The presentation outlines how leaders can navigate the new era of "high agency" by shifting their mental models and embracing agentic systems, which leverage AI to perform complex, goal-driven tasks with increasing autonomy.
Mind Map
Click to expand
Click to explore the full interactive mind map • Zoom, pan, and navigate
Good morning. Well,
Well,
>> that's great. I love this crowd. Well,
welcome to reinvent in Las Vegas. I'm
excited to be here with you today. Uh,
this is my 13th reinvent. I attended
first six like many of you in this room
as a customer of AWS and this is my
seventh one as a builder here at AWS.
Now, in my role at AWS, I wear dual hat.
I get to lead and build and solve
business problem using technology and AI
and I also get to work with seuite and
executives of some of our largest
customers like yourselves. How many of
you in the room are first time at
reinvent? Show a hand. Well, wow. Many
welcome. Any veterans here? Five plus years.
years.
Excellent. Well, I hope you have a
fantastic week uh because it's an
amazing time to be a senior leader in
the organization. What a privilege that
we all have to become the agent of
change and lead our organizations beyond
just automation to high agency. So in
this session over next 40 minutes or so
I'm going to talk about what do leaders
need to do to lead in this new era of
high agency. What are the mental model
shifts that we require as leadership
team? How do we reinvision our business
processes? and then go slightly deeper
into some of the technical and
architectural capability that help bring
this vision to life. So let's dive in.
Now I'm sure many of you have seen lot
of things being labeled as agents. But
when you peel back that wrapper
underneath that you find many of these
things. You have just good old scripted
automation that takes repetitive
predictable task and in a fixed set of
workflows codes it as you move up that
autonomy chain you have generative AI
assistance and the chat bots that
provide useful information has access to
data can respond to queries uh can
actually summarize the document and
information and has an ability to
respond but very limited ability to act.
As you move up that autonomy chain, we
start to see higher order business task
and the goal that these agents can do.
The goal and taskbased agents are
optimized for completing a specific task
by working with humans.
This is where we start to see lot higher
value. And then at pretty high up is the
highest level of autonomy of agentic
system where multiple agents work
together, take a much higher order
complex and sometimes ambiguous task and
are able to break that down into steps
and pursue that. So this is a good
mental model to think about when your
teams come and talk to you about
automation or AI agents. Now this is not
to say that one is better than the
other. As senior leaders, it is
important that we understand what tool
to apply to solve which problem. So the
question that I really find useful when
I'm talking to my team is to what are
the behaviors or attributes that makes
something an agentic system. So let's
talk about what are some of those behaviors.
behaviors.
Agentic systems are goal- driven. As I
talked about, they take a higher order
goal or an intent and have an ability to
break that into multiple chunk chunks of
tasks to go and complete. They are
resourceful. They have an ability to
access the tools, the data, the context,
the hierarchy and the roles inside of
your organization to take those action.
They remember, they have a memory so
that you don't start again when you have
a new transaction. They remember that
there was an issue with the billing last
time I tried to do something. They learn
and adapt. They get better with the
feedback and they use escalation not
just as a mechanism when something is
wrong but as an inbuilt trust mechanism
to invol human in the loop. So it's good
to keep this framing in mind when you
think about agentic system.
Now you might ask but we've been on this
journey for a couple of years now. So
why now? What has changed? And there are
two fundamental shifts that are
happening very very rapidly that we as
senior leaders need to pay attention to.
The first thing that is happening is
that the unit of task or the length of
task that AI can do is doubling roughly
every seven months or so. So you now can
take lot more complex task and give
agents to go and accomplish those task.
Now as senior leaders we know that just
having a technology or tool that is very
intelligent and highly capable but is
extremely expensive and unaffordable is
not very useful is it? So what is also
happening on the other end is that the
unit price or the cost to access this
intelligence is continuously dropping as well.
well.
