Play
Show Navigation
Show Transcript
00:00
Play
Seek 10 seconds backwards
Seek 10 seconds forward
00:00 / 34:02
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
Agentforce has to be the biggest breakthrough
that we have ever had on technology.
It's about humans with agents
driving customer success
together on the Salesforce platform.
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.
Look, we've seen this,
even when we were talking last year
about Data Cloud that customers were like,
had I was have 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.
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,
which are insights, your applications
and all of your workflows.
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, easy
to customize with this built in AI.
And you know that 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.
Welcome.
Are you ready for the third wave of AI?
AI-powered
agents are here and Salesforce
customers are saying hello to Agentforce.
Hi, I'm Nicole Smayling
and during the next few minutes
we'll explore Salesforce's
newest innovations, including Agentforce,
and we'll hear from customers
about how they're planning
to deploy generative AI and Agentforce.
And we'll see a demo
that shows how it all works.
So if you're watching this live
and you have any questions, please
feel free to drop them in the chat.
Our team is ready to answer.
Now let's get to it.
Starting with the biggest news,
which is Agentforce.
It's part of the third wave of AI,
and we've been through predictive
AI and generative AI.
And now in this third wave of AI,
we have autonomous agents.
And for anyone not familiar,
an agent, short for agency,
refers to an AI system that can reason
and take action on its own.
And it's changing the way that customers
are having their experiences.
Agentforce is helping humans with agents
drive customer success together
on the Salesforce platform,
and it includes three things: prebuilt
agents inside every Salesforce
app with every industry
and for our partner ecosystem,
a new reasoning engine called Atlas
and a new set of low code tools
called Agent Builder, and that is helping
companies build, manage
and supervise their own Agentforce.
And Agentforce is the easiest, low
risk way to build agents
for the enterprise, and that's
because it's a few different things.
First of all, it's role based.
It maps your customer
360 roles like sales, service, and more.
It also unifies and activates your data.
It can take autonomous actions
like building workflows to get jobs done.
It's available on all
your favorite digital channels
for employees and customers
like voice, email, and in your apps.
And it manages trust and security for you
on the Salesforce platform,
which includes AI
guardrails
like toxicity detection, and audit trails,
and more using the Einstein Trust Layer.
So now every Trailblazer is an Agentblazer.
Let's take a look
at what this means for our customers.
We have this amazing anecdote.
One of our sellers is using
the Agentforce
and has asked it
to summarize an account.
While she was on the phone with a customer
and she's a newer customer
and she said it would take her 20 minutes
to do that.
Normally, it took her 30 seconds, was able
to answer it while she was on the phone
and she said, and I quote,
I think I thanked Einstein allowed.
So it was really exciting
to actually see a user use it in real life
and it actually work. I love.
Can we make that a hashtag?
Yes, I would love to make that a hashtag.
I think I thanked Einstein out loud.
What does a unified platform of CRM,
AI and data mean for Carnegie Learning's
sales team?
It means they can work out of one place.
I mean, it is there's
so many different products out there.
There's so many different ways
that we've we've used or we've had sales
reps on in the past that we now have tried
to only have them in Salesforce.
They have enough to do
while they're driving from place to place
selling that they don't need to have
a million platforms and know where to go.
So having everything in one place
and then being able to use
all of the GenAI pieces
because we have it all in one place,
it's really going to change their lives
and make them so that that 30% hopefully
gets boosted to 40, 50, 60% of their time
is selling. That would be amazing.
Can you even walk us through
like a specific use case or example
that's been especially impactful?
I would say the sales emails.
I'm really excited by how typically emails
for our reps take about 10 minutes.
We did a survey
at the beginning of this year,
so 10 minutes takes them to write
a really personalized good email
that they are hoping
to get a response from.
And sometimes they do,
sometimes they don't.
As if any sales reps out there know.
So being able to write that email
in about 30 seconds
and then revise it for 30 seconds
and just have it sent saves so much time.
If you think about that
throughout the entire day,
throughout a week, throughout the year,
I mean, the amount of time
that they're going to save.
And then also it's going to be written
with personalized data from Salesforce.
So all of the activity history
that we already have,
I mean, it's all going to be right there.
Great.
Well, we actually have Kevin Quigley
here from Wiley.
I'd love to ask you a couple of questions.
Thanks for being here.
Thanks for being our customer.
All right. So Kevin,
can you just tell us about like you've
launched Service Agent
and tell us a little bit
about kind of the outcomes
that you've seen?
Yeah, sure.
