Play
Show Navigation
Show Transcript
00:00
Play
Seek 10 seconds backwards
Seek 10 seconds forward
00:00 / 01:41:27
Mute
Disable Captions
Settings
Picture in picture
Fullscreen
Search in video
You can search the video captions for specific words or phrases.
Popout transcript
Hide Transcript
Skip transcript
[UPBEAT MUSIC]
Salesforce.
For 25 years,
we've been a force
for sales, a
force for service,
a force for marketing, for
commerce, for analytics.
Well, starting now, we're
also your Agentforce.
A force for humans
with AI agents
to drive customer
success together.
Agentforce is not about
AI replacing people.
It's about how do
we enhance employee
experience to deliver
a better customer
experience.
We're not just talking
about a business
evolution.
We're talking about
an agent revolution.
Agents with the power
to act on behalf
of you and your business.
Agents with
context to make
customer relationships
more personal.
Agents with the
ability to do it
all intelligently,
accurately,
and autonomously.
Because when you've got
trusted AI agents at work,
your business can
succeed at scale.
Agentforce gives
us the ability
to deliver that high
touch, personalized
service to everybody.
You can improve
the communication
between supply and
demand, between patients
and doctors, employees
and employers, clients
and customers.
You see, this isn't
another basic bot.
No, this is a bona
fide Agentforce A-team.
This is using
data to reach
every possible
customer with exactly
the right message, then
taking immediate action
so they have exactly
the right experience.
This is augmenting
and elevating
humans to new heights
while always staying
grounded in trust.
It will help humans
become more human.
Welcome to a force of
meaningful and effective
intelligence.
Welcome to a
force for purpose,
for trust, and for good.
Welcome to Agentforce.
It's what AI
was meant to be.
And now, our CEO and
chair, Mr. Marc Benioff.
All right, here we go.
[CHEERS, APPLAUSE]
All right.
Good morning, everybody.
No, I said good
morning, everybody!
All right.
It's great to be
with all of you.
What a great day it
is in San Francisco.
A gorgeous day.
We are thrilled to
be with you today.
We are absolutely
thrilled,
and we are
grateful that you
are coming here all
the way from all
over the world
to be with us.
And this is going to be
an incredible program.
It is Dreamforce.
That is exciting.
How about that?
Are we excited to
be at Dreamforce?
[APPLAUSE]
And this Dreamforce
is really
like no other
Dreamforce we have ever
had because this
Dreamforce is about humans
with agents driving
customer success together.
Now, before I get
going on the stage--
and I'm super
excited because
for the last
several weeks,
we've been traveling
all over the world,
meeting with you, meeting
with our customers,
doing focus groups,
reviewing what we're
doing, and tuning
our message, kind
of figuring out what
we're going to say here.
And I'll tell you what.
We're here to inspire
you, to motivate you,
to energize you.
But before we can do
any of those things,
you know what
we have to do?
We have to thank you.
We have to thank each
and every one of you
for what you do for
us every single day.
We are so grateful to you.
We are so grateful
to all of you,
all over the world.
Those who are in this
audience right here
and those of us who
are watching us online
as well, thank you.
We are deeply grateful
to you, our customers.
We are so grateful
to our partners,
our Trailblazers.
We have some Trailblazers
here, some Serviceblazers,
some Datablazers, some
Salesblazers, some Data
Fammers, some Mulies.
[CHEERING]
Got some Mulies.
This is cool.
We have some
employees here.
We have some
community members.
We're so excited to
have all of you here.
And I'll tell you one more
group I want to thank.
This year especially
it's so important to me
personally.
I want to thank San
Francisco and California
for everything that
you've done for us.
[APPLAUSE]
And you're going to
see our fire department
and our police department
here in San Francisco
have done an extraordinary
job to get us going
and to make sure that
this is a safe and trusted
environment.
We're so grateful
to them and
to our whole
municipal agencies
as well throughout
the city.
And, of course, our mayor
has done a fantastic job
with us, getting ready for
this incredible program.
And I also want to thank
Gavin Newsom, who happened
to bring down an extra
couple of hundred CHPs
to keep our streets
safe for us.
So would you
do me a favor,
and if you see our
firefighters and police
force around
and everything
they're doing
to keep us safe,
would you give them
a pat on the back
and tell them thank
you on behalf of me
and tell them how grateful
that we are for being here
with us?
Thank you.
Now, one more thing.
We have a phenomenal
program put together
for you.
We have unbelievable
speakers--
1,500 sessions.
Now, we have
1,500 sessions.
45,000 people are
here in person.
Millions that are
joining us online.
We have 200 sponsors.
And these sessions
are incredible.
Look at all these
amazing speakers.
We expect you to go
to each and every one
of these 1,500 sessions,
so pay attention to those.
And we're going to
do an amazing concert
tomorrow night.
Is everyone excited to see
Pink and Imagine Dragons?
[APPLAUSE]
And we're also going to
have some great music
going on Howard Street
as well during the show.
We've got a lot of
surprises happening out
there.
You may be seeing some
of your favorite artists
appearing right in the
Howard Street world.
And all of this
is benefiting
our UCSF
Children's Hospital
that we're so
grateful for having,
and we've now given more
than $120 million to them.
How about that?
Pretty awesome.
So thank you for giving
back all the time.
Continuously giving back.
That's part of our core
values here at Salesforce.
As you probably know, we
have a set of core values
that we have been working
on for about 25 years.
And those 25-year core
values are still alive
and well.
Trust, customer success,
innovation, equality,
sustainability.
And they're more
important than ever,
especially when
you see how
it relates to
artificial intelligence.
And all the
technology we're
going to speak to
translates down
to that idea that your
data is not our product
here at Salesforce.
Now, it turned out
about 25 years ago,
we took a very
interesting moment.
We said we would take 1%
of our equity, our profit,
and all of our
employees' time,
and put it into a
501(c)(3) public charity.
Have you heard
about that already?
But guess what.
We had no equity.
We had no profit.
We had no time.
It was very easy to do.
Well, it turned out that
was a really good idea
because now,
25 years later,
we've given away
almost $1 billion.
We've done almost
10,000,000 hours
of volunteerism.
59,000 nonprofits and
NGOs run on our services.
We've been able to give
away more than $150
million to our local San
Francisco and Oakland
public schools,
including $23 million
that we gave
away yesterday.
We're giving
another $3 million
to our Hawaii
Department of Education,
a group that
we're very, very--
have in our hearts
every single day.
And we're a net
zero company.
And 18,000 companies have
followed us in this 1-1-1
model.
So first of all, here's
my opportunity to say,
if you are with a
non-profit or an NGO,
would you just stand up
and be recognized now?
If you're with a
non-profit or NGO.
All over this
room, if you're
with a nonprofit
or an NGO.
Look around.
Look around.
These are the people we
want you to help support.
They're doing God's work.
We want you to be
aligned with them.
OK, look it.
It's been an incredible
journey with Salesforce.
We are the number one CRM.
We are the second-largest
software company
in the world.
It's been a fast
track to $38 billion.
It's been incredible,
hasn't it?
And it's been incredible
how much of it
has happened right
here in this room.
It's amazing.
Incredible.
Look at that slide.
Who would have
ever thought
it's even possible?
And we did it
the right way.
And we did it with
great technology.
And what we're going to
talk about at this event
and what's
really happening
in our whole
industry right now
and why we are more
excited than ever
is because what's
happening with AI?
Now, through Dreamforces
for the last, especially,
10 years, we've
been talking
about the emergence
of AI and how
AI has been a critical
part of our future.
And we introduced
you to Einstein.
We did so much
in deep learning.
We did so much.
We even invented prompt
engineering at Salesforce.
And then as we've
gone forward and built
our own models and
added to our technology
and did all these things
to be a pioneer in AI,
it became clear to
us this was a moment.
This was a
moment of change.
See, we saw that first
generation of AI happen.
And we talked about
all those things--
predictive and
Einstein predictions
and the idea of building
Einstein into the platform
and how Einstein was going
to be a co-intelligence
with you and support you.
And I've been even
using that myself
now for five or six
years, where my management
team will tell me what
my sales figures are.
But at the end
of every meeting,
I will always say,
hey, Einstein,
what do you really
think is happening?
Powerful.
Sales leaders don't
like it so much.
Great for me, however.
That's very important.
And then we moved into
this Copilot world,
but the Copilot
world has been kind
of a hit-and-miss world.
A Copilot world has been a
world where customers have
said to us, hey, I've
got these Copilots,
but they're not
exactly performing
as we want them to.
We don't see how that
Copilot world is going
to get us to
the real vision
of artificial
intelligence,
of augmentation, of
productivity, of better
business results that
we've been looking for.
We just don't see
Copilot as that key step
for our future.
In some ways, they kind
of looked at Copilot
as the new Microsoft
Clippy, and I get that.
But it was pushing us.
It was pushing us.
And they were
trying to say to us,
what is the next step?
And we are now really
at that moment.
And that is
why this show--
this show is our most
important Dreamforce ever.
There's no question,
this is the most exciting
Dreamforce and the most
important Dreamforce.
And what you're going
to see at this show
is technology like you
have never seen before.
But it's going to
be more than about
just seeing
the technology.
We're going to let you
get what I've been telling
people, your hands
into the soil
to touch the technology
because this technology is
incredible.
Now, how many of you have
already been in a Waymo
already in San Francisco?
Raise your hands
if you've already
taken a Waymo ride.
Oh, not very many.
Well, let me
encourage you.
Put the Waymo app on your
phone while you're here
and call the car to
come and pick you
up because it is a moment.
It's a moment, OK?
The first time you take a
ride in an autonomous car
is a moment.
And that is an
opportunity for you
to do that, right
here in San Francisco.
That's something that
we expect you to do.
Try it out.
And the reason I'm
making that metaphor
is very simple
because the first time
you build and deploy--
the first time you
build and deploy
your first autonomous
agent for your company
that is going to help you
to be more productive,
to augment your employees,
and to get these better
business results,
you're going
to remember that
the first time it
was in your moment--
in your Waymo.
This is the third wave AI.
This is the
third wave of AI.
It's agents.
And we are
getting feedback
from you, from our
customers who have it
already, and I hope by
the end of this show--
because each and
every one of you
is going to have
an opportunity
to deploy your own
agents at the show.
