Please welcome Senior
Vice President Product AI
Platform Salesforce,
Adam Evans.
Welcome to day
two of Dreamforce.
Is everybody
having a good time?
Are you guys ready for
Dream Fest tonight?
Pink, Imagine
Dragons, Kygo.
It's going to
be a fun time.
So I wanted to say, well,
first off, thank you.
Thank you for
getting up early.
Thank you for
waiting in line.
Hopefully you
had your coffee.
Thank you for
being our customer.
Thank you for being our
trailblazers and soon
And if we could
just step back.
I mean, this is
such a moment.
And I don't mean
necessarily just us
in the room, but
the bigger us.
There's not many
moments like this.
30 years ago, we had a
moment kind of like this.
It's called the
internet came out.
It started slow
and then it
went fast, connected us,
made our world smaller.
15 years ago, we had
another moment like this.
We started carrying around
these little devices
in our hands, kind of
exactly this one, started
slow, and then
it went fast.
It changed the way
we communicate,
the way we operate
with businesses,
really transformed
like the social fabric
And today we
collectively are
going through another
moment together.
This is an AI moment,
and it's really
at this moment that we
think about the future
that we want, that
we're going to create,
the trailblazers together
in this room with agent
force and what
we're launching,
but more importantly,
not the technology,
but ultimately,
what you do
with it is going
to help change
this moment for everyone.
And for Salesforce,
this moment
started as a journey
10 years ago.
You've seen this with
AI, the first wave
with predictive, moving
into a generative wave.
And Mark did this
slide yesterday,
but I would like to
do a little change
You see that item at
the very left here?
That's when I
joined, and that
was my company that came
into Salesforce as family,
the ohana, as
we'd call it.
We've come back into
the generative wave,
so I've had the
pleasure of being
And I want to talk
to you a little bit
about the difference
between the left
and the right, 10 years
ago, the then and the now.
Because 10 years
ago at the beginning
of this wave, we would
build entire companies
with great engineering
and spend years on it
to build features
that would do things
like analyze
emails for sellers,
tell you what the next
steps are and do more.
And it was so much
work to do that.
Today, what's changed
across this timeline
is we can do
something like that
in a matter of days now,
with much fewer engineers,
And this is the power of
the generative technology
It is an entire collapse
of companies and products
And it's incredibly
interesting
to think about really
a step function change.
And during this
time, companies
have had
opportunity to grow.
We've had an opportunity
to increase our margins,
drive productivity,
and to completely
transform our businesses.
But yet during
this time, there's
been this expectation
always slightly ahead
of us, always more
growth, more margin, more
There's always more
work to do than there's
Simply put, there's not
enough time in the day.
So the question is, how
do we close this gap?
And that couple orders of
magnitude opportunity I
just spoke about in the
last 10 years, that's
That is an
inflection point
waiting for us to take to
ultimately close this gap.
And of course,
the way that we're
going to do this to get
more time back, complete
more work, have
more productivity,
have more growth
is with agents.
We are in the
era of agents,
and there's no
better place
to build agents
than on agent force.
It's everything
that you need
to build, to customize,
to test, to deploy,
to monitor once
they're deployed,
to improve full circle
everything that you need
built on the platform
that you've been using
for decades connected
to your Customer 360,
grounded in your
data, and more.
Today, we're going to go
through customer stories.
We're going to talk
about actual ROI.
We're going to
show you how
to build agents and
customize the ones that
We're going to show
you how to build agents
But before we
do that, I want
to talk a little bit about
what actually is an agent.
At the heart of it, you
have a reasoning engine,
and this is really the
key unlock, the ability
to take context
and actions
But context, where
does that come from?
That's your customer
information.
That's your instructions.
This is your
data connected
And ultimately, if
it was just data,
it could answer questions.
But if we want to
close that gap,
We have to complete tasks.
So the combination
of your data
and the actions
that are built
on the platform
with the reasoning
engine, these
three components
are critical to
creating an agent,
and it unlocks so
many use cases.
Use cases like a sales
agent that can follow up
with leads, qualify them,
and hand them off for you
Use cases like service
agents that can answer
customer questions 24/7
and deflect tier-one
Also, things like
transcription
for all customer
conversations.
Thinking about adding tags
to a customer's profile
for a marketing campaign,
understanding things
like product defects
that can go back
to supply chain, also
things about understanding
business policies, even
compliance as well.
I'd like to drill
into one of these
to tell a story to make
it more illustrative,
something we're
all familiar with.
Order management,
order issues,
you go and you place
an order online.
You want to communicate
with the company
So what is the data and
the actions for that?