So I'd say there's
two really amazing things that we've seen.
One is we were able to expand
the self-service topics
that we're covering
compared to our old chatbot
from the most important and common issues
that we were getting to virtually
every question that can be answered
by our knowledge base for that product.
So that's really cool.
And we're also now able
to give personalized, dynamic,
not canned responses to those inquiries
when they're coming in on the customer's
own terms. Awesome.
So bringing in knowledge,
very quick, personalized answers,
how, talk a little bit about
I mean, we were working together on this
and I think we kind of share
maybe a little bit of the story,
but what was it like
to actually set this up?
What was different? Who was involved?
I'm sure everybody's thinking,
how hard is this to deploy?
Yeah, sure.
So there's something really interesting
that's happening with agents,
which is that you're shifting
that conversational experience design
from being the sort of tedious back
and forth collaboration between
your support experts in your IT
resources, your CRM and your programmers.
And now there's
a bigger focus on the conversation
just by those support and product experts.
So you're taking the people who know
what a good customer
experience should look like
and they're able to tell the agent
how to perform that experience.
And so that's much more efficient.
You can imagine on the design side
than having to chart out that logic.
And like I said before,
it makes it easier
to handle more scenarios
because you're not having to define
every single branch of a conversation
you're just able to say,
this is how we want to support
this area of our product.
So you didn't need like an army of, you
know, PhDs in CS degree folks to have this.
No, no AI specialists,
we took our support experts,
we took our existing CRM team
and our product support teams
and we empower them.
They came together and they said
this is what the experience should be
and to a good result.
We've seen an over 40% increase in case
resolution compared to our whole chatbot
from the agent.
Love it. Awesome.
It's great to hear
all the excitement with Agentforce.
So you might be wondering,
why do you need AI?
Well, we'll link some more resources
for you in this broadcast description.
Now, great AI experiences also need great
data, and that's where Data Cloud comes in.
Data Cloud unifies your business data
so you can put it to work with data.
Cloud companies are connecting
and unifying their customer data
into unified profiles.
That includes all kinds of data.
So structured data like web forms or XML
files and unstructured data like an email
or video or a PDF. And Data Cloud was built
on Salesforce’s metadata framework.
So it can access
the underlying metadata as well.
And that means you can activate your data
with context
everywhere in Salesforce,
like to power your AI experiences.
And today the importance of data continues
to increase.
In fact, 93% of IT leaders say that
trustworthy data is needed more than ever,
and that's why
at Salesforce were heavily
invested in Data Cloud innovation.
So let's talk about what that includes.
We now have 200 new Data Cloud connectors
and APIs for MuleSoft available
so you can connect to any of your data.
We've also previously introduced zero
copy integration
and now to complement that,
we have a whole zero copy partner network.
So you can act on all of your data
without actually having to move that data
out of your data links.
We also announced Data Cloud One,
which is helping companies
connect their multiple Salesforce orgs
with only one Data Cloud implementation,
and that helps you create
a richer view of your customers.
And you don't want to miss Data Cloud
vector database
that's allowing companies to use
their unstructured data in a whole new way
so they can surface insights
from unstructured audio and video.
And this is opening up
a whole new channel of data
that can be shared with your agents,
making them contextually aware.
So, for example, a sales team could use
Agentforce
to analyze their recorded sales calls.
And Agentforce could pinpoint key moments
in the conversation
like common objections, competitors
or follow-ups.
So now your sellers can be more detail-oriented
and they have this great new tool
to help them
improve their pitch and win more deals.
We also know that with AI,
there are new considerations
for data security and governance.
So we've introduced
new features in Data Cloud, including
policy based governance
and AI based tagging,
both of which are natively built
on the Salesforce platform.
Now, companies everywhere
are seeing great success with Data Cloud.
In fact, it's
our fastest growing organic product ever.
Let's hear a
customer
story all about how Data Cloud works.
About four years ago,
we started our journey.
We kind of mentioned data
all over the place,
a petabyte of data. $2 trillion
a year of GMV
we move around the world every single day.
You take that with over 700 aircraft
over 200,000 vehicles, over 500,000
fantastic worldwide employees,
and you bring all of that together
and you can create
some pretty valuable things.
We're thinking about it
in three different ways.
One, we're leveraging this data
to fundamentally change
the way we run our network.
The second piece is we're digitizing
supply chains with our customers.
We you can't manage what you can't see
and what you can't measure.
And so we're helping digitize
our customers supply chains.