Pretty cool, actually.
This is going to be
something that we are not
going to forget, hopefully
because it goes very well.
But it's a little
bit of a high wire
act for a
technology company
because we're doing
something that no one has
ever done before.
But that's not
unusual for us.
We've been
doing those kind
of things for 25 years.
We love building the
number one AI CRM.
That's what we
really, really love.
But now we're going
to deliver something
like we've never
delivered before.
And we know that idea
that we can give you,
that next
capability, well,
that's just built into
our DNA at Salesforce.
It is.
You see, right
here, we've been
doing this for 25
years because for you,
our trailblazers?
Oh, come on.
This is what
we love to do.
We want to be the
first to welcome you
into the future.
We want to be the
first to welcome you
into the future.
And we look at our
Salesforce platform
as your future
as a service.
We want to
future-proof you, not
only in your careers,
but your companies, too.
And it has happened in
the Cloud, when we first
introduced our
platform in 1999.
And we said, we're
going to help
you get into the Cloud.
And then Mobile, in 2006.
And we said, we're
going to help
you get into mobile.
And we said, hey, social.
We're going to help
you get into social.
Yes.
And we helped
our customers
get into AI first.
And data-- for the
last several years,
we've been introducing the
concepts of building data
lakes and federating those
data lakes with zero copy.
And now, with agents--
this idea that
we are all going
to be using an agents.
But we're going to do it
all within our Salesforce
platform.
We're going to do it all
within our Customer 360
apps.
And we've rewritten
all of our Customer 360
apps, even the
ones that we've
acquired, into one
consistent, singular
platform.
And that platform
that we're all
very familiar with that
has three releases a year,
this platform is the
key strategic motion
of Salesforce.
And now this platform has
the best AI in the world--
we're about to
review that--
and the best agents.
And the reason why
that is so important
is because it is going to
empower you and enable you
to bring that to
your customers
and to your companies
and to your selves.
And we see that every
Trailblazer must be,
of course, a Salesblazer,
a Serviceblazer,
a Marketingblazer,
a Commerceblazer,
every sale--
every Trailblazer has
to become a Mulie.
But every trailblazer
also can become now
an Agentblazer.
And we've been very
proud for 25 years.
We've been very proud
for 25 years here
at Salesforce
to, of course,
help you manage
your Salesforce.
This has been very
important to us.
So thank you for letting
us manage your sales
organization.
We're so grateful to you.
How are you?
Good morning.
Is this the
Japanese section?
By some reason, I
might know that.
[SPEAKING JAPANESE]
How are you?
How are you?
Good.
[SPEAKING JAPANESE]
Thank you for all
your hard work.
So we've helped you
deploy your sales
forces, your service
forces, your marketing
forces.
We've helped you deploy
your commerce forces
and your analytics forces.
Of course, we've
also helped
you, over the last
several years,
deploy your data forces,
your Slack forces.
But now, and at this
show, what we're all
going to do
together is we're
going to work to deploy
your first Agentforce.
And in the way
that when you
get in that first Waymo
and have that experience
of a car driving you
around San Francisco
and going, whoa,
there's no driver,
you're going to have that
moment where you say, wow,
I'm deploying autonomous
agents for my company,
and it is working--
hopefully.
It's a high wire act in
the technology industry,
as I mentioned,
because this
is incredible
technology and code.
And the results that we're
seeing are just awesome.
Look, we know
back at home,
workforces are
overwhelmed.
They're doing these
low value tasks.
They've got kind of a
whole different thing post
pandemic.
Productivity is a
different place.
Capacity is a
different place.
You talk to doctors and
nurses and health care
centers all
over the world,
they'll tell you
the same thing.
They're kind
of burned out.
They kind of are looking
for a different way
forward, maybe
because we're
more anxious
about our health,
since the pandemic.
I'm not sure.
I'm not sure.
But whatever it is, we
do see that workforces
are different.
And we realize that
41% of the time
seems to be wasted
on low values
and repetitive tasks.
We want to address that.
Customers are expecting
more-- zero hold times,
to be more personal
and empathetic,
to work with an expert
all the time, to instantly
schedule things.
That's our vision, our
dream, for these agents.
The thing that's
really interesting
is we have a very large
health care organization
here in the Bay Area, and
they've been testing this.
And they've got
the best AI,
and they came
back and said,
this might be
working better
than the best AI we have.
And it's just giving
our doctors and nurses
more capability,
more capacity.
That idea that
we're directly
addressing the
burnout issue
by giving more
productivity
and more capacity to those
doctors and nurses, that
means everything to us.
That is very exciting.
It inspires us to think
about this in a new way.
That's when we
can start to say,
what if these workforces
had no limits at all?
Wow.
That's kind of a strange
thought, but a big one.
You start to put all
these things together,
and you go, we can build
another kind of company.
We can build a
different kind
of technology platform.
We can take the Salesforce
technology platform
that we already have
and that all of you
have invested
so much into--
the Salesforce
platform-- and we
can deliver it the
next capability.
The next capability
that's going
to make our companies
more productive,
to make our employees
more augmented,
and just to deliver much
better business results.
And that is what
Agentforce is.
Agentforce has to be
the biggest breakthrough
that we have ever
had on technology,
and I think it's the
biggest breakthrough
that I've seen
in a long time
in artificial
intelligence.
It's about humans
with agents driving
customer success together
on the Salesforce
platform.
I love that
line because one
of the cool things about
Salesforce is we're
not just tossing
you another model
or tossing you
a hyperscaler
or tossing you
an AI engineer
or tossing you
something else.
We're just saying, on the
platform that you already
love and use every day,
the Salesforce platform,
right inside the
configurator,
right inside the
system that you already
love and know,
you're going
to start to find
this incredible new
functionality.
And of course, it's going
to be trusted and secure.
It's going to have
a trust layer.
All of those things
are right there.
And we realize how
important that is.
I read a Gartner
report last week
about those
nasty Copilots,
and they were
spilling data all
over our
customers' floors.
And we're like, that is
no good for our customers.
That's not the kind
of businesses we run.
And of course, just like
every other Salesforce
platform, we're
going to be
able to just have
instant scalability,
but a very high
level of accuracy.
In fact, you're going
to find these agents--
these agents
are going to be
some of the lowest
hallucination agents you
have ever experienced.
And why is that?
Why would our agents be
so low, hallucinogenic
and so accurate?
Well, it has to do
with the platform.
It's because we have the
data and the metadata
and the workflow and
the business process
and the security model
and the sharing model
and all those things that
we love and have used
and are deeply wedded
to for 25 years.
It turns out those things
make a more accurate AI.
It turns out that
those things give us
what we need to have more
of a low hallucinogenic
AI.
And of course,
we already know
that we're going to
make it easy to build
these agents.
Well, you're
going to be doing
that in the next
couple of hours.
We already know all
the AI capabilities
and the models
and the ability
to train the models.
You're not going to
be buying a model
from a model company.
You're not going to have
to go somewhere else
to figure out how to bolt
on some other kind of AI.
No, no.
You're going to have
the most accurate AI
in the world built
into this platform.
And-- oh, yeah,
one more thing.
The platform also has all
these Customer 360 apps.
The apps are also
inside the platform.
It's one of
the reasons why
the AI is so accurate is
because it understands
the logic that's
coming out of the apps.
Because the more
customer touchpoints
you have with Salesforce,
the more our AI
learns and understands
who your business is
and how it can help you.
Because you're doing so
much with our platform
already, we have the
data and the metadata
and the knowledge
from these apps
to be able to support
you, and you're
going to see that in
real time at this show.
And of course, it's a
unified metadata platform.
It not only knows
what your data is--
your phone number,
here's my number--
but my metadata.
Oh, it's a phone number.
Because we can put those
two things together,
again, it's why the
AI is so accurate.
And it's an open system.
How many people
in the room
are actually partners
with Salesforce?
Raise your hands.
Welcome to all the
partners here--
all the partners and ISVs.
And this is
going to provide
a whole new
generation of apps
as well because
we already see now
all kinds of new apps
that we can build,
importing data into
our Data Cloud,
building apps around
that platform,
and being able
to deploy that
with these agents in
incredible new ways.
We're really seeing
some exciting things.
We're really seeing
that Agentforce is also
going to be
about surrounding
all of this technology--
which we'll GA in
October, but you're
going to have it
here at the show--
with our innovation,
by every industry,
and all of our global
community, all of you
worldwide.
We're going to try
to light this up
for everybody as
fast as possible.
It is amazing.
And the early stories
from customers
are blowing our mind.
It's blowing our mind.
I have to tell you about
one of my customers
that I'm so proud of.
I'm so proud of them.
Wiley.
We've talked about
Wiley at this show
so many times.
I've met with them
so many times.
It's more than a decade
of our relationship
with Wiley.
We love Wiley.
OK, do you know what?
This is their Super
Bowl right now.
Did you know that?
Because this is
back to school.
It's back to school,
so guess what?
Everybody's buying the
books and all this.
But what do you
do if you're
Wiley at this point?
You need to hire some
more workers, right?
Gig workers and
surge the workforce.
And not so easy,
actually, right
now in today's economy.
So how about this.
What if you could surge
your service organization,
and you could surge
your sales organization,
without hiring
more people?
That's Agentforce.
That is what's
so exciting.
And Wiley is
already reporting
that they're resolving 40%
to 70% of these aid cases.
And the next version
of Agentforce,
which is version 2 you're
going to hear about,
called Atlas--
Atlas-- Atlas, we are
seeing more than 90%
to 95% resolution on all
service and sales issues.
90% to 95% with
the new Atlas,
which is version
2 of Agentforce.
Another amazing
customer that we use--
I know I just
used it myself--
OpenTable.
I was in Los
Angeles last week
rolling this out
and making a dinner
reservation for The
Grill in Beverly Hills.
One of my favorite places.
I love the
creamed spinach.
And all of a sudden I'm
making the reservation,
and I'm resolving my
customer service issue.
And I'm able to do
it with an agent.
And that was a moment.
Very cool.
Jim Cramer is here.
Just saw you
sitting here, Jim.
Welcome to Dreamforce.
I don't think you've
ever been to the keynote
before.
Come on.
That's awesome.
We gave you a good
seat and everything.