Well, the data may be
the customer profile,
It may be your
order history,
being able to understand
the order details, maybe
inventory company
policies, more--
The actions are the
ability to maybe look up
a profile by email
or by phone number,
or maybe you
look up an order
by order number,
inventory by skew.
So let's take an example
of a customer saying,
I haven't seen
my order yet.
My order number is X.
What will the agent do?
It can take the order
number, collect the data,
And depending
on the answer,
It changes the next step.
Let's go check the
inventory for that skew.
Depending on if it's
out of stock or not,
In this example,
we're out of stock.
Let's look at
our policies.
What are our policies
when this happens?
That now changes the
response and the actions
that the agent
is going to take.
So it's this idea of
connecting actions
and data with the agentic
reasoning step by step,
reacting to the
data as it comes in
to navigate these choices.
I'm giving you
one example,
just an illustration
of something that's
relatable, a story
of something being
delayed because
it's out of stock.
But in the real
world, there's
many, many variations of
that, that same statement.
I haven't seen
my order yet.
My order number is X.
Could have played out
in thousands of
different permutations.
That order could
have been shipped
and maybe the agent
can check the tracking,
live tracking, and it's
actually in transit.
And then the outcome
would have been,
your order is going to
be there in two days.
That order could
have been shipped.
So that's perhaps a lost
and stolen package issue.
And we need to
check our policies
about how to handle that.
Or maybe that order
number doesn't even exist,
and the agent could
figure that out
and say, I'm sorry,
is this a typo.
Is this the right
order that you meant?
The point is that there's
a lot of complexity.
There's a lot
of variability,
and the reasoning
engine connects this.
And I've been a programmer
doing written code
I can tell you the way
that we use to solve this
is that we have to
go through every
permutation,or at
least we try to.
It's actually impossible.
We have to make a flow
chart for each thing.
We have to make a dialog
flow for each of these.
We have to know all
of the questions that
are going to be asked
before they're asked
Not only is it
no code, but it
lets you move across all
of these paths because
of the reasoning engine
within the agent.
Now, there's one scenario
that I haven't highlighted
here, which is, what if
the agent can't do it?
And that's where the
agent brings us in.
That's a big part
of agent force.
And really I think
that's what this really
What do we want to
do at this moment?
How do we want
to extend ourself
to augment ourselves,
to be more productive,
What kinds of
jobs and tasks
do we want to
work on versus
We get to design
the future,
and it's going to be
a really exciting time
for all of us to
go through this.
How we bring humans
and AI together,
grounded in your data and
connected to your actions,
your flows, your Apex
thousands of connectors
This is what agent
force uniquely has,
and these are
the key elements
And today, what
we're going to do
is we're going to drill
through each one of these.
We're going to show
you customer stories,
And for that, I'd like
to welcome to the stage
Senior Director of
Product Management, Gary
Brandeleer to kick us off.
Agentforce is what
I was meant to be.
It's the promise
of CRM fulfilled.
It is AI at the service
of your company,
your customers,
and your employees.
Now it's augmenting every
single of your employees
so that they can focus
on high-impact tasks
by removing
repetitive work.
They can now focus on
the customers which is
And of course, it's just
not about productivity.
It's about unleashing
creativity,
making sure that you can
build the best customer
Now we learned
a lot last year.
It felt like a
decade in AI terms.
The pace of innovation
is accelerating.
And with that comes also
a lot of challenges.
And there is one
truth popping up,
which is AI in
enterprise isn't easy.
Everybody is chasing
the same dream.
Its customer success
powered by AI.
The story, though,
is that you
want higher productivity,
higher margin,
But the reality is
that that's just
Beneath the
surface you will
face many companies
are facing
hidden costs, disconnected
data, complexities,
And the worst of it
is that the industry
is telling you go and
build it yourself, build
But the reality is
that, by the time
you are done doing your
AI, it's already outdated.
And there is a better way.
Agentforce unites
human AI, data, and CRM
together so that
you have everything
you need to innovate
without the headaches.
We bring you Data Cloud
so that you can bring data
from external and internal
sources to feed the agent
and make it knowledgeable.
We give you the
360 degree profile
so that humans and
AI work together
toward the same goal,
customer success.
And Agentforce so that
you can build and create
your agent in
a few clicks.
And the beauty
here is that it's
built on the
Salesforce platform.
It means that you
don't have to learn
You can reuse flows, Apex,
profile, permission sets
to create and
build your agents
and make sure that
you control as well
the access to data
that you will have.
Meet your Agentforce,
your team of AI and agent
We provide you
out-of-the-box agent
for service, for
sales, for marketing,
for commerce, so that
you can deploy your agent
in a few clicks and
make them your own.