MMLU is a standard benchmark massive
multil- language understand massive
multil- language task understanding and
that is used to benchmark language
models and just to give you the context
an MML of 43 is similar to a struggling
high schooler they mostly are guessing
answers but they are very confident
uh I have one at home so I know how that
feels like I'm sure many of you do too u
but MML of 83 is like a PhD level
expert. They understand the nuance. They
are able to deal with ambiguity. And so
we can see that MMLU and the unit price
to access both of this is dropping. So
we are in the sweet spot where the
capability are increasing and the unit
price and the cost is dropping. And this
is why we are starting to see real world
applications of agents.
DUA is a data security company. I'm sure
many of you in this room use them. Now,
when you're dealing with a cyber
security incident, a ransomware attack,
you don't have time to go through like
thousands of pieces of logs and
information manually to sift through
that when you're in middle of the
crisis. And so, Dua worked with AWS to
build Drew AI. These are agents that
don't just respond, but they take
action. They look at proactively the
logs and autonomously detect the system
issues and then they take corrective
action. They move the data around. They
update the policies. They move the data
to a storage that is lot more cost
effective based on the data retention
and the policies that you set driving
lot higher value.
But to take advantage of this requires a
change in how we lead.
If you think about historically
leadership has been mainly about
optimizing for determinism.
We are all rewarded for lowering and
reducing deviation having repeatable
predictable processes that do the same
thing over and over again by reducing
the error rate. And now this works
today. But the non-determinism, the
ability to improvise, the ability to
adapt, the ability to take different
action based on the context and changing
requirement with agent is a feature, not
a bug. Now, I'm sure this might make
some of us nervous, especially from
regulated industries. So, this is not
about just stepping into the wild west.
This is about us as leaders being aware
that the non-determinism is what gives
agents the power and how do we safely
harness this by setting up the right
guardrails. And the mental model that I
find useful is to think about how we
work with some of our high agency teammates.
teammates.
You don't call your high agency teammate
every Monday and say, "Hey, I'm going to
sit down with you to give you specific
tasks that you're going to execute every
single day and then you're going to come
and at the end of the day report to me
what you did, right? We actually give
them a strategic higher order intent. We
give them the boundaries within which
they can operate. We empower them with
the right resources and access that they
need to get the job done. And then we
trust them to escalate to us and involve
us as needed.
And so to lead in this high agency
requires a shift in the leadership model
because we are no longer managing automation.
automation.
We are managing thousands of agents at
scale and that intelligent autonomy and
managing that at scale requires shift
into four key areas of leadership.
Now please keep in mind that the mental
model that I'm going to share are just
mental models. They are not recipes or
strict operating model. So take them
with that lens. And four areas that I'm
going to cover starting with governance.
Now traditionally whether it is in
software or in compliance we have
gatebased governance. system moves,
comes to a complete stop, waits for
someone to verify a series of things via
a checklist that has been defined and
maybe audited couple of times a year.
They approve it, then the system moves
again, stops again at the next toll
gate. Now, this works today, but when
you have hundreds and thousands of
agents, you can't put these toll boots
in front of them consistently. That will
just slow it down.
Instead, the mental model that is useful
is to think about providing that
strategic intent and then having a
policy engine that can govern this at
scale. And as I was thinking about,
well, what governs like this, the the
thing that came to my mind is that if
you look at how board of directors
actually work with the CEO, once again,
they don't go to CEO and say, "I'm going
to tell you exactly how to run your
company every single day." Board and CEO
typically align on a strategic direction
and the vision. Periodically they go and
audit and calibrate but there is also
specific guardrails around what requires
board approval and the the management
team knows when to engage the board. So
it's a useful mental model to think
about governance this way.
The second shift is in risk.
Now today our riskmanagement controls
are pretty much like a factory floor. On
a factory floor you have fixed threshold
right? Even today in many of our
organizations we have fixed threshold
regardless of the exposure of the risk.
So if a purchase order is more than $2
million it requires approval of a vice
president. If it is beyond $10 million
it must go to the CFO. Now these
controls for risk break down when you're
dealing with autonomy at scale. The
mental model that I find useful is to
think about managing the risk like a
trading floor. And on a trading floor,
the risk is actually managed lot more aggressively.
aggressively.