And then a third
that we're very excited about
and that we're really starting to gain
some momentum on
is we're actually moving up
the e-commerce value chain
and we're doing that
through, this past Sunday
we actually made generally available
our FDX platform and we private previewed
that starting in January
and let me bring it to life for you.
If you think about an e-commerce company,
none of us shop anymore
without the expectation of understanding
at purchase time,
exactly when it's going to be there,
right?
So in the pre cart,
we're now powering, who better than us,
the transportation company?
And who knows a lot about it,
to actually help customers
predict that in cars. We're helping
say order within the next one hour
and 23 minutes is guaranteed there
Thursday between 10 a.m. and noon.
And we're layering in our insights.
This is the importance
of bringing our network data
and our customer data and our service data
and our sales data and the ability
to bring it together, which is obviously
what the Data Cloud is allowing us to do.
We then move that to the post-purchase
where we help power the post-purchase
experience,
and that's where our sales teams
engagement,
our customer service engagement.
When you talk about data
all over the place, it's really hard
to create a meaningful experience
and certainly create products
that helps our customers.
As you look at the last year,
as we've really leaned into Data Cloud
and we were talking about it
just this morning, just to show you size
and scale of how we're using Data Cloud.
In the month of August, we had 235 billion
rows of data in Data Cloud.
So if anybody's curious
if it can scale,
we have pressure tested it for all of you.
But again,
and I just want to reiterate,
like a lot of data is not that useful
if you can't curate it
and you can't generate insights
that then you can take action on.
And that's the journey
that we've been on over the last year.
We take that data that lives in Azure
and without having to copy
and this was a big request
that we obviously had
is I don't want to move that size
and scale of data all over the place
in order to make it contextually relevant
to create that insight
and to drive that action.
And so we are literally leveraging Data Cloud connectors
and we're taking advantage of all that
operational data, all of that customer
data, all that sales data, of course,
that lived in different ecosystems.
And you bring in,
of course our own proprietary enterprise
data platform because that much data,
we want to manage it, we want to own it.
But you've got the
power of Salesforce
and the power of the Salesforce cloud.
And so we don't have to take it
and move it all around.
We connect those together and the value
that we've had just in one year
is pretty phenomenal as we think
about recognizing potential attrition.
If you think about it,
a weather event potentially causes
a package to have a delay on it.
We need to know that, our sales team
needs to know that, our customer service
team needs to know that.
So we take the operations data,
we match it with our customer
and our sales data and the interactions
and the relationships that
that we continue to have
with our customers.
At Salesforce, our vision
since 1999 has always been to help
companies
connect with customers in a whole new way.
And now that's even easier
because every cloud is on our core
platform. Apps like Commerce,
Marketing and Tableau,
they've all been migrated to our platform,
And our apps also have built in agents
to help everyone drive productivity.
For sales,
there's built in SDR agents and a built
in sales coach agent. For service,
there are new agents for scheduling
and employee service. For marketing,
which is now on core,
there's a campaigns agent. For Commerce,
which is also now on core,
there's a merchant
and a buyer agent. For revenue and orders,
there's a new deal desk functionality.
Slack, also now heavily
integrated into our core platform.
And all of this is making it easier
to build your customer 360,
which is your single source of truth
for every customer.
We also know
that industries are different.
So we've announced over 100 new industry
specific
AI features and those are ready
to implement out of the box.
Let's hear more from our customers.
So the AI is going to do the things
that the salespeople hate to do.
Salespeople don't like to spend hours
and hours researching customers.
They don't like to start an email
with a blank page,
how to reach out to that customer.
They want to spend their time
engaging with customers, meeting
with customers,
traveling to see our customers.
And AI is going to take care
of the busywork
that they really don't care to do.
Absolutely.
And give them time to do the things that
they enjoy to do that makes us humans
human.
How will having a unified 360 degree
view of your customers impact Bombardier?
So our customers are
some of the busiest people in the world,
and if you reach out to them
with the wrong message at the wrong time
and try to sell them the wrong aircraft,
they're just not going
to have time for you.
So having this 360 degree
view of our customer
allows us to get that messaging right
the first time at the right time.
So now that we've covered our latest innovations, let's hear from more customers.
For that,
Chris Pericak was recently at Dreamforce
and he spoke to customers to learn
firsthand
how they're using Salesforce today
and how Agentforce can help them
go even further.
Let's see what they said.
AI innovation is moving fast.
We've gone from predictive
AI to generative,
and now just one year later,
we're talking about autonomous agents.
This is the moment
when AI doesn't just work for us,
but with us, as an extension of our team.