And the reality here is
that all of these agents
have built-in
seamless handoff
to humans when human
oversight is needed.
Now, you might
be wondering, OK,
but I have a chatbot, so
how is this different?
Back to what
Adam was saying,
which is like,
hey, this is
You need to think about
all the conversation
the customer is
going to have.
So you need to set up the
intent, the dialogues,
a lot of things
to set up there.
And it's never going
to fit all your--
The Copilots, they
are assistive,
but, kind of like
productivity,
It's not really
easy for them
And then you
have Agentforce,
and you have agents that
are autonomous, proactive.
They can take actions on
your behalf, of course,
always bringing you when
human oversight is needed.
Just to give you an
idea of the unlock
here that Adam was
thinking about.
We had a customer with 140
intent in their chatbot.
They moved to agents
and got to topics only,
and that agent was able to
endure more conversation
That's the business
simplification
we are talking about here.
Now picture this across
every single industries.
You could have agents
in retail doing
commerce concierge
always on on your website
You could have, in telco,
an agent doing customer
support 24/7
reducing wait time.
And the beauty here is
that the possibilities
You can configure and
customize these agents
at every level, at the
agent level, the topic
level, the action
level up to you
to decide what they
are going to do.
It's not only across
every industry.
It's also across
every app.
We replaced Einstein
Copilot with Agentforce.
It can now learn reason
take actions for you
Something extremely
important to keep in mind.
All these agents are
built on the same exact
It means that you
have a role, which
is defining the topics
that the agent can
You'll have instructions
that the agent
You will feed some data
so that the agent is
knowledgeable
about your business
and relevant to
your business.
You assign actions
so that they
can take actions for you.
But don't worry, there
is guardrails, of course,
so that you have
defined limits.
They will act within the
limits you give them,
and they can
interact across
All this built on
the trust layer.
Because data safety
is still number one.
And the second
part is that you
want to guarantee the
highest degree of quality
for every single
interaction.
Now, let's speak a little
bit about customer success
I was fortunate enough
to do many, many pilots
with many of our customers
and learning with them.
And we learned a
ton, to be honest.
Wiley was one of our first
pilot customer, a leader
And what they did
there was like there
School starts, you need
to buy courses and get
So seasonal surge,
and the story
there is that they
added to increase
the number of agents
to insert the cases.
But with Agentforce,
they could literally
answer 40% more cases
by piloting Agentforce.
So with that, we are going
to deep dive in the demo
where you'll see how
role, action, guardrail
are combined together
to make an agent that
is going to answer
Wiley's customer needs.
And for that, I'm
going to bring on stage
my favorite PM at
Salesforce, Angela Le.
So Wiley is one of the
world's leading publishers
and one of the global
leaders in research
So every year they
see a huge surge
in customer requests
when students
are getting ready to
go back to school.
So that's why they
deployed Agentforce.
And Agentforce is grounded
on Wiley's business
So it understands
that, when
I ask if I can read a
textbook on the plane,
it semantically reasons
through that request
and knows that it
needs to work offline.
But it doesn't just
answer questions.
It can also take
actions for me,
like helping me
reset my password.
But what if I ask it
something a little more
complex, like helping me
add and update something
It's going to
reason through that.
But actually,
today, this agent
doesn't know how
to do that yet.
So it actually does
what I want it to do,
which is to deflect and
redirect me to a human.
But let me show you
how you can actually
customize an agent like
Wiley's in our Agent
So let's go into Setup and
look for our Agentforce
service agent and
open up our Builder.
An Agent Builder is where
the customization magic
Here, we have a
couple of topics,
and topics are where
we can let our agent
know what the jobs
that needs to be done
and the topics of
conversation it
should be able to handle.
So let's take a look at
our Order Management topic
Now every topic has two
elements, instructions
And actions are crucial
because they provide those
guardrails of what the
agent can and cannot do.
So we already have a few
instructions in here,
like redirecting to a
human representative
if someone tries to
update billing details.
But look, my
five-year-old, it
needs a few more
instructions
to get the job
done correctly.
So let's add an
instruction here
that asks for
confirmation details
when someone tries
to update an order.
And then we'll
do another one
that asks to help
with our order
if they ask for
order information.
And let's go to
the next step.
So the second
part is actions,
and actions are
so powerful,
because they
allow our agents
But what's really
special about our actions
is that they're built
using the platform
tools that your
Trailblazers have already
been using, like
Flows, Apex,
So let's take a look at
one of our actions here.
And here we are
in Flow Builder.
And you might
be wondering,
Well, because
your Trailblazers
have been spending
years putting things
into Flows, your business
rules, your processes.