Please welcome Jim Cramer.
[APPLAUSE]
And Fossil.
Fossil-- does
everybody know Fossil?
The amazing watches
and the retail stores.
And they're using
this to envision
the future of Fossil
in sales and service
in the retail environment.
So exciting.
So exciting.
But let me tell
you where I'm
going after Dreamforce.
I'm going to Disneyland.
I am going to Disneyland.
How many of you have
been to Disneyland?
Anybody here?
Not that many.
Shocking.
OK, great place to go.
Number two, how
many of you,
when you go to Disneyland,
get a Disney guide?
Raise your hand.
Only a couple of hands.
Let me give you a tip.
Avoid the ride lines.
Avoid the ride lines.
Get a Disney guide.
You get a Disney guide.
They help you get
around the ride lines.
It's awesome.
It's like this service
created by Walt Disney.
They use Salesforce.
They've all got phones
in their pockets,
and they've got Slack.
And they've got
Salesforce on their phones
in Disneyland.
These Disney guides,
they're amazing.
I love them.
I have been to
Disneyland so many times.
I go, actually, about
four times a year.
One of my favorite
customers.
I love how they
use our store--
they use us for
their store.
They use us for Disney+,
for the customer service.
Across the whole
product line,
we're their customer
touchpoint automation.
But let me tell
you why I'm
excited about their
work with Agentforce--
because it's
about helping them
create these
unforgettable experiences.
And my vision here
is very simple,
and I think I can make
a compelling case of why
this will transform my
experience at Disneyland.
Because when I go to
Disneyland, I'm there.
I'm walking around
all the Frontierland
and Tomorrowland and
all these things.
And then I'll say to
my guide, let's roll.
We're going to go
to Galaxy Edge.
Do you know what
Galaxy Edge is?
It's Star Wars land, OK?
And then I'm
like, I'd like
to go right to this ride,
Rise of the Resistance.
Anyone here have been to
Rise of the Resistance?
Great ride.
OK, we've got a
couple happy people.
But Rise sometimes
isn't working.
It's so, so incredible,
a visionary ride.
Sometimes it's
working, sometimes
it's not working.
And then my guide
will know, oh, wait,
the ride isn't working.
But here's the thing.
The AI-- Agentforce--
well, my guide,
it can start
to work with
Agentforce and say,
Agentforce, we're on our
way right now to Rise.
And I got Marc
Benioff with me,
and I just got
a notification
that ride us down.
Agentforce, help me!
And Agentforce is
going to do two things.
One, it's going
to look at--
because I've opted
in, of course--
all my ride
history, how am I
doing, what I've been
on, what I liked, what
I didn't like, right?
What my personal
preferences are.
What brands I like
at Disney, on and on.
But number two, Agentforce
does one other thing.
It looks across
the whole park.
It looks across
the whole park,
and it says, oh, what
rides have long lines?
Where can we get
in Marc right now?
How do we do the
flow control?
How do we keep
the park moving?
Not how do we just
make Marc happy.
Brings the two things
together, and hey, Marc,
have you thought
about Toontown today?
It's just like the
Rise architecture,
but it's with this
incredible new brand,
Toontown.
And I'm on my
way to Toontown.
A better experience.
My Disney guide, working
with the agent together.
The agent doing what it
can do best, these very
complex situations.
This is really the vision
for a future of a company.
This is the company that
we're going to build here
at the show.
We're going to all
build this together.
And you're going to see
another amazing company.
Now, this slide was
not in the presentation
yesterday because
yesterday,
our customer, Saks--
who knows Saks
Fifth Avenue,
one of the great stores?
[APPLAUSE]
Wow.
We have more Saks Fifth
Avenue people here
than Disneyland people.
Amazing.
It really speaks
to something.
I don't know what.
So Saks came
in and said, we
want to give our
shoppers more concierge,
better return management,
better service management.
And last night,
they sent me
a link, and all
of a sudden,
they had Agentforce
running in their existing
Salesforce
implementation, and it
was live on their site.
And I said, I hope that
every Salesforce customer
has the ability to do
that at Dreamforce.
Will that be awesome?
So we added this slide
last night on what
happened yesterday because
we have flown in 4,000
of our own Salesforce
engineers to work with you
and help you
get this done.
And we've created
these launch pads,
and it's going
to be awesome.
Now, when I think
about Salesforce today,
I think about it in
three layers, maybe four.
First is, I think about
for the last 25 years,
what have we been doing?
We've been automating
every customer
touchpoint, right?
Sales and service
and marketing
and commerce and
analytics and Slack.
And anywhere your
customer is coming in,
we're connecting, and
we are making that part
of our Customer 360.
Two, we are also
building a Data Cloud
so that you have
a data lake that
is able to absorb
all of that customer
connectivity,
including if you have
multiple Salesforce orgs,
and federate that Data
Cloud out to not only
all your Salesforce orgs,
but to other types of
data lakes like Snowflake
and Databricks and Google
BigQuery and Amazon
Redshift and even
IBM mainframes.
Amazing.
And then we're able to
take all of that data
and bring it down
into the Customer 360.
And this has been our
vision for the last 25
years, but now
what we want to do
is wrap that with
agents and make
you even more productive
and more capable.
And it's an extension
of our core platform,
so you can have health
agents and banking
agents and product
agents and ops agents
and sales agents
and support agents
and marketing agents
and customer experience
agents and analytics
agents and finance agents
and HR agents,
and it's all
built on this
Salesforce platform,
with all the trust and
security and ecosystem
that you need.
And this means that
our architecture now
looks different.
It looks like this.
And this is not what it
looked like the last time
we were all in this room.
It didn't look like this.
This isn't where we were.
We had a different
vision of the future.
Customer 360
and Data Cloud
was our best-selling, most
exciting new product ever.
But agents are
really changing us.
They're transforming us.
They're giving
you that ability
to have something that's
trusted and secure
and scalable and
accurate and easy
to customize with
this built-in AI
and the Customer
360 is built in.
The metadata and the
data are built in.
The open ecosystem
are built in,
and you buy nothing
else from anybody
to make it work.
It just works,
with accuracy
and low hallucination.
And some of the
hypnosis that we've
had around AI, that it
doesn't work exactly
like that, or you
have to DIY it.
DIY-- do you all
know what DIY is?
I thought everybody
knew what DIY was,
but it's not.
Maybe it's a San
Francisco term.
DIY means do it yourself.
I was talking to my
friend Neil Young,
and he knew exactly what
that was because he said
it was like home grown.
But DIY means I'm just
putting it all together
on my own.
But I don't think
you can DIY this.
I think you want a single,
professionally managed,
secure, reliable,
available platform.
I think you want the
ability to deploy
this Agentforce
capability across all
of these people
that are so
important for your
company and all
of these digital
and human workers.
And the reality is
we all have struggled
in the last two years with
this vision of Copilots
and LLMs, and how are we
putting it all together?
So why are we
doing that when
we can have Agentforce?
We can move from
chat bots to Copilots
to this new
Agentforce world.
And it's going to
know your business,
and it can plan,
it can reason.
It takes action
on your behalf.
On that idea of working
with a large health care
system at scale,
it's scheduling,
in our vision,
the MRI for you,
or the CT scan, or
the repeat labs,
or your doctor's
office visit for you.
It's taking care
of the drudgery
and the low-value
tasks that
are slowing those
doctors and nurses down.
And we're going
to deliver it
across all of our
industry clouds in all
of the key industries
that we support with all
of the compliance and
governance that you need,
whether it's FedRAMP
or HIPAA or SOC
or whatever it is, so that
you get it as you need it,
and it's ready to go.
And I think we're
also going to inspire,
at this show, a whole
new generation of apps
built on our platform.
When we saw the large
network vendor come along
who said, oh,
Marc, we want
to help you get more
people back to office,
and look at who's
in the office
and who's not at office.
And I said, that's
interesting.
And they're like, we're
running your VPN for you.
And I said, well,
that's interesting.
And they said, we've
hooked our VPN data
into your Data Cloud.
And I said, oh, that's
very interesting.
And then we're looking
at the VPN data
in the Data Cloud.
And then they said,
and now look at this.
Here is now an
app that shows you
who's in the office
and who's not.
And I said, wow, that's
really next generation.
And then they
said, and now
here's a bunch
of agents that
are talking to
your employees,
encouraging them to
get back in the office.
And I said, wow,
that is something
I did not expect.
And I wonder how many
more apps are out there
that I didn't expect.
Now let's go and let's
look inside Agentforce.
Let's look at what
the possibilities are.
And please welcome the
CEO of our AI, Clara Shih.
Clara, where are you?
Here she is.
All right, Clara,
show it to us.
OK.
Thank you, Marc.
And this is my
18th Dreamforce,
and it is so special for
me to be here with all
of you in this moment
because we're in a time
when, in the
very near future,
agents will be as
commonplace as apps
and web pages.
And no one is better
positioned than all of us
trailblazers to deliver
on this amazing future.
So you just
heard from Marc
the vision for
agent force,
some of the customer
success that we're seeing,
and our ecosystem.
Now I'm going to take
us a little deeper
and talk about
what agents are
and why the Salesforce
platform is the easiest,
lowest-risk way to
build and deploy agents
for the enterprise.
Now, there are five
things that make an agent.
First, you need a role.
What's the agent's job?
It's similar to the
roles that you've already
defined in Salesforce.
If you use
Sales Cloud, you
have these roles
for your SDRs,
for your account
executives.
If you're like
Kevin from Wiley,
and you have service
reps on Service Cloud,
you have these roles
defined for your support
team.
And so if it's
back to school,
and you need to scale up
your service organization,
you can start there.
But it's not just
defining the role,
it's managing the role.
Many of you already
use Omni Supervisor
to manage all of
your service calls
in real time.
You can listen in.
You can track
how the CSAT is
trending for every single
call that's happening.
We have extended Omni
Supervisor to now
also help you manage
your Agentforce.
We'll show you this
in just a moment.
The second thing you
need is you need data.
You need data.
Again, you have this
data in Salesforce
already, whether
it's structured data
like a custom object, or
it's unstructured data,
like a Slack conversation
and knowledge articles,
all of that is there.
You have your metadata
in Salesforce,
and you can even bring
in your external data.