We caught up with Salesforce
customers here at Dreamforce to learn
how they're using AI, agents,
and a host of other technologies
to transform their business.
Let's check it out.
We are actually about a year
into the journey,
so we have both service replies for chat
and email turned on in our Salesforce org
and we also have work summaries
turned on for our chat transcripts
to be able to summarize a much longer chat
transcript.
Really what we want to be able to
deliver is a truly, it feels like you're
just chatting with a human because people
aren't frustrated with chatbots.
Everyone says they hate chatbots.
It's a bad experience.
What they hate
is not getting the answer they want fast
and not resolving their problems.
I think we're against the idea
of giving a bad experience
and that's, I think where
we're going to see generative
AI is really able to deliver. Our ambitions are
well beyond the email channel,
because the grounding that we've built
our replies on in email, of course is channel agnostic
so we can move to live chat,
it can move to
WhatsApp as well, and WhatsApp
will be with us in quarter four of this year.
We're in the seventies
for NPS score on satisfaction,
and I think that's really because
members feel like they're getting,
not just accurate information,
they're getting helpful and consistent
and well-written information as well.
We take a step back Simplyhealth
has a real purpose as an organization,
and that purpose is to improve access
to healthcare for all
in the UK.
We serve 2.5 million customers today,
but aspirationally we want to serve 10
million, 12 million over the coming years.
Now, to do that, we need to be able
to grow as, scale, as an organization.
And it's not just about saving time, it's
about making that customer experience great.
So an example would be when they call in
and they've got some issue
of it's happened
in the past multiple times,
being able to identify
it as a repeat issue,
find the cases that it's happened
at before, surface those
to our team member
who's actually handling the current case
that they're on that helps us resolve
that current issue faster.
And also figure out, maybe there's some
underlying things that we need to work on.
What about your employees?
What was their day-to-day like before
and how has it changed?
They feel like they have more tools
that are helping them do their job better.
I've got 24 complaints
in my pipeline at the moment,
but I serve my team serves
two and a half million customers.
So you can do the maths there.
The service we're providing is excellent.
So we looked at
what are some really big time
sinks where there's a lot of time
that's getting put into
that's frustrating our team.
And one of those is the account hand-off.
So we took what was 15 minutes, 15 to 20.
We turned it into, it's like 1 to 2 minutes
to read the summary and maybe another 2
to 5 to really dive deep into some of
the important things that they care about.
Now, you said that the Agentforce announcement inspired you to create
a list of the use cases
that could transform your business.
Tell us what's on that list.
So when people are asking
for their flight status,
when people are asking
for the status of their refund,
when people are asking for the status
of their lost or missing baggage,
I believe
Agentforce can be a very powerful tool
to deflect and at the same time provide
that great experience to the passengers.
If you look at before
what you would have to do,
if you wanted to have a service agent,
you'd have to build a big tree.
It looks like an upside down tree,
and that's all the different paths
that it could go on.
Pretty much create every possible scenario
that it could be.
It's not dynamic.
So it's a programed conversation.
So question and answer.
And the only questions we can ask
you are what we have thought of.
Unlike with Agentforce,
you know,
it can dig in to the knowledge base,
it can actually automate.
So the balance of our human expertise
and the use of generative AI,
we've got
we've got it pretty well balanced, right?
So the level of emails
we talked about 43%.
You know, here we are at Dreamforce
and we've been talking about Agentforce.
Well, you know, just 40, now becomes 60, now
become 80%.
Let's talk about data.
How many different sources
where you bringing together?
What types? What did it look like
to bring all your data
together to power these GenAI experiences?
One of the things
I think that's unique about PenFed
is that we've consolidated on the
Salesforce platform for a number of years,
so all of that data was available
to be able to ground GenAI in,
and I think that really helped us
accelerate our journey with GenAI
and know that our data
was trusted in a trusted location
and we trust Salesforce
to protect that data.
So what's been the biggest impact?
Is there a stat or result or
what's happening to let you know
this is working?
You know,
more than a third of our volume
are now being handled by the chatbots
and not reaching our agents.
12 months in, we've been able to decrease
our average handle time on chats
by 30 seconds.
We were able to get that number down
by 26%
reduction in average
handle time for repeat issues.
We're now sending circa
1,200 emails a week.
That's creating around about 95 hours
worth of saving in terms of work.
Our CSAT
scores have gone up by 10%,
claiming experience has never been better,
we got a 99% satisfaction rate for online
claiming.
We've heard a lot about don't DIY your AI.