But it is managed through real-time
visibility and control. Traders have a
portfolio that they can uh play the
trades in. Not every move is managed but
if the portfolio or a particular
transaction violates the policy then
there are circuit breakers that stops
the trading. Let's say the portfolio
drops by 20%, the circuit breaker kicks
in and stops the trading. And so we need
to think about agents this way where
agents have to earn their liquidity by
operating within the risk controls and
the boundaries that we design and have
it with real-time visibility and
automation. And it's also not about
managing every single agentic
transaction but also monitoring the
systematic drift in a multi- aent
system. When that happens, you want the
circuit breakers to kick in.
One of the most fundamental change
though is going to be in the
organization structure. And again as
leaders we all know this. Every single
time there has been a major
technological change that has required
us to reimagine and rethink how we organize.
organize.
Before cloud we had application and
development teams and then
infrastructure and technology operation
team. When cloud came these boundaries
got blurred. you started to get full
stack engineering teams that can operate
at all layers of the stack. In fact,
with agents, we are seeing this inside
of our own teams where boundaries beyond
just engineering, including the business
process roles, product management,
engineering, TPMS are all getting
blurred because you have an ability to
execute and work with agents throughout
the entire value chain.
Historically our orc structures are
vertically optimized.
Now this structure provides us stability
but it is not designed to move fast. If
a customer has an issue that gets handed
off sequentially between the department
from customer support to supply chain to
distribution to return and refund and it
slows it down. But the mental model to
use in terms of how you organize for
agents is like an immune system.
How does our body's immune system work?
If there is a threat or if there is a
problem, our white blood cells don't
wait for a memo from the brain, right?
They don't call a meeting with the
lungs. They actually swarm that problem
and then figure out how to solve that.
So the crossf functional teams that are
organized around a business workflow
regardless of the current departmental
structure is how you really get outcome
from agents. The other thing that
happens in this kind of arc structure is
that system learns constantly. So it's
sort of like creating antibodies, right?
So when you have this responsive swarm,
it gets better with period of time.
The last piece
and so before before I go there really
what we need to think about is that
agents should not be limited by your org
chart. They should be limited by the
objective that they are pursuing. That
brings us to the last part of this
leadership mental model and that is
around culture.
Historically we have all optimized the
culture for precision. It's sort of like
well you got to almost hit a bullseye
every single time. That's what we reward
a perfect execution.
But what happens in a research lab-like
culture? That culture is open to new
discovery. Sometimes good, sometimes
bad. But if those mistakes happen, they
are used as a learning mechanism. They
are documented. They are shared widely.
And the new discovery and adaptation is
once again a feature not a bug in this
kind of a culture. And so that's the
shift that we need because what we are
trying to scale is not obedience. We are
actually trying to scale the
intelligence throughout our organization.
organization.
And so the four key leadership mental
model shifts that I talked about,
governance like board of directors that
provide strategic direction, the
continuous calibration and the
guardrail, risk management like a
trading floor where you have real-time
visibility and circuit breakers and then
agents earn their liquidity and
authority to operate by consistently
showing us that they're operating within
those risk controls. the organization
structure that is like an immune system
that is a lot more fluid and responsive
and then finally the culture that is
like a research lab culture that is open
to new discoveries. If you want to read
more you can scan that QR code and and
and dive deeper into some of these
mental models.
Now I want to talk about the business
process and I'm going to pick a business
process that I'm pretty sure most of us
in this room are familiar with uh which
is accounts payable.
Now traditionally the goal of an
accounts payable business process has
been to pay invoices on time and
accurately. And I want all of us to time
travel to preppp days. Right? So just
stay with me here. In the preppp days,
what happened was that an account
payable system had a fixed goal to pay
every invoice on time and uh and
accurately. But the workflows were
vertical. So procurement will process
the PO receiving will confirm the
receipt of the goods. Uh treasury will
make the payment and AP will post the
invoice and so on. The SOPs were all
vertically inside of each of the
department and the function and then
there was sequential handoff that
happened. Now in this kind of a system
if there was any error or an issue it
will manually get kicked back into the
previous process. Somebody will have to
call that department to fix that issue.