You heard Marc talk about
our zero copy partner
network from Data Cloud.
All of your data
from your data lakes,
your data warehouses,
all of that
can now be activated
by your Agentforce.
Now the third
thing you need--
this is really important--
is you need actions.
What are the workflows?
What are the systems
your agents can access
to get the job done?
Now, this is very
powerful because it's
the basis of automation,
and it is not
something you want to risk
having an LLM hallucinate.
Good news, you
don't have to.
You've spent 25 years
building your trusted
business logic
into Salesforce.
Whether it's your prompts
or the billions of flows
that run every single week
or every line of APEX code
you've invested in
and every MuleSoft
API, all of that is there
for you to point and click
and empower your
Agentforces with.
Now, the fourth thing
you need are channels.
This is where
your customers
and your employees
interact with the agent.
You already have
Sales Cloud.
You have Service Cloud.
You have Marketing
and Commerce Cloud.
And only the
Salesforce platform
offers all of the
major digital channels
natively from
within our app.
WhatsApp, Apple Business
Messenger, SMS, voice,
email--
it's all there.
You just turn it
on, and you go.
Now, the final,
most important thing
that you need to deploy
trusted enterprise agents
is trust and security.
The very first thing we
built when we started
on this journey was our
Einstein trust layer,
and every single
Agentforce interaction
runs through that
trust layer, which
means that you
can rest assured
that it has data security,
like prompt injection
defense.
It has data privacy, like
zero retention prompts
and data masking.
It has ethical guardrails,
like our toxicity filter.
It has guardrails
to define
what agents aren't
allowed to do
versus what they can.
It has observability
and monitoring.
But it's much
more than that.
If you take a step
back and look,
everything that
you've ever done
has led you to Agentforce
because every role,
every piece of metadata,
every flow, every channel,
all of that becomes the
guide and the guardrails
for your autonomous
Agentforce.
Now, let's talk about how
these pieces come together
to drive real
business outcomes.
It all starts with our
Atlas reasoning engine.
Atlas is the brain
of Agentforce,
and it takes your goal,
it takes your role,
and it loops.
It creates a plan.
It evaluates the plan.
It refines the
plan, and it
keeps looping until
it's confident it
can achieve your goal.
It uses advanced retrieval
augmented generation,
or RAG, to pull in
the structured and
unstructured data that
it needs from Data Cloud.
And then it takes
action for you
across the Customer 360,
whether that's automating
a financial services
campaign in Marketing
Cloud or it's engaging
with a prospect in Sales
Cloud or, in the
case of OpenTable--
I'm a frequent user of
OpenTable-- confirming
that perfect
dinner reservation
for your husband's
birthday.
All of that
comes together.
And if it ever
gets stuck, Atlas
knows to
seamlessly escalate
to one of your
team members
using Sales,
Service, Marketing
or Commerce Cloud.
Very smooth.
My favorite thing,
though, about Atlas
is that the more you use
it, the smarter it gets.
Because while everyone
else in the industry
is talking about
reinforcement learning
from human
feedback, we have
pioneered
reinforcement learning
from customer outcomes.
That's right, all
of the customer
outcomes you have
in the Customer
360, whether it's
marketing conversion rates
or sales deal
wins or service
resolutions,
all of that is
used to continuously
tune and improve
your Agentforce.
And because your data
isn't our product,
all of your outcome
data is proprietary
to your company,
allowing you
to create strategic
advantage over time.
Yeah, it's amazing.
Thank you.
[APPLAUSE]
And just tremendous kudos
to our fantastic research
organization for all of
the amazing technology
that's gone into
Atlas and Agentforce.
And we're seeing
amazing results--
33% greater accuracy, two
times greater relevance.
And these are according to
our customers benchmarks,
not ours.
And this is the difference
between a DIY science
project versus a real,
enterprise-grade agent you
can confidently deploy
into production.
And this is why
we are so thrilled
to be bringing Agentforce
now into every Salesforce
Cloud--
Sales Cloud, Service
Cloud, Marketing,
Commerce, every
industry Cloud
Einstein Copilot
is being officially
upgraded to Agentforce so
that it can learn, reason,
and take action for you.
And to help you
get going fast,
we're also excited to
be releasing over 100
out-of-the-box industry
specific actions
for Agentforce.
[APPLAUSE]
We also want to make
it really easy for you
to customize
your Agentforce,
as well as to
build your own.
You're familiar with
our low code tools.
I know, there's tens
of millions of you
trailblazers that use Flow
Builder, Model Builder,
Prompt Builder.
Well, I want you to
meet Agent Builder.
It's the newest member
of our low code family
and part of the
Agentforce studio.
And it allows you not only
to access a familiar look
and feel, but
also to access
any of the existing
data, metadata, roles,
and business
logic you already
have in Salesforce.
Just drag and drop
it into your agent.
That's how Saks
was able to get up
and running in
just a week.
And I know it's amazing
that 2.8 million badges--
you've earned 2.8 million
AI badges on Trailhead,
and I know you're
just getting started.
And you are well
on your way to each
becoming an Agentblazer.
Now, to see this come to
life, I want to hear--
I want you to hear a story
from a true Agentblazing
customer.
I see Mike there,
who's a CTO from Saks.
You want to give
a wave, Mike?
And to hear how they're
using Agentforce
to deliver luxury
experiences
to every customer
at scale.
Let's roll the tape.
We believe there's going
to be a fundamental shift
in the way that you
interact with humans
at Saks that's really
going to be enabled
by agent force.
At Saks, we
deliver a dream.
We sell things that
people want to love,
the emotional connection
you have with finding
that one thing you want.
There are lots of
new changes happening
across the
technology ecosystem.
You need to have
the best technology.
We saw the luxury
consumer beginning
to move to e-commerce.
We said, we've
got to pivot.
Really important for
us to meet the customer
where they want to
be and service them
in the best ways.
Agentforce offers
personalized service
to customers like Maria.
In this case, she has
a birthday coming up.
If you have millions
of customers,
and you want to
create millions
of different experiences,
it's not scalable.
But Agentforce gives
us that ability.
Agentforce will enable
us to service customers
in ways we couldn't
imagine before.
It will recognize photos
and understand text
and make personalized
recommendations
to customers like Maria.
We really believe there
is an immense opportunity
for Agentforce to allow
for our service agents
to become stylists, really
focus on clienteling
with our customers.
We are recommending
things for you
that are personal to you,
that are authentic to you.
Agentforce is really
allowing our humans
to have the deeper, more
impactful interaction
with our customers.
It gives us the
ability to continue
to offer a very
high touch,
luxury experience that
people expect from Saks.
And I know it
sounds simple,
but that full
360 degree view
of the consumer,
everything
they're doing from how
they're browsing, from how
they're shopping,
from what they return,
from what they call
the call center
about, from how they
pay, from everything,
really understanding
them, we're
going to give them that
comfort that they're
the most important to
us, which they are.
When Maria contacts
us, it's intelligently
routed to a customer
representative
based on the nature
of her question.
Agentforce is going
to free up our people
to work in a different
way with their clients.
It's not going to replace.
It's going to augment.
Here we have Agentforce
making a recommended
response based on customer
data, previous cases,
as well as
knowledge articles.
All we have to
do is hit post.
We believe that
Data Cloud is
going to be the platform
for us to activate
that data,
through servicing,
through commerce,
through order management.
If you can get
people comfortable,
and if you can
work with them
on an individual basis,
a personalized basis,
the sky's the limit on
what you can do with them.
I don't believe that
the experience that we
are delivering
would be possible
without Salesforce.
It goes back to the belief
that humans with agents
drive customer
success together.
Together, that's how
we're going to win.
[APPLAUSE]
You can always
tell the Saks team
because they're
the best dressed
people in the room.
Mike, thank you so much
for being an agentblazer.
And to show you Saks'
actual Agentforce,
please welcome up my
colleague, Patrick Stokes.
All right.
Thank you so much, Clara.
Good morning, everybody.
So I absolutely
love Dreamforce.
I love being on this
stage to show you
all these
incredible products.
But I'm going to admit,
I do get stressed out
about one kind
of silly thing,
and that's what I should
wear when I'm up here.
And even right now,
I'm not really sure
if this is technology
conference or fall
wedding in New Jersey.
It could be either.
So a couple days
ago, I decided
to go to the
saks.com website.
And I was browsing
along, and I
ordered a new jacket--
kind of jacket-sweater
combo that I really liked.
And it came to my house.
I tried it on, and
it didn't really fit.
And I had a crazy idea.
I thought it would be
really fun to bring 45,000
people together here in
San Francisco and millions
online and call
customer service.
Now, before we call
Saks' customer service,
I want to call everyone
else's customer service.
So let's give it a try.
[PHONE RINGING]
Hello, and thank you for
calling customer service.
If you now the
extension of the party
you are trying
to reach, you
may dial it at any time.
To hear our store
hours, please press 1.
To start a return,
please press 2.
For product inquiry--
Let's not do that.
That's no fun.
Nobody wants to call that
customer service line.
It doesn't feel natural.
It's not human.
I can't even
start talking,
which is what you do
when you pick up a phone.
I have to wait.
I have to select a number.
That is an absolutely
terrible experience.
In fact, do you
know what they call
that in the industry?
They call it
case deflection.
Did you know that?
They're actively
trying to deflect you
from talking to somebody
who can actually help you.
It's crazy.
We don't want that.
As consumers, as
customers, we want help.
We want resolution.
We want solutions
to our problems.
And after a few more
calls like that,
we might even want
some retribution.
That is terrible.
But the good news
is it doesn't
have to be like
that anymore
because we have
Agentforce,
and because Saks
has Agentforce.
As Marc showed us
earlier, Saks just
rolled out their new
Agentforce agent,
and they call her Sophie.
Let's give Sophie a call
and see if the experience
is any different.
[PHONE RINGING]
Hi, I'm Sophie, your
Saks AI assistant.
How can I help you today?
Yeah.
Hey, Sophie.
This is Patrick.
I'm wondering if you
can help me with my most
recent order.
I think I might have
got the wrong size.
I'm sorry to hear
that, Patrick.
I'd be happy to help.
Is this about the
Saks Fifth Avenue
COLLECTION Cashmere
Baseball Bomber Sweater
you purchased
on September 9?
Yep.
Totally is.