And we want to make sure
that you can reuse them
to be really prescriptive
to your agent
so that it's pulling
the right order
information to ensure
a seamless customer
So let's go back
into Agent Builder,
add those two actions,
and click Finish.
And just like
that, we were
able to add in new
instructions and actions
to a topic without writing
a single line of code
or creating any
complex dialogue trees.
So let's head
over to Preview
and test some of
these user requests
And what you're
going to see here
is our reasoning
engine reasoning
So what are we looking at?
Well, this is the result
of our reasoning engine.
This is not a
dialogue tree.
This is the reasoning
engine, reasoning,
thinking, grounding
through our request
to pick the right
topic and to select
the right action in order
to complete the request.
So let's go back to
the original request
Again, we selected
the right--
we're going to go and
look for it to select
And then now we're
actually getting an update
And just like that,
with the simple change
in our instructions
and actions,
we're now able to have our
agent do this job for us.
But let's test and see
if our guardrails worked
and try to update
payment method
and see if I can trick the
agent to doing something
And remember
that instruction,
we had to not update
billing information.
Look at our
reasoning here.
It correctly states that
it can't do this update
for us because we provided
explicit instructions
to prohibit it, the
agent from taking billing
So now it's redirecting
us to act to a human.
So I can continue to go
and preview and test,
but that's going to be
really hard to scale.
So let's go back to
the request we had
And here we have our new
batch testing center.
And we already see that
the request we put in here
But let's go
ahead and create
a test that I know
is going to fail,
something that
has nothing to do
with Order
Management, which
And what I'm looking for
is to fail, which it does.
And if I wanted to have
Order Management tell
me jokes, I can take
a recommendation
So let's go
ahead and delete
that because it
has nothing to do
And while it would
be great to go line
by line with you
all thousands
of people updating
utterances,
I'm actually not
really good at updating
So now with the
simple prompt,
I can ask the
LLM to generate
And what it's doing is
creating many permutations
of Order
Management-related
And what I'm looking
for is a pass and, wow,
look at that, all greens.
And so now I can
feel very confident
that I can activate
this topic.
And it's not going
to work just once
So let's activate this
topic because it's
So now I'm back on
this support page,
and let's try that
utterance again,
because I really need that
microbiology book to start
It's able to
update that order.
So with Agent
Builder, I was
able to quickly
create a new topic,
have a new job to be
done, test it at scale,
and bring new
functionality to my users.
I love the test
center being
AI helping you
launch AI faster.
Well, we actually have
Kevin Quigley here
I'd love to ask you a
couple of questions.
Thanks for being
a customer.
So Kevin, can you
just tell us about--
you've launched
Service Agent.
Tell us a little bit
about the outcomes
So I'd say there's two
really amazing things
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
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.
So bringing in knowledge,
very quick, personalized
Talk a little bit about--
I mean, we were working
together on this.
And I think we share maybe
a little bit of the story.
But what was it like to
actually set this up?
I'm sure everybody's
thinking,
how hard is
this to deploy?
So there's something
really interesting
that's happening
with agents, which
is that you're shifting
that conversational
experience
design from being
this sort of tedious
back and forth
collaboration between
your support experts
and your IT
resources, your CRM,
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 PhDs and CS degree
We took our
support experts.
We took our existing
CRM team and our product
support teams, and
we empowered 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 old
chatbot from the agent.
Kevin, thank you so much.
Wiley team, thank
you so much for being
And so speaking
of knowledge
and being able to have
great results with Wiley,
that brings us to our next
chapter, which is data.
Avanthika, do you like
to tell us about data?
Well, isn't it
quite amazing
how Agentforce is able
to orchestrate everything
from workflows and data
all the way to prompts
and models to create this
truly autonomous agent
Now, after speaking with
many of you in this room,
here's the question
we're all asking.
How can we trust
these agents
to operate autonomously
and deliver real business
Well, you might
have heard us
say that your AI is only
as good as your data
because your
agents need access
to trusted, accurate,
and real-time data.
Now in terms of
how you do this,
it's quite easy to say
that you need to power
your agents with
data, but how
Now, a year
ago, many of us
thought that the
answer to this
was to train a custom
model on all our business
But soon enough,
we realized
that this isn't actually
the most efficient
approach, especially from
a cost and time investment
These models quickly
went out of date
especially as your data
kept evolving and growing.
Now, at the most
basic level,
these AI agents
work by sending
a series of prompts
to a large language
model, which then
generates a response.
So here's where the
real magic happens.
It's all about
bringing the right data
to the right prompt
at the right time.