How many of you in the room have been
part of an ERP implementation
or or run an ERP? Okay, several of you.
Now, what happened during ERP is that we
could not look at these vertical
processes. We had to re-engineer an AP
process horizontally. We had to connect
the dots between procurement, receiving,
treasury, AP and so on.
that that forced us to talk across
department and function to relay out our
business process. But that there was
still limitation because the goal was
still fixed which was to pay the
invoices on time and accurately and if
there was an issue anytime during the
process it will get kicked back and then
manually you'll have to handle the exception.
exception.
Now what if in an agentic system that I
described earlier we take a lot higher
magnitude goal. What if the goal of AP
is not just to pay invoice on time but
to optimize our cash flow and the system
has the freedom to operate fluidly
within the boundaries that we set. So a
particular invoice will go through all
of the steps, but then a second invoice
comes in and the agents will know that
this invoice is in euro and I have a
60-day payment term on this particular
invoice. That means I'm going to call a
forex trading agent and say, can I
invest this for 59 days and actually
improve my cash flow? or a third invoice
comes in and it recognizes that last
four times I approved this particular
vendor payment. It had to go into
dispute because we did not like the
quality of the deliverable that the
vendor had. And so this time I'm going
to proactively bring human in the loop
and say even though approval processes
have confirmed I'm going to involve the
human and say hey last four times we
didn't like what happened here. Do you
still want me to pay? And so that's a
lot higher order task but also a lot
more fluid workflows that are happening
here. Today though as I was talking
about we are already seeing goal-based
agents being in play. This is where you
have a planning agent or a planner that
takes this higher order task breaks it
into manageable chunk and then you have
orchestrator that works across
individual agents inside of each of the
function like procurement, receiving,
AP, treasury and goods to get to the
payment and and reduce the cycle time.
In fact, we are seeing this in Amazon as
well. I'll give you an example of an
orchestrator within Amazon. In our
warehouses, we have over a million
robots that actually help us safely and
quickly move the packages around. And we
have this orchestrator
called Deep Fleet. Sort of think about
this as a brain of this robotic fleet
that manages these 1 million robots
distributed all over the world across
our warehouses. And by constantly
optimizing that we are able to reduce
the travel time by 10%.
Now 10% may not sound a lot but at our
scale with million robots and multiple
hundreds hundreds of warehouses and
distribution center that means that we
are able to get the packages faster to
you. And so that's an example of an
orchestrator operating at scale
optimizing the business outcome.
Now earlier I talked about the behaviors
of an agentic system. Let's double
click. We we talked about the behaviors.
We talked about the leadership mental
model as well as the business process
changes. Let's double click and say what
are the technical capabilities that
bring these behaviors to life. And there
are three things that agents need. And
again, if you want to geek out a little
bit more in architectural implication,
you can scan this QR code and and read
an article that dives a lot deeper into
the architectural implication in your
environment. But really, agents need
three things. They need intelligence,
they need context, and they need trust.
And and if we were to think of agent as
sort of human body, here is how that
looks like. Uh the intelligence is sort
of like the brain of the agentic system
and your models including your thinking
model for chain of thought reasoning
reflection they provide the brain an
ability to take the intent and break it
into task. But just having a brain is
sort of like having a brain in a jar
right it cannot take any action. So you
then have the access the context which
provides agent an ability to access the
right data. It provides an ability to
actually take action. It provides an
ability to access the tools to go and
make things happen. And that's sort of
like having the the hands to go and do
the work.
But without trust none of this matters.
And so the final layer of this is the
trust. It is sort of like having an ID
badge. What is the agent's identity? Who
are they operating on behalf? What are
their authorizations to execute and do
this task? And then what are the
guardrails that they are going to
operate within to make sure that they
are doing this safely. And so let's
double click on each one of them and say
what are some of the implication in
terms of technical choices that we have
to make. So the first thing is that
agents need intelligence. Now in a in an
ideal world, we would want the most
intelligent agent at the lowest possible
price at the fastest possible speed,
right? We want to optimize on all three
of them. But in real life, based on your
use case, based on the problem that
you're trying to solve, you might not
need all three of these in equal
measure. In fact, there is a trade-off.