That's the one.
I tried it on,
and I think it's
just a little bit tight.
I'm sorry the sizing
didn't work out.
Based on your
purchase history,
a size medium should
provide a relaxed fit.
How does that sound?
Yeah, that sounds
pretty good.
But I noticed you
said cashmere.
Is it going to shrink?
The sweater is
100% cashmere,
so we recommend
dry cleaning only
to preserve the
natural fibers
and avoid any
potential shrinkage.
Would you like to
go with a medium?
Yeah, let's do the medium.
Great.
Based on your
shipping address,
you should receive it
within three to five
business days.
Does that work?
No.
I have a pretty big
event coming up.
Is there any way I can
get it in one or two days?
Unfortunately, that's
the fastest shipping
available for this item.
Would you like me
to transfer you
to someone who can
assist you further?
No, not right this
second, Sophie.
Thank you, though.
Appreciate it.
OK.
[APPLAUSE]
Totally, totally
different experience.
Very friendly.
I was able to immediately
start talking.
Sophie knew
exactly who I was
because she has my full
Customer 360 profile.
She knew my
orders because she
has all of our order
history stored inside
of Data Cloud.
She was even able
to take some action.
She was able to switch
and order me a new medium
jacket.
But right there
at the end,
you may have noticed
one thing that Sophie
wasn't able to do.
Sophie wasn't
able to figure out
a way to get me that
jacket any sooner.
And that's
because right now,
at this moment in
time, Sophie really
only knows how to talk
to the shipping carriers.
She can look that up,
but that's about as far
as she can go.
But that's not
as far as Saks
can go because
Saks has stores
all over the country.
And if we could enable
Sophie with some ability
to identify those stores
and maybe even look
into the inventory
of those stores,
maybe Sophie could have
gone one step further.
And that's what I want
to show you right now.
So as Clara
showed us earlier,
where we have our
all-new Agentforce studio
with Agent Builder.
And this is the very first
time on a Salesforce stage
we're going to
show you this.
I am so excited.
So here we are inside
of Agent Builder,
and you can see we have
our configuration here
for Sophie.
And configuration is
really, really important.
It's all natural language.
What's so cool about
building these agents is
if you can describe
it, Agentforce
can probably do it.
It's really,
really awesome.
So here we have
our avatar.
We have our agent name.
We have our description.
But what I really want to
show you is these topics.
Now, topics are really
the foundational building
block, along with
actions, in how
you build these new
autonomous agents.
And think about topics as
just kind of categories
of information.
So I've got an Order
Management topic here,
for example, and
that actually
happens to be the
topic that we were just
in in our last
call with Sophie.
And if you're wondering
how that works,
again, it's just
a description.
If we look at this
Order Management topic,
we can see the kind of
description and scope
of the topic.
We can see some
specific instructions.
And what happened
in that conversation
is Sophie was
just listening
to what I was saying
and identifying that.
I'm probably talking
about Order Management.
Simple as that.
That's how we make
that connection.
No writing complex IVR
trees or writing code
to make that happen.
It's just reasoning.
Now, within these
topics, we have actions.
And you can see
some of the actions
that Sophie already
knows how to do.
And if you notice, these
are actually just flows.
We'll spend some more
time on that in a moment.
But you can see
some of the actions
that Sophie actually took,
like finding my order
number, checking
the order status,
even modifying the orders.
Those are all
actions that we just
saw Sophie perform.
But I want to add
some new actions.
I want to give
Sophie the ability
to find stores
and see if we can
find some new inventory.
So if I click
Add Action, I
can see here I've got
a couple things that
might help me out.
I've got get
nearby stores.
I'm probably going
to need that.
Change delivery method.
I might need that.
But you'll notice
I don't have
anything for the
store's inventory.
I can't look into a
store inventory anywhere.
So let's fix that.
I'm going to close this.
I'm going to jump
over here to Add a New
Agentforce Action.
Now, as we heard earlier
from Clara, what's
so incredible
about Agentforce
is you're starting
from so far ahead
because you've already
got all of the workflows
and processes built
right into Salesforce.
You already have
all of your data,
so you can see
all of the flows.
These are just
all of the flows
that you've already built
attached to your org.
You can pick these and
add these to Agentforce.
But in our case, I
need to call MuleSoft,
so I'm going to
pick a MuleSoft API.
And I happen to have
a store inventory API
already available to me.
And what's amazing
about these agents
is they can actually query
and talk to these APIs,
just like we
would be able to.
So I'm going to
add this API.
I can edit the inputs
and outputs if I need to.
And I'm going to go
ahead and click Finish.
And we're going
to jump back over
to Agent Builder.
And if I add
these actions,
we should get
some new things.
So let's add get
nearby stores.
Let's do change
delivery method.
Let's schedule an
in-store pickup,
and let's store our--
let's add our store
inventory API.
So we'll add those.
And you can see they got
added to our actions here.
Now, there's
some magic here
that's going to happen.
I'm going to show
you the magic,
but there's some
magic, which
is we don't have to
write any more code.
That's it.
That's all we had to do.
We just had to
add the actions,
and Agentforce
and Sophie are
going to reason over
what I want as a consumer
and figure it out.
But you don't
have to trust me.
Let me show you how
it figures it out.
We're actually
going to show you
the Atlas reasoning
engine thinking
every step of the way.
So I'm going to
go back in here,
and I'm going to type in--
we saw voice a moment ago.
I'm going to type
in what I want here.
And bear with me because
I'm pretty confident,
but I am not
confident enough
to type on stage,
so I'm just
going to paste that in.
So hi, my name is
Patrick Stokes.
Customer ID,
yada yada yada.
And you can see,
as she's analyzing,
we can actually see the
Atlas reasoning engine
here right in the middle.
We can see the prompt
that I just gave it.
We can see the connection
to that Order Management
topic that we just saw.
And now we can start to
see the actions actually
taking place.
So Sophie is
actually going out
and querying our find
order number flow,
bringing that back.
She's then moving on
to the next step, which
is to check the
order status.
Now, this is where
she failed before
because in my
question, I'm
asking if I can
get it any sooner.
She failed at that
before, but now she
goes on to the next step
because she's figured out
that I might have another
way to get this here--
the jacket here just
a little bit sooner.
So you can see,
get nearby stores.
She's trying to see if
there's a store near me.
Now she's actually looking
into the store inventory
API.
And then she's figured
out that, hey, I
need to go back
to the customer.
I need to ask if the
customer would like
to do an in-store pickup.
She doesn't just
schedule it herself.
She's going to come
back and ask me as well.
So do I want a new
in-store pickup?
Yes, I do.
We're going to
enter, and we're
going to see the
conclusion of Atlas.
And there we go.
So now Sophie
is figuring out
these last few
actions, which
is to change our
delivery method
and schedule an
in-store pickup.
Now, what's amazing about
this is all I have to do
is deploy this agent,
and it works everywhere,
whether we're in
voice, like we just
were a moment ago,
or whether we're
in Apple Business
Messages or in the chat
on our website.
It just works.
It's all one agent.
And to prove
that to you, I
want to give
Sophie a call back.
And I hope this
works, but we're
going to give
Sophie a call back,
and we're going
to see if she now
has this new capability.
So let's give it a shot.
[PHONE RINGING]
Hi, I'm Sophie, your
Saks AI assistant.
How can I help you today?
Yeah.
Hey, Sophie.
It's me, Patrick, again.
I wonder if you
can just give me
an update on my
order delivery
from my most recent order.
Is this about the
Saks Fifth Avenue
COLLECTION Cashmere
Baseball Bomber Sweater?
Yep, that's the one.
Great.
We have two delivery
options available.
I can have it delivered
within three to five
business days, or it
can be picked up as soon
as today at Saks
San Francisco.
Which option works
best for you?
Oh, that's great.
I would love to come in
to Saks San Francisco
and pick it up.
Great.
I've placed the
order and notified
the in-store client
advisor that you
will pick up the item.
They will have
it ready for you
within the next
three hours.
Is there anything else
I can help you with?
No.
That's fantastic, Sophie.
Thank you so much.
You've been super helpful.
Thank you.
[APPLAUSE]
So you can see
how we think
that this is going to
transform everything, how
you can get these
agents to reason
and do anything that you
might need them to do.
Remember, if you
can describe it,
you can get
Agentforce to do it.
But as Clara said,
we need to be
able to do this
with trust as well.
And so we're excited to
show you our new Omni
Supervisor, where you can
not only come in and look
at what all of
your human agents
are doing with
your customers,
but even look at what
your Agentforce agents are
doing here as well.
And we can see that
Saks, they maybe
have actually rolled out
quite a few agents, Sophie
and maybe a few others,
because depending
on where you are
in the world,
you might want
to talk to people
in all sorts of
different ways.
So we can see some of
my last few interactions
here.
We can see an interaction
that closed a little while
ago between our
customer, Claire, who had
some tailoring help done.
Let's give that one
a listen real quick.
I'm Kevin, your
Saks AI assistant.
How can I assist
you today?
Hi.
So I just--
That's awesome, but what's
really cool about Omni
Supervisor--
I'll just hang
up on that--
is that we can even
listen to calls as they're
happening in real time.
So we've got
two calls here
that are actually
happening, one here
with Brian Green.
Looks like he's
having some problems
with his password.
Let's give that
one a listen.
--problem at all.
I can send you a link
to reset your password.
Would you like me
to stay on the line
while you create
a new password?
No, I don't want
to stay on the line
while he recreates
his password.
I think one customer
service call was enough.
Super exciting.
Thank you all so
much for your time.
Marc, back to you.
[APPLAUSE]
OK, are you getting jacked
for how this is working?
Do you get-- do you
see what's happening?
You can see why
we're so excited.
It's kind of amazing.
And I was just
sitting there,
thinking about I
actually bought
these shoes that I'm
wearing at Saks--
they're Christian Dior
shoes, very fancy--
for the keynote.
And I'm like,
yeah, I could
make all these changes.
I think I buy just
about everything online.
I bought this
suit from Berluti,
which is an LVMH company.
I bought the shoes,
then I put it
all on this morning
for the first time.
And I'm like, it's amazing
what is possible now.
And I think it's not
just what is possible,
it's what you are
going to make possible
because, as you're going
to see, these agents,
you can make your own.