What would you tell companies that are
thinking about bringing in their own model
and doing it themselves?
You need to think about
what is the business strategy you have.
It's not just about how much it cost
today.
Keep in mind our total cost of ownership
and also when you DIY
now your team owns it.
So when it breaks on a holiday,
it's not exactly ideal
when your team has to go fix it.
But it also takes away
from building other things,
so there's opportunity cost of what
they're not working on.
Now some people are hesitant to deploy GenAI,
what would you tell those people?
Get started, right?
Look, look for a domain
where your data is clean and strong.
We put a thousand emails answering
previously, answering those three
frequently asked questions
into our grounding and touch knowledge
articles, was how we got started.
Amazing to see so many customers together
and hear what they're thinking.
Now let's
see how this comes to life through a demo.
And for that, I'm going to pass it
over to Jody for our Jody Farrar.
Take it away.
Thanks, Nicole.
In this demo, I'll show you how Saks
Fifth Avenue uses Agentforce,
powered by Customer 360 Data
and AI to connect
with their customers in a whole new way
on the trusted Salesforce platform.
Now, as a busy marketer,
I have been known to shop online
and recently I purchased a new sweater
from Saks Fifth Avenue.
I was thrilled to get the sweater,
but it didn't fit quite right.
So I thought about calling
customer service.
Now, normally when I've called customers
service, it's gone
a little like this:
Hello
and thank you for calling
customer service.
If you know the extension of the party
you are trying to reach,
you may dial it at any time.
To hear our store hours
please press one. To start a return
please press two. For product
inquiries, please press three.
I thought
to myself, no, I don't want to do that.
That's not fun. It doesn't feel natural.
But I decided to call anyway,
and the good news is
the experience was completely different
because Saks
Fifth Avenue is using Agentforce.
They just rolled out
their new agent named Sophie
and this is how the call went.
Hello, I'm Sophie, your Saks AI assistant.
How can I help you today? Hi,
this is Jody.
I'm wondering if you can help me
with my most recent order.
I think I have the wrong size.
I'm sorry to hear that. I'm happy to help.
Is this regarding the Saks
Fifth Avenue collection,
cashmere baseball bomber sweater?
Yes, that's the one.
I apologize that the sizing wasn't right.
Given your past purchases, a medium
should offer a comfortable, relaxed fit.
How does that sound?
That sounds good, but you said cashmere.
Is it going to shrink?
This sweater is 100% cashmere,
so we recommend dry cleaning to maintain
the natural fibers and prevent shrinking.
Would you prefer a medium size?
Yes, let's go with the medium.
Given your shipping address, it
should arrive within 3 to 5 business days.
Will 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 quickest
shipping option for this item.
Would you like me to transfer you
to someone
who can provide further assistance?
No, thanks.
Ok,
now, that was a totally different
experience.
I was able to immediately start talking.
The automated agent knew exactly who I was
because it could access my full customer
360 profile, including my orders,
because my customer data
was all connected with Data Cloud.
It was even able to take some action
and order a new size.
But at the end
you may have noticed that it didn't know
how to get that sweater to me any faster,
and that's because
right now the agent only knows
how to talk to the shipping carriers.
But that's not as far as agents can go
because some stores have
physical locations.
So let's configure
Agentforce using Agent Builder
so we can see what happens
when the agent has the ability
to identify physical stores
with their inventory levels.
Here we are in
our all new Agentforce studio with Agent Builder.
We have our configuration here for Sophie,
we have our avatar,
we have our agent's description.
And to configure this, it's
all done in natural language,
so if you can describe
it, Agentforce can do it.
And what I really want to show
you are topics
which are the foundational building blocks
along with actions that help
you build these new agents, topics,
or categories of information.
I have an order management topic here,
which is the one
that was just used in
the last example with Sophie.
This order management
topic has a description
and scope with some specific instructions.
So when there's a conversation
with a customer and the agent detects
it, it's about order management,
it makes that connection.
This was
all done here with a natural language
description,
so no code was needed to make this happen.
Within these topics, we also have actions.
You can see some of the actions
that the agent already knows
and those are actually just flows.
Actions
we saw included finding my order number,
checking the order status,
even modifying the order.
Now I want to add some new actions.
I want to give the agent the ability
to find stores and check their inventory.
If I click ‘Add’ action,
I can see here I've got a couple of 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 too, but you'll notice
I don't have anything
to help the agent check the store's
inventory, so let's fix that.
I'll close this and
navigate over here
to add a new Agentforce action.