Now with Agentforce,
you can actually
leverage a lot of
your existing business
workflows and data
to be able to create
For example, we can start
by pulling structured data
Think Flows, related
lists, merge fields.
All of this already
lives in your system.
But let's take this
a step further.
You all have vast troves
of unstructured data
living in your enterprise.
Think emails, cases,
conversation history.
You can't just pull
all that data directly
into a prompt, but
at the same time,
you can't afford to
ignore that data either.
So this is where the
power of retrieval
augmented
generation comes in
or what we call RAG
in order for you
to bring the right
unstructured data
Now with Data
Cloud, you actually
have the ability
to bring all
the structured and
unstructured data
And from there your
agent, at the moment
it needs that data, can
easily search and retrieve
So we offer a variety of
techniques for search,
whether it's vector
search, hybrid search,
or even search-based
on knowledge graphs.
Now, in terms
of search, we
talked about
how important it
is to be able to bring
in the right data
So as you can
see here, data
It's the fuel
for what powers
Agentforce's next
generation reasoning
Now, let's talk about
how this all works.
In order to build these
context-aware agents that
are able to reason
on your data,
you also need
good prompts.
Prompts are what
really power this.
Now many of you
love Prompt Builder.
Thousands of
your own users
are already using
Prompt Builder today
Think content generation,
record summaries.
A lot of our users are
reaping huge productivity
gains from using
Prompt Builder,
and we're excited to
see how you all continue
Now, speaking
of customers,
don't just hear
it from me.
We actually have one
of our very own Agent
Blazers here in the
room with us today.
So let's go ahead
and say hello
Well, I want everyone
to take a moment
to say hello to Erin
and the ezCarter team.
Let's wave at the camera.
Erin, well, we're
here to talk about AI.
But before we get
into AI, can you
share a little bit more
about what ezCater does
So I imagine
everybody here
knows how easy
it is to place
an order for
food or friends
and family on
a Friday night.
But if you have to
place a business order,
suddenly you don't
know exactly how much
You don't know people's
food allergies.
And how do you
make certain
that the delivery
driver is going
So that's where the
ez-tech food platform
We're making it simple
for organizations
to manage their
food needs.
Well, we all
talked about AI
and how critical it is to
powering your business.
Tell me a little bit more
about some of the use
cases and opportunities
you see AI really driving
value and how
Agentforce is
critical to that journey.
So in recent years, we've
been pointing AI and ML
on our 17 years
of catering data.
So with a few simple
inputs from a customer,
we can generate a novel
order that also honors
So if you wanted to place
an order for a team of 17,
but that restaurant's
lasagna tray only
serves 12, we
can auto generate
what's the right
additions to that order.
Where we're going now with
the help of Salesforce
is solving what we're
calling the discovery
So today our
solution really
depends on the customer
deciding their restaurant
of their choice,
or they can
opt to talk to what we
call our Beyond Helpful
Human Customer Service
agents that have
the full business catering
ontology in their heads.
So when customers
use terms
like I want something
gourmet or seasonal
or phrases like can
you order me something
similar to what
I had last month,
the agents can take
this unstructured set
of prompts and decide
what the customer needs.
So as we scale and need
to handle more volume,
we need to augment
our human agents
with a solution
that's going
to give the customer that
same sense of talking
And so that's where
the Salesforce solution
The Prompt Builder
is allowing
us to structure these set
of grounded prompts that
can think about the
context, not just of food
descriptions, but also the
customer's order history
You don't want to be
the sales person sending
your client pizza for
the fifth day in a row.
And so we have
the confidence.
Not only is it
understanding
that grounded context, but
using modern techniques,
it's going to validate
that against data
Many moons ago, in our
early experimentations
with AI, we had
a model decide
an interesting
recommendation.
It was spaghetti with
your side of French toast
So we trust that the
Salesforce solution
is going to give
the customer really
a well-reasoned response
and know when to hand it
back to a human
agent, which
is super important to
our customer service.
Erin, what a
wonderful use case.
I love your
team's innovation,
and especially, thank
you for being a pioneer
and believing
in Agentforce.
Well, you all just heard
it directly from Erin.
So what are we
waiting for?
Let's see this in action.
So up next, we're
going to show you
how ezCater is using
prompts, data, search,
and the power of actions
to power what Erin just
said, the next
generation customer
Now, here I am on
ezCater's site.
When I'm hosting
large team on-sites,
I know I can depend
on ezCater to help me,
especially with
my complicated
Now I log in to the site,
and a rep from ezCater
is available to
me to help me
with my dietary
preferences.