You can make them highly
customized for you.
You can make them do all
these amazing things.
But because
only Salesforce
does these three
things, automate
every single
customer touch point,
have the deeply
integrated Data Cloud,
have the complete
Agent Builder,
and deliver it as all
one integrated platform,
means that you don't
need to DIY your AI.
This is the big,
fundamental thought.
Our goal is
simple, for you
to augment your employees,
to create better
experiences, to deliver
higher revenue and better
business results
for your companies.
And I think you're going
to figure all out how
to do that at this show.
That's our
fundamental goal.
We are so excited
about this.
But every time
we get excited,
we're getting
even more excited.
And the most
exciting thing for us
is we've rolled
this out to a number
of our customers, and
we've rolled version 2
out to a number of
our customers as well.
And version 2, which
is called Atlas--
and you've heard some
of this already--
we're starting to see
some amazing results.
And you saw some of that
with the 2x accuracy
and benchmarked against
the leading models,
we're 2x their accuracy
and their hallucination
rates because we have
this unfair advantage
at Salesforce called
the Salesforce platform.
And because we hold so
much data and metadata,
all the customer apps,
all the infrastructure,
everything, the
workflow, and because you
have done so much
work in this platform,
the AI is simply better.
This is what AI
was meant to be.
And you're going to
see how Agentforce
is outperforming OpenAI
on Azure in cost,
time to value,
and accuracy.
It is incredible.
And we're going to
encourage you to benchmark
us, to do the
bake-offs so that you
can see the cost
differences and the time
differences.
It reminds me a lot
of when we started
Salesforce, and we started
putting together the Cloud
and putting these
things together and kind
of making it all
happen, but there
were other approaches.
There was a lot of
DIY approaches, right?
So now Parker, come
over here, would you?
Yeah.
He's trying to hide
in the second row.
Parker Harris,
my co-founder.
And Parker, you remember
this very well, don't you?
I do.
Remember, Parker,
this slide.
When did we start
delivering this slide?
Like, 25 years ago?
This idea, you
want your agents,
but here's your
customer success.
But oh, no.
Oh, no.
Look at all the cost.
Unbelieve-- that's
hiding below here.
Customers were DIYing it,
and all of a sudden, yeah,
you want AI?
No problem.
You have to have
a custom AI model.
This is very good.
Now you have to retrain
it and train it.
You have to-- you've got
all this fragmented data.
Don't worry,
you'll hook it up.
Oh, you've got all
these disconnected apps
and agents.
Don't worry, we're going
to put them all together
for you.
You don't have a security
or sharing model.
Don't worry about it.
It'll all happen.
Oh, look at that.
You need to hire
an AI engineer.
You know that.
And finally, it's going
to require the scale.
I mean, how long
have we been
delivering this slide?
For.
2 and 1/2 decades.
Are you shocked
we're still
delivering this slide?
I'm not shocked.
It's just been a journey.
25 years, what our job was
is just to make it easy.
And that's what
we're doing with AI.
We used to have
a slide, it
was called You
and the Fun Stuff.
Remember that?
The fun stuff is getting
this AI working and seeing
the customer success.
And so we want to
give you all of this,
but it's built on 25
years of technology.
It's big shout out to MK
and C. Fisher and Srini
and the entire
engineering team that
have done an
incredible job creating
this technology.
[APPLAUSE]
Well, Parker,
it's amazing, so
congratulations to you,
to the product teams,
the engineering teams,
to the whole company,
and also all
the trailblazers
because the slide
still holds together.
And here we are on the
next wave of technology,
and you don't
want to DIY it.
You don't want to DIY it.
And it is the next decade
or more of Salesforce.
So exciting.
Congratulations.
Thank you.
So look at this.
The Salesforce
platform has evolved.
Of course, you've invested
so much in these apps.
You've invested so
much in the platform.
We've introduced you
to the trust layer
and the Data Cloud and
our new RAG techniques
and now, all of
these agents.
So the platform
has changed.
It's transformed.
It's evolved.
It's gone forward.
And yet it's still the
simple, easy-to-use
platform that's inside all
of your companies already.
It's already there.
You already have your
login and username
and password, and
boom, all of this stuff
is there for
you, ready to go.
Think about it.
That is our job
at Salesforce,
is to take you,
as trailblazers,
to the next place.
And right now, it
means taking you
from Trailblazers to be
Agentblazers, just like we
have consistently
for 25 years
so when you
leave this show,
you can go back
to your employers
or wherever you're
going and say, hey,
we're going to go--
I'm ready.
We're going to
deliver these agents.
And it's possible through
this incredible platform.
This is really what
AI was meant to be.
It's about the
Customer 360.
It's about the Data Cloud.
It's about Agentforce.
It's about the
Salesforce platform,
and it's about
our core mantra
at Salesforce, which is
don't want to DIY it.
This is why we started
this company because we
know that there is
companies and technology
companies and on
and on and on who
are going to try to
come along and say,
we've got the
new great thing.
And you're going to
have to wire it all up
and hire a new
team that's going
to go make all this
happen for you,
and it's too much.
But we can do
it in a new way,
and we can do
it right here.
Look, we've
seen this, even
when we were talking last
year about Data Cloud,
that customers
had islands of all
of this disconnected
data all over the place.
And then what did we do?
We said, it's
in the platform.
And we have our Data
Cloud in the platform,
and through zero
copy, we can plug
into whatever you have.
We can unify your
data and metadata,
and we were so
excited about that.
It's become our
best-selling new product
ever.
And companies
have come along
and made huge investments
in this Data Cloud.
And it's been
remarkable for us
to what we have
been able to deliver
for customers so rapidly.
But here's the
other thought.
What we didn't realize
was by encouraging
you to move in--
while we encouraged you
to move to the Data Cloud,
and you are now doing 767
trillion records per month
in the Data Cloud,
and the huge work
you have done with
the Data Cloud, which
is awesome, and we're
so grateful for that.
What we didn't realize
is we were preparing you
very well for AI.
We were preparing you
for this next step,
that this was now
setting you up
so that when we rolled
out App and Agent Builder,
because all of that
work was there,
it was incredible what
we could now do for you.
So to help see the
next level of that,
please welcome Sajna.
Sajna, where are you?
I'm over here, Marc.
All right.
Thank you so much, Marc.
Now, Data Cloud is an
incredible innovation
in our platform.
But in order to really
appreciate its power,
we got to tell
you how it works.
And it all starts with
connecting to your data.
Now, this is any
data that you
can dream up, whether
it's structured
or unstructured.
It could be in a different
Salesforce Cloud.
It could be in a
third party system,
like SAP or
Concur or Workday,
or it could even be in
external data lakes.
And we do this in a really
special and distinct way
using our zero copy
integration because we
don't want all of you to
incur the cost of moving
your data every time you
want to use it inside
of Salesforce.
We don't want
you to do that.
So instead, we
virtualize that data
like any other object
inside of Salesforce.
So you can build your
workflows on top of it.
You can build
your applications,
and, of course,
power your agents.
Now, once you've
connected to your data,
there's still a
problem because
every single
system that you
have to describe
a customer does it
in a little bit of
a different way.
So what Data Cloud does
is it harmonizes this data
so all of your systems now
speak the same language
about your
customer, and you
have one unified
customer profile
that you can activate
across the Customer 360,
with your insights, your
applications, and all
of your workflows.
Now, I know what
you're thinking.
We're here to
talk about AI.
Even if you connect
to all of your data,
don't you need to
train your own model?
Well, the answer
to that is no.
And we're going to debunk
that myth for you here
today in some detail.
Now, for most customers,
many of you in this room,
you think if I just
give all of my data
to a large language
model, that's
how they're going to
know my business, right?
Give all of that
data into the model.
However, this
is expensive.
It's costly.
Like Marc showed
you, there
are all of these
needless steps that you
have to go through.
And most importantly,
as your data changes
and scales, this system
doesn't scale with it.
So instead, we can teach
a large language model
about our business through
the power of a prompt.
And a prompt is nothing
but a set of instructions
that we send to
an LLM to teach it
about our business.
Now, another thing that
we don't want to do
is load up a prompt
with all of our data
and have 100, 200
page prompt just
to teach an LLM
about our business.
We don't want to
do that either.
So we're going to flip the
script here a little bit,
and we're going to use a
technique called retrieval
augmented
generation for AI
to understand
our business.
Now, this is a
cutting-edge technique
that lives deep
inside of Data
Cloud in our
Salesforce platform,
and it enables us to
search through all
of that data you have.
Think your images, your
PDFs, your policies,
all of that.
And it allows us to
augment our prompts easily
and teach AI about
our business.
Now, Clara mentioned
earlier our Atlas
reasoning engine.
Data Cloud and retrieval
augmented generation
are at the heartbeat of
this reasoning engine,
and it helps it iterate
and plan and help
your agent take action.
Now, I want to make all of
this really real for you
in a demo about
Saks, and I'm
going to ask Kristen and
Claire from the demo team
to help me out there from
behind the demo desk.
[APPLAUSE]
All right.
Now, this story is
about my actual journey
with Saks to get
ready for Dreamforce.
This outfit is from
Saks, and Sophie is here
to help me with all
of my questions.
Now, a really
common question
that customers have at
Saks is about a price
adjustment because
how annoying
is it when you buy
an expensive item,
and then it immediately
goes on sale?
You want to make sure
you get your money back
so you can have that
happier customer
experience.
So I want to go
ahead and give Sophie
this new ability to
answer this question.
And this is actually
really complicated.
I want to take
a pause here
because for a
service rep at Saks,
answering the simple
question would mean
that they would have
to know everything
about their
policy data, would
be able to search for
that specific citation
to fix that
customer question,
and then deliver it
back to the customer
in a matter of seconds.
It's not possible
for a human,
so it's perfect
for an agent.
So why don't we go
ahead and give Sophie
some new abilities, and
our journey is going
to start in Data Cloud.
Now, it looks
like we've already
connected to our CRM
data right here, which
is a really great start.
But I really want to
connect to my Order
Management System
data that I lives
inside of Snowflake.
So I'm going to go ahead
and create a new data
stream.
And Data Cloud
makes this super
easy with out
of the box data
connectors for
any data system
that you can dream up.