So, if you're working with an agent that
is legal agent, you might say, "Hey, you
know what? I cannot compromise on
accuracy and intelligence here. But I'm
okay if it takes half a day or few more
hours or even a day to give me the
response. So, I'm going to optimize for
intelligence, but I'm okay to trade off
on speed of response. On the other hand,
if you're dealing with a customer
service agent, you want fast, quick
responses because your customers are not
going to wait for 10 minutes for agent
to come back with a 100% accurate
answer. And so this is where you
optimize for speed, but then you can
trade off on intelligence or the cost.
And this is why when we are thinking of
enabling the intelligence in the agentic
system, the choice of models, having
access to different types of model is
very important because every model has a
different strength. Some models are good
with reasoning, others are very good
with quick responses. Some do text based
task really well. Others do images and
mathematical task really well. And so
this is why our approach with Amazon
bedrock has been to make the broadest
and the widest set of models available
including open source model, Amazon's
own model with Noah as well as a lot of
third party models and we see this
application inside of Amazon businesses
across our company. Take example of
pharmacy. Now at Amazon Pharmacy, our
goal is to reduce the time it takes to
fill your prescription and do that
accurately. And sometimes the
prescriptions are handwritten notes and
this is where we use models and
intelligence to reduce the time by 90%
while reducing the error rate by 50%.
On the other hand, uh on Amazon ad site,
we want to provide the ability for
brands who want to advertise to take an
image of their product and actually
touch it up and make it better and and
make it a lot more compelling when they
list it. And this is where we optimize
for ability to generate compelling
images on the prime video side. Uh any
any football fans in the house? All
right, some of you. uh if if you're like
me, you always join the game a little
bit late and then you're like what did I
miss and so you have the feature of
rapid recap which is where model is
going and saying here are the key things
or key plays that happened and let me
catch you up as you come in or nextgen
stats which actually provides
lot more probability and information to
the viewer bringing them closer to the
action. All of these use cases require
different behaviors and different models.
models.
Take example of our customer Senta.
Now farming if you think about it is a
is one of the most complex multivaried
problem right a farmer has to take into
account so many different things. What
is the weather condition? What seed to
plant? When do I plant it? Uh what
pesticide to use? How much should I
spray? Do I fertilize or not? When do I
fertilize it? Now, these are just the
factors that are in their control. But
they are all dependent on so many other
external factors. The soil condition,
the moisture, the weather pattern, the
best activity in that particular area.
And this is why Sententa worked with AWS
to develop cropwise AI, a series of
agents that take information from
multiple different data sources
including soil condition, historical
yield, the seed quality, but also 80,000
different growth stages of crop to
provide specific action plan to farmers
on what they need to do when, including
here's the prediction of what might
happen next week and this is what you
should be doing right now increasing the
yield 5%. Now again that is sustainable
but it is also providing a direct
business outcome making it easier for
the farmers. So we talked about
intelligence but as I said just having
intelligence is sort of like having a
brain but not an ability to act. So
let's talk about context. Now context is
sometimes misunderstood as this is all
about just data. But as I'll show you,
context is a lot more than just your
existing data. In fact, there's a
tongue-in-cheek uh statement and by the
way, this is tongue-in-cheek. So take it
with that from a senior scientist at
Amazon that talks about the fact that
like if you think about this, anything
out of an LLM is a hallucination. It is
our job because it's basically
predicting the next token and uh and and
the word but it is our job to provide it
the right context to make sure that that
hallucination is relevant to what we are
trying to solve for. And this is why
there is a growing importance of context
engineering. When we think about just
optimizing the prompt, you're just
providing a one-time input with text.
Now sometimes you give one shot, you
give multiple example but it is still
back and forth with context in your
organization especially when you're
targeting complex workflow you need
agents to understand the role the
hierarchy the data the system the tools
and this is why we are seeing emergence
of context engineering roles in this
competency in many of the organizations.