Now, as Erin
mentioned earlier,
the reps probably get
thousands of these types
So how can they help
their business scale
but yet provide this kind
of white glove experience
that they're providing
on their site today?
Well, we just learned
about how good prompts
So we're going to
start our journey
So here we are in
Prompt Builder,
and I'm going to
create an instruction
to provide catering
recommendations based
So when a query comes
in, this variable
called the Input
Request, that's
what dynamically
captures what
Now we get the
user's request,
and we want to be able
to answer their question,
but it doesn't stop there.
We want to know
a little bit more
about the company the
user is coming from,
along with some data
about their past orders.
Now this resource
picker right here
is your access point
to all your data
So from here, I'm going
to go ahead and click
I can bring in a
record snapshot.
This is essentially
a snapshot
of all the
information we have
Now we can go beyond
the surface-level data
and actually use
some existing flows
that we have in
our system to fetch
some of their past
order history.
So now we insert our Flow
to get the order history.
Now let's take it
a step further.
We know that we
have enough context
about the customer, but
what about ezCater's data?
What about all
the information
about their caterers, the
menu options, the customer
All this data lives
outside of Salesforce.
And obviously I can't show
you ezCater's database,
but it might
look something
like this, where they
have thousands of rows
As you can see, they have
menu descriptions, caterer
I mean, look at that
long menu description
So how can we
make sure we're
getting just the
right information we
Well, with Data Cloud,
you can actually
bring that information in.
So we have all
this information
that we just saw
stored in a data model
object that many
description that we
saw earlier is brought
into Data Cloud.
Now we want to be able
to search this data.
And to do that, I'm going
to build a search index.
It starts by determining
what fields of data
we want to
search based on.
And from there, we're
going to actually segment
this data into
smaller chunks, what
Now, once we
chunk the data,
we want to be
able to create
numerical representations
of this information called
And for that we're going
to use an embedding model.
Now I've used this
embedding model.
I create those
vectors, and now I'm
able to store it in Data
Cloud's vector database.
So I've done everything I
need to create that search
I'm back here in
Prompt Builder,
and I'm able to access
that search index I just
created with all the
caterer information.
And now I need
to determine
how I want to retrieve
that information.
First, we input
the search query.
Now you'll notice
that this is
This is almost like
a prompt of its own
because this is what
dynamically captures what
the user is asking
for and passes that
And from there, I'm
going to determine
what fields of information
I want to retrieve.
This includes the customer
review, the menu options,
So I have all
the data I need.
The last thing
I'm going to do
is insert a few more
formatting instructions,
stylistic considerations.
Now I've built my prompt.
Now the beauty
of Prompt Builder
is you can even test
your prompts right here.
So I'm going to be able
to test this on a sample
account record and enter
the same query I asked
Finally, we can
just select a model.
So I have a whole host of
models I can choose from.
These are all
generic models not
trained on any of
ezCarter's data.
And here I am ready to go.
So let's go ahead
and give that a test.
Now, let's
actually break down
what we're looking
at right here.
Let's zoom into
that resolution.
What we've done
is we've actually
resolved all the different
data references you
saw earlier in that
prompt template
So first, we
had a reference
So we brought all
the information
that's on that account
record right here.
From there, we
also brought
in some of their
past order history
So all those results
are brought in as well.
And finally, what about
those catering options?
Remember we had that large
unstructured database
Well, we use
search to bring
in just the relevant
results for the query.
And in this case, I asked
about vegan restaurant
Our search was able
to bring in just
I mean, that first one
with vegan table, a 94%
So that's how search is
able to bring in just
And we have all this data
packed into the prompt
that we send to the
large language model.
Let's go ahead and
send that to the model,
and let's see what we get.
Here we have it,
our response.
It was able to synthesize
all that information
and give us right
what we needed,
which were the three
catering recommendations.
Now all I need to do
next is attach this
prompt to my agent
as another action,
and let's see what the
ezCater experience looks
like now with Agentforce.
So I'm going to ask
the same question.
We got our three
recommendations
Now, we know
that these agents
go beyond simple
question answering.
We can even have these
agents take actions
So how about we
asked this agent
to place an order
for my team?
Now, what happened
behind the scenes?
We were able to invoke
ezCater's proprietary API
They have their
own API, which
was also available as
an action for our agent.
I'm going to go ahead
and submit my order,
and I can rest easy
that an awesome catering
order is on the way
for my team on site.
And that, my
friends, is how
ezCater is able to power
this white glove customer
experience using the power
of prompts, data, search,
and overall agent for us.
So thank you so much
for following along.
That was such
a great display
of how accurate data
with good prompts
And there was one thing
that you showed right
I just want to
highlight that,
being able to transact
with the order.
