understand
36:28
the
36:29
cost
36:29
of
36:29
that
36:29
out.
36:30
You
36:30
know,
36:30
what
36:30
is
36:31
the
36:31
missed
36:31
sales
36:31
opportunity
36:32
today,
36:32
this
36:33
week
36:33
for
36:33
not
36:33
having
36:33
that
36:34
product
36:34
on
36:34
shelf
36:35
as
36:36
well
36:36
as
36:36
how
36:36
is
36:37
it
36:37
relatively
36:37
prioritized
36:38
against
36:39
all
36:39
the
36:39
other
36:39
tasks
36:40
that
36:40
are
36:40
out
36:40
there?
36:40
Right,
36:41
right.
36:41
Your
36:41
point
36:42
not
36:42
all
36:43
outs
36:43
are
36:43
created
36:43
equal.
36:44
Right.
36:45
Yeah.
36:45
And
36:46
how
36:46
pissed
36:46
are
36:46
the
36:46
customers
36:47
that
36:47
they're
36:47
potentially
36:47
looking
36:48
at
36:48
empty
36:48
shelves
36:48
in
36:49
that
36:49
section
36:49
of
36:49
the
36:49
store
36:50
too?
36:50
Which
36:50
is
36:50
a
36:50
factor
36:51
too,
36:51
Right?
36:51
I
36:52
mean,
36:52
we
36:52
hear
36:52
that
36:52
a
36:52
lot.
36:53
Oh,
36:53
man,
36:53
this
36:54
is
36:54
great.
36:54
Yes.
36:55
Brad,
36:55
thank
36:55
you
36:56
so
36:56
much
36:56
for
36:56
taking
36:57
the
36:57
time
36:57
with
36:57
us
36:57
today.
36:59
It
36:59
was
36:59
so
36:59
insightful.
37:00
It
37:00
was
37:01
so
37:01
fun
37:01
to
37:01
get
37:02
to
37:02
get
37:02
properly
37:03
schooled
37:03
on
37:04
robotics
37:04
and
37:05
what
37:05
we
37:05
can
37:05
expect
37:06
in
37:06
the
37:06
year
37:06
ahead
37:07
here.
37:08
I'm
37:08
sure
37:08
there's
37:08
a
37:09
lot
37:09
of
37:09
people
37:09
who
37:09
are
37:09
going
37:09
to
37:09
be
37:10
reaching
37:10
out.
37:10
They
37:11
want
37:11
to
37:11
get
37:11
in
37:11
touch
37:11
with
37:12
you.
37:12
What's
37:12
the
37:12
best
37:12
way
37:12
for
37:12
them
37:13
to
37:13
do
37:13
that?
37:14
Absolutely.
37:15
You
37:15
know,
37:15
first
37:15
and
37:15
foremost,
37:16
I
37:16
would
37:16
encourage
37:17
folks
37:17
to
37:17
hit
37:18
our
37:18
website,
37:18
simirobotics.com
37:20
you
37:21
can
37:21
reach
37:21
out
37:21
to
37:21
me
37:22
personally.
37:22
I'd
37:22
love
37:23
to
37:23
hear
37:23
from
37:23
you.
37:23
It's
37:24
just
37:24
BradIMBY
37:25
robotics.com
37:26
or
37:27
search
37:27
for
37:27
me
37:28
on
37:28
LinkedIn.
37:28
Brad
37:29
BegoliaIMBI
37:31
and
37:31
would
37:32
love
37:32
to
37:32
hear
37:32
from
37:32
you.
37:34
And
37:34
Chris
37:34
and
37:34
Anne,
37:35
thank
37:35
you
37:35
so
37:35
much
37:35
for,
37:36
you
37:36
know,
37:36
the
37:36
opportunity
37:37
and
37:37
dialogue
37:37
to
37:37
be
37:38
here
37:38
today.
37:39
Wonderful.
37:40
Well,
37:40
thank
37:41
you,
37:41
Brad
37:41
Begolia.
37:42
That
37:42
wraps
37:42
us
37:42
up.
37:43
Brad
37:43
Begolia
37:43
of
37:44
Simbi.
37:44
Thanks
37:45
to
37:45
everyone
37:45
out
37:45
there
37:45
for
37:46
listening
37:46
in
37:46
as
37:47
well.
37:47
And
37:47
on
37:47
behalf
37:48
of
37:48
all
37:48
of
37:48
us
37:49
at
37:49
omnitalk,
37:50
as
37:50
always,
37:51
be
37:51
careful
37:51
out
37:51
there.