What's so incredible about Agentforce
is you're able
to leverage what you've already
implemented in your Salesforce org,
like your workflows and processes
so you can get up and running even faster.
Pick what you want
and add it to Agentforce.
In this case,
I'm going to pick a MuleSoft API
and I happen to have a store inventory
API already available.
Agents can actually query
and talk to these APIs just like we would.
So I'm going to add this API.
I can edit the inputs and outputs
if I need to,
and I'm going to click finish.
Now let's jump back over to Agent Builder
and if I add these actions,
we should get some new things.
So let's 'Get Nearby Stores'
let's do change delivery method,
let's schedule an 'In-store Pickup'
and let's add our 'Store Inventory API'.
So we'll add those
and you can see
they were added to our actions here.
Now, all we had to do is add the actions
and Agentforce is going
to figure out how to help the customer
get what they want.
But you don't have to trust me.
Let me show you how it reasons
using the Atlas Reasoning Engine
thinking every step of the way.
So I'll test it with my use case and write:
hi, my name is Jody Farrar, customer ID,
yada yada yada yada.
In the middle of the screen
we can actually see the Atlas
reasoning engine taking actions
it defines on its own.
We see the prompt I just gave it.
We can see it makes a connection to the
order management topic that we looked at
and now we
can start to see new actions taking place.
The agent is actually going out
and querying our find order
number flow, bringing that back in.
It's then moving on to the next step,
which is to check the order status.
Now this is where it stopped before
because in my question
I asked if I could get it any sooner,
but now it goes on to the next step
because it's figured out
that I might have another way
to get this customer the sweater faster.
So you can see it checks
if there's a store near me
and it's looking into the'Store Inventory API'.
And then it’s figured out
that it needs to go back to the customer
and ask if the customer
would like to do an 'In-store Pickup'.
The agent asks if the customer wants
an in-store pickup and yes, I do.
So now the agent decides
these last few steps,
which is to change the 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 using voice
like we were a moment ago
or using Apple Business messages
or using the chat on a website.
It just works.
It's all one agent,
so let's see it in action.
Hello, I'm Sophie, your Saks AI assistant.
How can I help you today?
Hi, it's me, Jody again.
Can you give me an update on my order
delivery from my most recent order?
Is this regarding the Saks
Fifth Avenue collection,
cashmere baseball bomber sweater?
Yes, that's the one. We offer two delivery choices.
I can arrange for it to be delivered
within 3 to 5 business days,
or you can pick it up
today at Saks San Francisco.
Which option suits you better?
Oh, that's great.
I would love to come to the store
and pick it up.
Great.
I've processed the order
and notified the in-store client advisor
about your pickup.
The sweater will be ready for you
within the next 3 hours.
Is there anything
else I can assist you with?
No, that's all.
Now, we've seen Agentforce in action
and we've seen it
reason. We also know we need to be able
to do all of this with trust.
So let's take a look at our new Omni
Supervisor
where you can see what your human agents
and Agentforce agents are doing
because a company might have many agents,
especially if they're global.
Here we see different agents
and recent interactions.
There's an interaction
that closed a little while ago
between a 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?
I'll just hang up on that.
And with Omni supervisor,
we can even listen to
calls as they're happening in real time.
Here are two calls that are happening.
One with Brian Green.
Looks like he's having a problem
with his password.
Let's give that one a listen.
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
to ensure everything goes smoothly?
No. I don't want to stay on the line
while he recreates his password.
So now you've seen
how Agentforce is helping companies
connect with their customers
in a whole new way,
using AI and Customer 360 data
on the trusted Salesforce platform.
Back to you, Nicole
Amazing.
Thanks, Jody.
So now we've heard all about Salesforce's
newest innovations,
including Agentforce.
We heard firsthand from interviews
with customers,
and we saw a demo showing how it works.
Thanks so much to everyone who joined us.
You can find more resources and related
materials in the broadcast description.
And if you asked a question,
we'll get that answered in the chat.
Don't forget this is part
two of a four part broadcast series.
We've already covered AI readiness,
so be sure to check that out
and up
next, we'll be talking to Forrester's
Kate Leggett about how AI is changing
customer relationships.
Register to watch, live
or catch it on-demand.
See you next time.
Resume AutoScroll
Link copied to clipboard
Episode 2: Join business leaders to explore what's new with Agentforce.
Discover the GenAI tools driving customer success. Hear real-world customer stories and watch Agentforce in action with an exclusive demo.
Up Next
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 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 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, TDX, Tableau Conference, and Connections. 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. 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.