That was connecting
previous investments
and APIs that were already
built before the agent
to the agent so that the
agent could take advantage
And that's what we call
actions, which brings us
to our last chapter
here with VP
of Software Engineering,
Claire Chang.
It's great to be
here with you all.
When we talk about
Agentforce brings together
humans with AI,
data, and actions,
the true value here is
about getting work done.
Agents being able
to take actions
is what empowers
employees and drives
How does Agentforce
extend your workforce?
What does
Agentforce provide
to make your teams
more successful,
give them more time,
and help get to the jobs
that they can now
complete every day?
First of all, Agentforce
is giving you access
to a collection
of highly capable,
out-of-the-box
autonomous agents.
As you heard from
Gary earlier,
we have built
multiple agents
to complete the common
jobs across Customer 360
to help your service
teams, sales teams,
You can enable them
easily and customize
them to fit your business
and drive your success.
Why Agentforce can assist
you and take actions
At the center of it is
Atlas Reasoning Engine.
As you've learned
from Adam earlier,
this is the brain
behind Agentforce force
which simulates how
humans think, plan,
It starts from
evaluating users
request and the context,
refining them for clarity.
From there, it retrieves
the most relevant data
from your business, your
CRM, and your Data Cloud.
This is super
critical to make
sure the plan is formed
and tailored to solve
The process keeps
evaluating and refining
the plan, making
sure only the right
and the relevant actions
are going to be invoked
With this extremely
powerful reasoning engine,
you now have the
ability to get
If you can describe it,
Agentforce can do it.
It means you can customize
out-of-the-box agents
or build your new agent,
all powered by Agentforce
As we've seen from
the earlier demo,
in Agent Builder,
you can create
jobs to be done
for your agents
by describing the topics,
writing natural language
instructions, and creating
a library of actions using
the tools that you already
have today in Salesforce.
You can use Flows,
Apex, MuleSoft APIs,
and the prompt template
that many of you
have been already
using in the past year.
In Agent Builder
you can also
observe how agents reason,
plan, and take actions.
You can evaluate
the results
and refine the
instructions
Since Agentforce is a
native part of Salesforce
platform, all
of your data,
all of your
Customer 360 apps,
and all of your business
logics and automations
that you have
already built
can be leveraged
by the agents.
Because Agentforce
is deeply integrated
with your apps and
with your data,
we are now
transforming the work
can be done across
every row, workflow,
We are truly bringing
together humans and AI
agents to drive
customer success,
and we can scale it
up like never before.
And of course,
Agentforce platform
is extensible
and is integrated
with our amazing
partner ecosystem.
You can extend
your workforce
by bringing a
partner agent,
or you can use
a partner action
and add it to your
existing agent.
Or you can bring any data
with our zero copy data
So now you have
a collection
of out-of-the-box agents,
and you have all the tools
you need to customize and
build your own agents.
How do you employ those AI
agents in your workforce
and ask them to take
actions on your behalf?
Well, with
Agentforce platform,
You can srevice the agents
in any of your existing
apps across all
your conversations
and even integrate with
your automation flow.
Now we would
like to show you
how you can
build your agent
and lighten up in
your organization.
With that, please
welcome Carlos Lozano.
Let's build a custom
agent together.
Following the
anatomy of an agent
that you see
on the screen.
And let's start right
here in the agent setup.
So as I click New,
notice that Agentforce
is giving me
the flexibility
to start with a pre-built
agent for service,
for sales, for
marketing, for commerce.
But today, let's start
an agent from scratch.
If you can describe it,
Agentforce can do it.
So let's go ahead
and describe
the purpose and the
goal of this agent.
And let's do
an agent that's
going to handle
something that we all
like to do every time
we go on a business
trip, which is our
travel expenses.
This next Monday
or in a few days,
when you guys
go back home,
we're all going
to do this.
Wouldn't it be
nice that we
have actually
a custom agent
We can give it, all
of our expenditures,
and can handle
that for us.
Let's go ahead
and do that.
So let's go ahead and
give it a purpose.
So it's going to
be a travel expense
agent that's going
to be tracking here
expenditures,
reimbursements,
and making sure it
follows, very important,
Now watch what
happens next.
Based on this natural
language instructions,
we're going to see what
Agentforce is actually
what's actually
happening here?
It's doing a
semantic search.
What does that even mean?
Based upon the
description we provided
in the previous
step of the wizard,
it's actually able to
find semantically similar
Salesforce resources
that you already
We have a number
of actions here,
and it was able to
infer in which channels
given the
descriptions we might
Let's take a
quicker look inside
of this topic suggestion.