So to provide this context, let's talk
about what are some of the technical
capabilities that you need. The first
thing is that agents need to understand
the relationships in your data. And take
example of a relationship looks like,
right? Gartner evaluates magic quadrant
and magic quadrant evaluates technology
vendors, right? That's the relationship
between different objects and domain
inside of your data. If you're a
retailer, if you're a media company, if
you are a bank, you have many objects
whether it is customer transaction,
their trade, their viewership behavior
where you need to establish this
relationship so that agents understand
how to navigate your workflows. And this
is why knowledge graph
becomes important in your data strategy.
The second thing that agents need is
that they need to understand semantics
which is the adjacency because
especially around adaptation and
understanding the ambiguity, you're not
always going to have an exact term that
an agent is going to go and search and
look for. This is why they need to
understand what is closer to what other
thing. So in this example, if we were to
envision this in a three-dimensional
space, a cat and dogs both are pets. So
they're closer to each other and Gartner
Magic Quadrant and the leading cloud
providers are are sort of far away from
cats and dog. But if you actually go
into second dimension, cats and dog are
not the same family and so they are
farther apart and the Gartner magic
quadrant is a lot closer to the leading
cloud provider. And this is why the
semantic understanding of your data is
what AI and agents need. And this is
where vector databases come into play
because vector is the language that
agents speak. It provides that you need
to provide them relationship. You need
to provide them the semantics.
But all of this won't matter if you
don't have the memory. And when it comes
to memory, I want to focus on the bottom
right. The four things on the bottom
right. Think about priming. Now priming
is sort of like uh mindset. It's giving
a role to your agent that you are a
financial service uh agent. That means
you're staying in character. You
understand what the role you are
playing. You then have procedural memory
which provides the agent the how. Right?
This is our email system. This is our
ERP. And so they have the ability to
remember who I am, what I'm allowed to
do and where it is. Then you have
semantic. Semantic is sort of like your
word knowledge. So the memory needs to
understand not just all of the knowledge
that is available in the word but also
understand here is my Q3 sales strategy
and then finally the episodic memory so
that agents remember what happened last
time. So hey, you know, this particular
invoice as I shared in the AP example
had issues four times in previous run.
So I better remember to address this
next time when I'm encountering this
problem because if you don't provide
memory to the agent, it is sort of like
having a goldfish, right? It forgets
everything and then you don't get the
outcome. And that creates not only poor
customer experience, it also destroys
some of those behaviors that I talked
about earlier that it needs to get
better. It needs to remember, it needs
to constantly optimize and improve. So
we talked about in the context the
relationship and knowledge graph,
semantics, the vector databases, four
different types of memory that the agent
needs. But lot of us know especially in
large enterprises that lot of our
content is not even in databases. It is
actually in documents
that look like this. Right? And they are
designed typically for all of us as
humans to understand. We know when we
look at this memo to say is a large
bolded test text that looks like a
title. There are section with numbering
and the bullets that means I'm looking
at a list. There's a paragraph and this
break. We know how to read this, but
agents don't. And this is where we need
to focus on taking the content that is
in lot of these documents and convert
that into MD machine readable files that
are friendlier to agent. Here's a
wonderful example from Stripe and you
can read more about it in terms of what
they have published but which is taking
our SOPs, our documents, our workflows,
our orc charts and making into machine
readable agentfriendly documentation
because it's the combination of
structured data memory as well as
content which is going to give the
ability for agents to have this context
and then the final piece of this context
is ability to access the tools and
actually take action.
Now before MCP model context protocol,
those of you who have dealt with lot of
APIs know this that every time when you
don't have a standard protocol, you're
trying to connect to a system, you're
building a point-to-point integration
and that is very very difficult to
scale. What MCP has done is it's sort of
like a USBC port for giving agent an
ability to access lot of your tools and
it allows you to have a standard
interface across your systems, your
tools, your data so that agents have the
context and an ability to access the
tool and the information that they need.
So the combination of these pieces, the
relationship, semantics, memory, better
content and MCP or any other protocol
that actually allows it to access to the
tool allows us to move from data just
being an asset which we have heard many
many times to actually having knowledge
as a capability. Because when we are
leading in intelligent autonomy, we need
an ability for humans and agent to share
the knowledge and be able to share back
that with each other as well. And we see
this that when you provide the context,
the outcomes are amazing. Rufus is
Amazon's shopping assistant. Uh and it
provides personalized contextual advice.