So I'm going to go ahead
and click that Snowflake
icon and create my
new data stream.
Now, what I
get immediately
on the next screen
is I'm going
to see a data graph of
all of the associations
of my customer across
every single touchpoint
of that data I
just connected to,
which is super powerful.
So now why don't we
go into Agent Studio
and give Sophie
this new ability.
Now, as Patrick
mentioned, this
is really where we give
our agents the ability
to answer different
questions through topics
and actions.
Now, we already have
a topic drafted here
for pricing
questions, and I've
gotten a little
bit of a head
start on this action
here, which is
a prompt under the hood.
But I want to
edit this prompt
and make it a little
bit more intelligent.
Now, our customers
have been building
prompts on the platform
for over a year now,
and our trailblazers are
going crazy for this.
And I want to
tell you why.
The first reason is
because we enable
all of you to pick
whichever model you want
to use under the
hood of your prompts
because we know it
seems like there's
a new model being created
every single week,
every day, and we
want to give you
the freedom of choice
on the platform.
Now, the second reason
that our customers
love building prompts
on the platform
is because this is
prompt engineering
the Salesforce way, the
low code way that scales
with your business.
So why don't we go ahead
and draft our first prompt
here.
And I got a little bit of
a head start, like I said.
I'm going to go ahead
and paste that in.
Now, I want to
show you how
we can use that
data we just
connected to make this
prompt more impactful.
And I'm going to
go ahead and bring
in that information from
my Snowflake instance, all
of that Order
Management data.
I'm going to pull
in the right fields,
and it's just a
few clicks away.
And why don't we go ahead
and test this prompt
and how it resolves on
my own contact record.
OK, this is pretty
good at first glance.
We have the amount that
I could be refunded.
But at the end of
the day, this prompt
isn't actually resolving
the customer question.
I think we can do
better than this,
and we can do better
with retrieval augmented
generation.
So let me show you
how easy this is.
So what we're
going to do is
we're going to bring in
what we call a search
retriever, and
it does what
it sounds like it does.
It retrieves
the right data
from all of that data
you just connected to
and grounds your
prompt with it.
So I've gone ahead
and put that in.
And I want to give
some search parameters
right here to the prompt.
And let's see how we did.
Let's preview this.
All right, this
is so much better.
And if we go into
that resolution text
that we're scrolling
through right now,
you can actually
see the exact part
of the information I
just connected to that
is powering our prompt.
Now, why don't we see this
in that experience for me
with Sophie,
the Saks agent.
So when I ask
about my order,
Sophie is now empowered
with all that data,
that Order
Management data.
And I've been making a
lot of orders from Saks
lately, so she's
got to confirm
if this is the right one.
She's right on
the money here.
And now that we've
confirmed that that's
the right order, Sophie
can resolve that question
in a matter of seconds.
Now, this would have
taken a service rep
many different hours
to go through all
of their policies to
resolve this case.
And Saks was able to build
this incredible customer
experience end-to-end on
the Salesforce platform
and Agentforce, without
training a single model.
Back to you, Marc.
[APPLAUSE]
Amazing, Sajna.
And I think we're making
the case, don't you think?
I think we're
making the case.
And it's cool, isn't it?
It's really amazing.
And I'll just say--
you can give it a hand.
[APPLAUSE]
As we kind of got
ready to get going,
and especially about
90 days ago, that's
when we said,
look, there's
only one way
anyone is actually
going to believe this.
You're going to
have to let them
put their hands
in the soil
and get going
on the platform.
And that's when
we said, we're
going to have to bring
thousands of our employees
here and work with
thousands of our customers
and make this work.
And it will be the
largest, most exciting
deployment of agents
ever in the history
of our industry.
And then everyone who
does not understand agents
or does not understand
AI or doesn't understand
all the bits and the
bytes and the nuances
and the nudging and all
these things you have
to do to get your
agent live and going,
you're going to
figure it out
while you're here,
with these people,
with these experts,
and with each other,
because that's what
trailblazers do.
And that is
what is exciting
about this Dreamforce.
This is the
Dreamforce that we
think is not only the
most exciting, but most
important Dreamforce ever.
And we think that this is
what AI was meant to be.
Now, we already
know, Salesforce
is this number one CRM.
And this is one
of the reasons why
the AI is so accurate.
It's because we have this
incredible Sales Cloud
that you've
invested so much in.
And now this Sales
Cloud has a built in SDR
agent and a built
in sales coach agent
to make your sales
forces more successful.
You're going to see
not only the new sales
agent and sales
capabilities,
but the new Service
Cloud and the new service
agents, including
the scheduling
agent and the employee
service agent.
And you're going to
see the new Marketing
Cloud, which has
been rewritten
from the exact target
stack into core so
that it's all running
right inside flow
and not just inside
Journey Builder.
Because we want one flow
for all those agents
running.
Did you see how
important flow was now?
Flow is more
important than ever,
so we need everything
running in flow.
And while we love
Journey Builder,
and Journey
Builder's awesome,
we need to move into a new
environment inside flow
itself to get the power
that you're seeing here.
And that idea that
Marketing Cloud
has been rebuilt,
you're going
to get your hands on that
as well here at this show.
And that level of
personalization
and all of these
things is coming very,
very soon and instantly
to our customers.
And Commerce
Cloud, as well.
So Commerce
Cloud, we're going
to have the merchant
GA available now.
You're also going to have
this incredible buyer
agent.
And also, we wrote
Commerce Cloud
into the core as
well, so that you
can have commerce on core
and marketing on core.
And also you're
going to see
this incredible new
Revenue and Order Cloud,
which is actually
where I bought
this suit because
the company
where I bought
this suit, Berluti,
they use our Order
Management system
to make it happen.
And that is an incredibly
powerful thing,
and that is going to
include our new Deal Desk
functionality as well.
And you're going to see
this here at the show
as well.
Every Cloud and
every agent on one
trusted platform.
Every Cloud and
every agent on one
trusted platform.
One workflow.
One metadata environment.
One data environment.
One sharing model
environment.
One security model.
And one more thing.
We also--
remember Tableau?
We bought that a few
years ago, the number one
business intelligence
platform in the world.
Well, we decided we're
going to rewrite that,
too, all on Data
Cloud, all in core,
so you can visualize
the whole thing as it's
happening because
you need these data
vizes and this ability to
have this visualization
capability.
Look at that.
You can visualize across
the whole company,
across all your systems,
because it's all
built in Tableau as well.
This is really capable,
and this Tableau agent
is going to be GA now
and Tableau Pulse now.
You're going to have
your hands on that.
It's all deeply integrated
into the Data Cloud.
And Slack as well.
Slack deeply integrated
in the Data Cloud.
Slack deeply
integrated into flow.
Slack deeply integrated
into our core platform
so that you have one
consistent interface, one
platform for the
whole company,
for the whole
Customer 360.
And you're going to
want to, of course,
do this by every industry.
So I talked to you about
the health care idea.
Of course, that's
going to be
a core part of
our Health Cloud
or our Consumer Goods
Cloud or our Net Zero
Cloud, helping all
of our customers
go net zero, or our Public
Sector Cloud or our Health
Care and Life
Sciences Cloud.
We have this amazing
new Life Sciences Cloud
for life sciences
companies,
helping them to build
the next generation
of pharmaceuticals.
How important do you think
it is for agents to reach
out to people
who are going
through some kind
of life sciences
pharmaceutical trial
to check in on them,
how are you doing
during the trial?
It's super important.
Or in the Health Cloud
for the health care
facilities,
like the doctors
that I talked
about earlier.
How important do you think
it is for a health care
organization, like the
ones that are testing
Atlas now, to do this--
to call you back.
How did the MRI go?
Did you drink
all the water
to flush out
your contrast?
Did you take
the medication
like we told you to do?
That is an incredible
role for these agents.
So whether it is health
care or public sector
or net zero or
manufacturing or energy
or utilities or financial
services or communications
or consumer product goods
or media or automotive
or nonprofit, each
and every time--
and I'll tell you,
I have a new car.
It's amazing.
You may know, I'm
a huge car person.
I love cars.
I'm always getting
another car.
And GM sent me
their new Hummer EV.
It's awesome.
And we had helped them
build this amazing OnStar
platform.
They are awesome.
GM delivers the best
customer success.
It's beyond my experience.
And every time
I hit OnStar,
I get this incredible
experience.
I love my car incredibly.
I want that next
capable functionality.
I'm going to just build it
into the Auto Cloud also.
So that idea that
every customer
can have this next
generation experience
and to connect
with their customer
in a whole new
way and use agents
in these incredible ways
that today, this last mile
to get to our customers
is just too hard.
And we can do it in this
Agentforce platform.
So with that, let
me introduce you
to Leah McGowen-Hare,
who's going to give you
an incredible demo.
Leah.
Let's go.
Let's go.
Final inning.
I am so excited to share
with you all how Saks uses
Agentforce to scale their
employees across all
their Salesforce apps.
Now, [? Rucha, ?] myself,
and [? Maximo ?] have five
use cases we're going
to walk you through.
So we're going to look
at the merchandising
team, marketing team, as
well as in-store advisors.
But first, let's
start with Slack.
So here we are in the
merchandising channel,
and the buyer is
sharing all the items
they want to reorder
for the upcoming season.
But what I want to
bring your attention to
is the upper
right-hand corner.
There's 25 people in
there collaborating.
Those are 25 humans.
Right next to it,
you see three.
There's three
agents in there
as well, collaborating.
Well, let's see what
that actually looks like.
In here, we can see that
Robbie is in there typing.
Well, Robbie is
actually not human.
It's the Saks
merchandising agent
powered by Agentforce.
And here, it's profile.
And here, are all the
things that it can do.
It has skills, it has
jobs, and the knowledge
that powers Robbie.
Well, this is great.
And you can see in there,
they're collaborating.
You got folks in there
asking questions.
Robbie's answering
the questions, just
like any other teammate.
Now, here's the thing.
Robbie doesn't just
answer questions.
Robbie also takes action.
But before we
actually look
at the action
Robbie takes,
I really want you
to take this in.
What you are seeing
is humans and agents
collaborating in
a Slack channel.
Have you seen that before?
I can answer that for you.
No, because no other
platforms do this.
Our competitors,
they're not like us.
They don't do this.
So this is pretty awesome.