These are your assets and
resources you have already
And because you have
properly described them,
the descriptions
are very important
for these assets,
the system
is able to bubble them up.
Now these have
high similarity,
and that's looking great.
I also want to actually
surface and deploy
my agent to allow it
to send notifications
So I'm going to go
ahead and click on that.
As we go to the next step,
based on the descriptions
you have provided to your
resources, to your Flows,
to your Apex, to your
prompt templates,
it is also able to infer
these topics instructions.
Remember, as part of the
anatomy of a custom agent,
these instructions
act like the rules
that the agent
needs to follow.
How is it going to
use these actions?
And what should it not do?
I can edit them at
any step of the way.
For today, let's just
go ahead and move on.
Where do we want this
agent to be deployed?
It has pre-populated
this channel selected.
For the sake of today, I'm
going to unselect email.
I want it to basically
give us an output on Slack
and allow my users
to engage with it.
But also very
important, agents
can act in the
background headlessly
without you even noticing.
And how are we
going to trigger
We're going to use
a mechanism that you
In this example, we're
going to use Flow.
Let's move on to
the next step,
which is looking at the
data, very important.
This is what's going
to give it context.
This is what's going
to ground the agent
and allow it to
essentially provide
these answers in
respecting my company
These are things that are
available in your org.
This is structured data
available in your org,
like budget,
payments, knowledge.
But it can also be
unstructured data
that you decide, for
example, to upload
in a PDF file, perhaps
a specific policy
for a specific
region, for example.
Now this is looking great.
I'm going to move up to
the next step for a recap.
So it has a user,
and that user
you will give it the
access and the permissions
We gave it the agency
to act on our behalf
through topics
and actions.
We hooked it up
to data, and we
decided in which surfaces
we're going to deploy it.
The only thing and the
last part of this wizard
We land in the
Agent Builder.
We love the Agent Builder.
Final step is we're going
to create an agent trigger
so that we can essentially
use the vehicles that
that you are used to
using to invoke processes,
can point to these
agent trigger.
So it's going to auto
suggest here a name
What is it that I want
to pass to this trigger?
I'm actually going to pass
that very travel expense,
and I withhold it
in this record ID.
When do I want my agent
to stop doing the work?
When will it exit
that reasoning loop,
When we have
an expense that
Let's go ahead
and apply this.
Let's activate this
agent, and now it
We're actually
going to invoke it
every time a travel
expense record is created.
Every time my travel
expense record is created,
I'm actually fetching it
using this get element.
I have stored the
record in a variable,
the record ID I
just called it,
and now we're
basically going
to call the invokable
action that we have
created for the agent
that is fetching all
of the parameters that
I previously created
Let's go ahead and
activate our Flow.
And now we can run
this simulation.
This is the travel expense
that I have created.
I have provided
the information.
I have attached the
unstructured data
like receipts
and essentially
the expenditures
that I have had.
And as I submit this,
the reasoning engine
It's going to
start assessing
if it's going to approve
or reject this travel
So let's take a
look at the outcome.
My recent travel expense
has been approved.
And thank you very much
for your attention.
And Thank you, Michael,
our demo driver here
So what you have
seen is something
that only
Agentforce can do.
This is humans
working together
with AI across all
kinds of channels.
The reasoning [INAUDIBLE]
grounded in your data
with Data Cloud,
and policies,
and unstructured data,
and ultimately activated
through Flows, Apex,
MuleSoft, more.
This is what
Agentforce is.
And when are you
going to get it?
It turns out most of the
things you've seen today
are GA-ing in a one
month from now, right.
This is the out-of-the-box
agent, sales agent,
service agent,
marketing, commerce.
This is also the
reasoning engine
And the Builder that
we've been demoing.
We're not stopping there.
In our spring
release in February,
this is where we saw
that really awesome batch
Additionally,
more developments
in advanced search,
multi modality as well.
Image processing
and voice support.
Agentforce is
piloting right now.
And if you can't
wait to get started,
head out to Moscone West
on the second floor.
If you haven't seen
it, it's awesome.
We built 500 agents with
you in 30-minute sessions,
by the way, since we
started yesterday at 8:00
You can get your hands on
this now and launch agents
in just a few minutes that
are personalized to you.
Additionally, while you're
there, stick around.
On the third floor, we
have the MuleSoft platform
or the Keynote,
which is going
to help you integrate
it with all actions
across everything,
and then
the platform, which
is going to take it
to the next level,
building multi
modality and agents
beyond CRM use cases
Last but not
least, thank you.
Can't wait to see
what you build.
Hey, Trailblazers,
Thanks for joining us.