So if you're you know buying something
and say does it need a AAA battery or
double A battery or hey I bought this
other thing uh in the past does it
actually work with the product that I've
already bought. This year alone over 250
million shoppers have used Rufus
throughout the year. And those who use
Rufus are 60% more likely to complete a
purchase. And that happens because Rufus
understands and maintains the context
and provides the useful information to
the customer.
The last piece is the trust because an
intelligent agent that has an ability
and the context but the one that we
cannot trust will never scale in an
enterprise. And one way we can be sure
about the trust is by setting guardrails.
guardrails.
And as part of Amazon Bedrock, we have
we have Amazon Bedrock guardrails which
allow you to set specific guardrails
depending on the industry, your company
policy. For example, uh before I joined
AWS, I was a CTO for a global media and
entertainment company. And that meant
that we could not use certain term uh
during prime time in our show. Now
imagine having to apply this rule agent
by agent throughout the enterprise.
Well, that will not scale, right? But
Amazon Bedrock guardrail allows you to
mention the denied topics to say, "Hey,
never provide financial advice. Do not
mention competitor." And then that
applies to every agentic workflow and
every model that you're using from
bedrock. So you can be confident that
these guardrails are consistently applied.
applied.
Think about the sensitive information
filter, the PII. You don't want that to
be exposed. You can define some of those
rules in the guardrails. Contextual
grounding checks, which provides
information to all of your agents that
are at a policy level to say, you know
what, our return policy is 90 days. You
define it here and every time there's an
interaction, it can and if there's a
conflict, guardrail will make sure that
that is grounded in the policy that you
defined there.
But one particular area that I want to
highlight in the trust is automated
reasoning checks. Now automated
reasoning checks is a search for a
mathematical proof that a function, a
program, an agent did something that it
was supposed to do. Now you're doing
this mathematically.
And I'll give you an example of how this
actually works. So let's say we want to
say how do we know that Pythagorian
theorem is correct?
Well, one way to do this is to try and
draw every symbol, every single
variation of a triangle and then go and
manually measure everything to make sure
that the theorem is correct. But that is
not practical, right? That is not how we
can prove the Pythagorean theorem. The
way we actually establish this is by
having a mathematical proof that this is
correct without having to manually go
and draw and measure every single
variation of a triangle. That is exactly
how automated reasoning works. And as
part of Amazon Bedrock guardrail,
automated reasoning checks are available
that reduce the hallucination by over 99%.
99%.
And even before agentic AI, we've been
using automated reasoning for provable
security across AWS for a number of
years. So S3's public storage and
blocking that or VPC access analyzer
where you can say, hey, does my database
have access to internet? Well, how do
you actually prove that mathematically
so that you have approvable security? We
do this through automated reasoning
check. And that's one of those tools
that allow us to trust the agent and
make sure that we are able to
effectively scale them in our companies.
I'll share an example from Amazon text
and compliance. Now when you're dealing
with text rules and compliance all over
the world, uh you have different
policies, different documents, and again
it's very difficult to do this manually.
And so our text and compliance team
worked with agents to look at 600
different companies around the world
including the text policies and the
rules to do the benchmarking. Now that's
an example where the trust is very
important and you have the provable
security to establish that trust. Now
after looking at all of this when you
start to move agents and operate
multiple agents in production it is
still hard.
It requires you to have better runtime
so that you can isolate each of the
runtime. As I talked about it needs
memory so that it remembers different
types of memory that I mentioned
earlier. uh you need to provide an
identity to that agent so that you know
who is that acting on behalf of and what
it is allowed to do. Uh it needs access
to different tools. It needs a gateway
that it can access information from and
then it needs observability so that you
can validate and audit and feel
confident that it is doing what you want
it to do. Now all of this requires a set
of solid primitives. And if you as
senior leaders, if you go back to like
just basic components of primitives or
the building blocks, if you had compute
and storage, we pretty much can build
many different application. You can
create a website, you can create an ERP,
you can create a CRM with just compute
and storage. We believe that inference
is going to become another building
block of all of the applications that
are going to come out. And this is why
with agent core and Amazon bedrock, we
provide these building blocks and
primitives so that all of the things
that I talked about from identity to
memory to providing access to the tool
across any model across any protocol,
not just the models that are on bedrock.