So now let's actually look
at the reorder process
that was kicked off.
So in here,
the buyer, when
they want to look at the
full reorder process,
they simply don't
have to leave Slack.
They can stay
right there, thanks
to Salesforce Channels.
Now, Channels have always
been the core of Slack.
But now, with
Salesforce Channels,
you can bring the
goodness of your CRM data
right there in Slack.
All the insights, right
into the flow of work,
right into your flow
of conversations.
That is incredible.
Now let's switch
gears and look
at how Saks'
marketing team uses
Agentforce with Tableau.
So here we have this
beautiful dashboard.
But what I want to
bring your attention to
is the upper
left-hand corner viz.
Here it shows how many
Agentforce customer
conversations have had.
So that's a great number,
and it's going up.
What would be really
insightful to know,
what are they
talking about?
What are our
customers saying?
I can't get that
from that number.
But here's the challenge.
That is unstructured
data, just
like your Slack messages,
just like your emails,
just like notes.
So it would take a human
and a data marketer
and all these folks
hours and days and weeks
to gleam through all
that data to find out
the key words and what
are they talking about.
But not for Agentforce.
With Agentforce,
the marketer
can simply ask, why
are these conversations
on the rise, and what
are they actually talking
about.
And Agentforce responds
in natural language
with an insight
around the key words,
and Agentforce
shares a viz.
Agentforce
speaks viz, too.
It gives a lovely viz
of all the key words,
and it prompts
the marketer
if they want to
further break
that information down.
So we can break down
this information
and say, what
are they talking
about for seasonal
collections?
And then it comes back,
and Agentforce says,
you know what?
Folks really want to
come into the store
and get their hands on
that seasonal collection.
And Agentforce
recommends adding
an additional segment
to an already existing
campaign that's
performing really well.
We're going to create
a new segment for that.
Now, before we leave
this, [? Rucha ?]
[? and Maximo, ?] I want
to stay here for a minute.
I want to give
the folks a minute
to take in what
we just saw.
What we just saw, you were
able to get an insight
from that number and go
all the way to action.
Insight to action
on one platform.
That is the power
of Tableau on core.
It now has access to
all the metadata, all
your custom and
standard actions
that you have in your
org, whether it's
existing flows or Apex
or any of your prompts.
All of that, you can
build and take action.
I am telling
you what I know.
There are no
other applications
that can do this,
so take it in.
I'll give you a
minute to take it in.
That's a lot.
That's powerful.
Let's go ahead and
create a new segment.
That's a flow that gets
kicked off right there.
So here we are, and it
kicked off the flow--
Agentforce kicked off the
flow and came back with
37,000 folks for
our in-store event.
Probably don't have
the capacity to handle
that, so the marketer
goes back to Agentforce
and says, do you think
you can bring this down
a little bit to be
compliant with our store
occupancy level?
And Agentforce,
because it has access
to all the data, knows
our top customers,
knows the compliance,
comes back
with a more
manageable number.
Perfect.
Now we have our
campaign, and we've
got our segment created.
So now let's check it
out and see what it looks
like from the website.
So we're back
on the website,
and Heather's over there.
And it's customized
just for Heather
as she shops on
the mobile app.
And Heather's been
eyeing this bag on there.
Well, Sophie is on there.
Remember Sophie,
Agentforce?
They're ready to answer
any question Heather may
have because Sophie has
the full context of who
Heather is.
And Sophie invites Heather
to the in-store event
because she says,
you know what?
You can get that bag
in store, right, Srini?
Srini is like, yeah,
let's get the bag.
So we can get to go
into the in-store event
and get the bag.
And Heather starts
to get really excited
about getting the
bag, and starts
to ask about
styling questions.
Now, you all
heard Patrick talk
about building agents,
and we put up guard rails.
Guard rails are what
they can and cannot do.
Well, Sophie
cannot do styling.
That's not her job.
So when Sophie gets
questions about styling,
she's instructed to
pass over to a human.
And in this case,
that's the Saks advisor,
and that's exactly what
Sophie's going to do.
But before they do, I
know what you're thinking.
Because I can
read your mind,
I know what
you're thinking.
Oh, my goodness.
Heather's going to have to
repeat all the information
that she shared
with the agent.
Or you all have
been there.
You've called.
You put in your
account number.
You finally get to a
human, and they're like,
can I have your
account number?
You're like, did I not
just punch that in?
Well, guess what.
Not with Salesforce.
Because when the advisor
comes into this screen
here, they have
all the information
about Heather--
all her past purchases,
all the full conversations
that she's had
with the agent.
And the Agentforce
even summarizes
the conversation
for the advisor.
So now what you're
seeing is the advisor
and Agentforce
working together
to answer all of Heather's
styling questions.
Well, Heather
is super jacked,
ready to come
into the store
for that in-store event.
Now, let's stop, fast
forward into the future,
and it's the day of
the in-store event.
Now, here's the thing.
We want to make sure that
the digital experience
and the physical
experience
are seamless for Heather.
And thanks to the
power of Retail Cloud,
we can do just that.
Now, Agentforce is
providing details and all
this information on
Heather's unified profile
on the clienteling app
that the in-store advisor
is using to get
prepped on Heather
so they can be prepared
for her arrival.
So now when Heather
comes into the store
for the event, she can
receive that white glove
treatment, a treatment
that's very demure, very
mindful, right?
So she's in here, shopping
and really enjoying this.
Now also, she's
going to get the bag.
She may get some
additional items.
And Agentforce
can also process
in-store transactions, as
well as print receipts.
Now, what you're
seeing is Agentforce
is the constant
thread from beginning
to end so we can get
Heather to come back
again.
And that, my
friends, is how
Saks drives
customer success
with Agentforce across
their Customer 360.
Back to you, Marc.
I'm going to do
some shopping.
[APPLAUSE]
All right.
Was that amazing or what?
Yeah.
It was pretty awesome.
We were just talking.
We really think this is an
unbelievable opportunity.
It's probably
the best keynote
team we've ever
had, the best
keynote we've ever done.
Did everybody check
out our new cash
register we have up here?
Was that awesome?
Did you see that?
That's part of our
PredictSpring acquisition.
It's incredible.
It's going away
on that desk,
but you're going to check
that out at the show.
You're able to
check out the store.
All of that is integrated
into the whole platform.
It's the first time we
have a physical device
that we're offering as
part of our product line
with PredictSpring.
Incredible.
And you can really see how
the platform has changed.
I think that this
new kind of--
I call it the
rainbow slide--
really makes it clear what
it is that we're doing.
And you can see this
vision is really
starting to unfold.
We're ready for you to
get going for Agentforce,
but we know all
of you don't
have all of our clouds
installed, right?
But talk to us
here at the show,
and we're going to
turn something new
on for you called
Salesforce Foundations.
And Salesforce Foundations
is a free upgrade
available for Enterprise
Edition and higher,
and it will
automatically flip
on Sales Cloud, Marketing
Cloud, Service Cloud,
Commerce Cloud,
Agentforce,
and Data Cloud for
you automatically.
So that is going to be
a big shift forward.
Incredible vision
for the future
of all of our
businesses, and you
are going to be able to
build your first agent,
pilot your Agentforce now.
You're going to become
Agentforce Agentblazers
here at the show.
Really, really excited
for everyone here.
One last thing.
We also going to
go on the road
all over the
world for you.
So Sadhguru,
sitting right here.
Sadhguru, thank you for
coming to Dreamforce
for the first time.
Great to be with you.
Thank you so much for
being here with me.
So grateful for you.
The Agentforce world tour.
All right, you
have colleagues
you wish were here
with you, right?
Folks that you wish
had come to Dreamforce.
We're going on the road
all over the world.
Look at all these
cities that we're
going to be traveling to.
I'm going to
every single one.
No, I'm not.
You are.
But it's going
to be awesome.
And we hope to do--
here at these shows, what
is happening here exactly,
including the launch pad--
so getting customers
live and running
and understanding what
it is that's happening
and hooking them up
and making it all
come together live for
them, this is so powerful.
And finally, one last,
very important slide.
[SPEAKING JAPANESE]
Thank you so much
for everything
that you do for us.
We are so grateful.
And here's all
our new friends.
We can't wait for
this Dreamforce.
We can't wait for
Imagine Dragons and Pink
tomorrow night.
Can't wait to get
your feedback.
Look forward to
talking to you
all during this
conference.
Thanks so much for
coming, everybody.
[APPLAUSE]
[UPBEAT MUSIC]
Resume AutoScroll
Questions about Salesforce+? We have answers.
What is Salesforce+?
Salesforce+ is the free streaming service for business. It’s a place to watch live events and original series that help you grow your career and company, on your own time. Salesforce+ is produced by Salesforce, so you’ll find our company’s big events like Dreamforce here — as well as new original shows and virtual learning made for your role and industry. Everything is free and unlimited.
What can I watch on Salesforce+?
You can watch all kinds of helpful, entertaining, and inspiring videos on Salesforce+. One thing our members love is our events. Whether you catch them live or on demand, Salesforce+ gives you a free front-row seat to our biggest global events, like Dreamforce, TrailblazerDX, and Connections. Our members are also big fans of our original series. These entertaining business shows star people in roles and industries just like yours, giving you fresh ideas for how to grow your company and do better work. The best part is, it’s all free.
Do I have to pay for Salesforce+?
Salesforce+ is free. Watch any Salesforce+ events or series at no cost. To enjoy unlimited free access to our entire library of videos, become a member by signing up for Salesforce+ with a Trailblazer account. You don’t need a Trailblazer account to watch original series. To join us for virtual events like Dreamforce or Connections, you need to create your own Trailblazer account (it’s free!).
What is a Trailblazer account?
Your Trailblazer account gives you access to a unified profile across the Salesforce ecosystem and allows you to manage your settings and access across multiple Salesforce sites.
How do I sign up to register for live and on-demand events, like Dreamforce?
Sign up or log in to your Trailblazer account and complete a few additional details to watch Salesforce+ events live and on demand. We recommend preregistering for all events on Salesforce+ to get your own personalized journey, reminders, recommendations, and more.
Do I need to be a Salesforce customer to watch Salesforce+?
You don’t need to be a Salesforce customer to watch Salesforce+. Our virtual learning is open to everyone.