Agent core allows you to do that so that
you can provide agent memory. You can
manage the agent identity. You can
provide a runtime that you know is
secure and is isolated.
You can provide the gateway that manages
the connection with the other tools. And
this is why we are pretty excited about
what we can build using these primitives.
primitives.
Now, one of the questions we often get
from leaders is what are some good
places to get started? Now, as I talked
about earlier, while this is not automation,
automation,
it is also not full autonomy. It they
are still early days. And so, let's keep
in mind that these are still early days.
And we make sure that we don't think of
agents as a magic wand. In fact, if you
have a predictable
uh workflow with fixed steps uh very
limited tool use, then just basic
automation, some Genai assistant works.
Agents are really good when you want
dynamic tool selection, when you want to
take advantage of that adaptability and
learning, where you want to do pattern
recognition and matching, where you are
looking at things like latency and the
cost implication based on the business
problem that you're trying to solve. And
the three specific areas where we see
the biggest value is in software
development, customer support and
customer care, and the knowledge work.
especially when you are handling
exception loop type processes. Now, how
many of you uh in the room do not have
Well, that was a trick question. Uh
pretty much all of us have technical
debt and that's a wonderful example
where agents can actually help us move
fast because paying off technical debt
locks in lot of our engineering
resources into doing something that must
be done but doesn't always necessarily
give better business outcome or
features. It is sort of like managing
the risk. And here's an example from
Thompson Reuters. They had a lot of net
legacy code that they had to modernize
and they use AWS transform which is our
agentic AI based modernization agent and
they were able to reduce and move that
modernization forex faster that meant
that their product and engineering teams
can actually solve the business problems
rather than just paying off the debt.
And so this is a wonderful example where
agents are already helping us drive
better outcomes. So I would I would I
would look at your businesses and find
areas like that where you can start to
apply the agent. Now none of this
matters if we don't prepare our
organizations with skill and training.
And this is why over last 25 years we
have invested heavily into the training
and certification
to build the competency across not only
the companies but around the countries
across the world. so that we have the
right talent as leaders to take
advantage of this. Lot of this training
is available for free. So I encourage
not only all of you but also encourage
your teams to take advantage of it. One
of my favorite things here is the AWS AI
league. What I've found leading product
and engineering teams for a long time is
that gamification is always a great way
to get people highly engaged. It's a low
friction way. You're making it fun.
people get to learn something and that's
what AWS AI league does where you can
actually host a competitive fun league
inside of your own company. We also, I
believe, announced yesterday that
there's going to be a championship
league with $50,000 price uh where teams
can compete into. And finally, you're
going to need experts and we are here to
help. Uh there is guidance from AWS
experts, many of the folks from our
executive and residence team and other
experts throughout the company. We have
made over hund00 million investment in
AWS generative AI innovation center
where we bring machine learning and AI
experts from all over the company to
work alongside you to help you solve a
business problem. and then AWS
marketplace where you can quickly get
access to some of the pre-built agents
and tools that you can start to deploy
today in your organization.
It is really a fascinating and fantastic
future that is ahead of you and I'm
really excited to see what you all build
together. I hope you have a fantastic
reinvent and rest of the week. Thank you
Click on any text or timestamp to jump to that moment in the video
Share:
Most transcripts ready in under 5 seconds
One-Click Copy125+ LanguagesSearch ContentJump to Timestamps
Paste YouTube URL
Enter any YouTube video link to get the full transcript
Transcript Extraction Form
Most transcripts ready in under 5 seconds
Get Our Chrome Extension
Get transcripts instantly without leaving YouTube. Install our Chrome extension for one-click access to any video's transcript directly on the watch page.
