The generative AI

advantage:
A leader’s guide to using
your data as a differentiator
Contents

A leader’s guide to using your data as a differentiator 3

Generative AI: a brief primer 4
Put data at the center of your generative AI approach 5
Turn data into a differentiator for generative
AI applications 7
Establish a data foundation for generative AI 11
Think beyond technology to create a
competitive advantage 14
Tap into your data in a new way to deliver more value 19
Glossary 20

2
A leader’s guide to
using your data as a
differentiator
The world has been captivated by generative artificial intelligence (gen AI)
and its potential to transform how we communicate, create, and operate.
In large part, the fascination with gen AI has been spurred by consumer-
facing applications, such as ChatGPT and Claude. These groundbreaking
chatbots have revealed an awe-inspiring ability to mimic human creativity
and conversation.

$7T
But the true strength of gen AI goes beyond general-knowledge
chatbots. After the initial surge of enthusiasm in the past couple of years,
organizations are peeling back the layers and learning from their gen AI
pilots. As they scale these solutions, business outcomes are driving the
decision to invest further in gen AI. According to the 2025 Amazon Web
Gen AI could raise the global
Services (AWS) and Harvard Business Review Data Leader Agenda report,
GDP by almost $7 trillion
83 percent of survey respondents said that gen AI is the top (13 percent),
over a 10-year period
a high (37 percent), or a moderate (33 percent) strategic priority—and for
good reason.1 Goldman Sachs predicts gen AI could raise the global gross
domestic product (GDP) by almost $7 trillion and increase productivity
growth by 1.5 percentage points over a 10-year period.2

Given these findings, it is no surprise that business and data leaders

want to move quickly with their own gen AI applications. They want to
know not only how to take the next best step, but also how to gain a
competitive advantage in this emerging space. The key to unlocking the
potential of gen AI is your organization’s own data.

Your data is your differentiator.

1
“Scaling Generative AI for Value: Data Leader Agenda for 2025,” Harvard Business Review Analytic Services report, August 2024
2
“Generative AI could raise global GDP by 7%,” Goldman Sachs, April 2023

3
Generative AI:
a brief primer
At a high level, gen AI can be defined as a type of AI used to produce
new content and ideas. Gen AI applications can, for example, write
stories, generate code, and design digital images. These applications Artificial intelligence
also make it possible to automate cumbersome tasks, such as taking
lengthy documents and condensing them into brief summaries.
Machine learning
While this list is far from exhaustive, we commonly see our
customers use gen AI applications to:

• Improve the customer experience through capabilities such

Neural networks
as chatbots, virtual assistants, intelligent contact centers,
personalization, and content moderation

• Boost employee productivity with conversational search, content Generative

creation, text summarization, and code creation models

• Turbocharge production for all types of creative content, such as

art, music, and animation

• Streamline business operations with intelligent document

processing (IDP), predictive maintenance, quality control and
visual inspection, and data augmentation

Like all AI, gen AI is powered by machine learning (ML) models—very

large models that are pre-trained on massive amounts of data. These
models are commonly referred to as foundation models (FMs).

4
It’s important to note that at its core, an FM leverages the latest advances
in ML. A class of FMs, such as the generative pre-trained transformer (GPT)

32%
models, are commonly referred to as large language models (LLMs) and
are specifically focused on language-based tasks, such as summarization,
text generation, and open-ended Q&A. LLMs are special because they
contain a large number of parameters that make them capable of learning
advanced concepts. of companies are able
to realize tangible and
Put data at the center of your measurable value from data

gen AI approach
We’ve long known that data is a strategic asset to businesses. Yet,
according to an Accenture study, only one in three (32 percent) of
companies are able to realize tangible and measurable value from data—
even after investing in data infrastructure.

Gen AI can help move these numbers in the right direction. It presents an
opportunity for you to tap into your data in a new way and get more value
from it. Gen AI enables you to innovate on top of your data more quickly,
leverage this data in new types of applications, and unlock the value of data
that has traditionally been hard to work with, such as unstructured data.

We’re already seeing some of our customers combine data with gen AI
to improve business outcomes and customer experiences. For instance,
Intuit built Intuit Assist, a new gen AI–powered assistant that uses relevant
contextual datasets spanning small business, consumer finance, and tax
to deliver personalized financial insights to customers. And Smartsheet
implemented Amazon Q, a gen AI assistant, to help improve employee
productivity by consolidating organizational knowledge and providing
employees with instant answers to their questions through natural
language queries (NLQs), freeing up their time to focus on impactful work.

These applications are exciting and represent perhaps just a fraction of

what gen AI can deliver for companies. The ways in which gen AI will
change our world are still coming into focus. You may be grappling with
how to capture this enormous potential when it feels as though we’re
entering uncharted territory. In reality, the path to realizing business value
with gen AI is not much different than it is with any other technology. It
comes down to the strength of your data strategy and how you leverage
your data as a differentiator within that strategy.

5
You may already have a data strategy in place or are just starting to build one. In
either case, there’s never been a better time than now to bring this strategy together
in a way that allows you to turbocharge your business value with gen AI. You have
an unprecedented opportunity to gain a sustainable competitive advantage by
differentiating with your data.

In this whitepaper, we provide business and data leaders with the insights and next
steps for using data to create gen AI applications that are unique to their organizations.
To innovate and compete in this arena, you need to develop a broad data strategy that
includes technology, as well as your business priorities and use cases, your employees,
and your governance guardrails. Taken together, this strategy represents a modern view
of data that helps ensure you can realize business value from your gen AI applications.

We will focus on 3 areas to help you create a

modern data strategy:

1 Turning your data into a differentiator for your generative AI

applications

2 Establishing the right data foundation to unlock the value of

your current data through generative AI

3 Thinking beyond technology to create a competitive

advantage with generative AI

6
Turn data into a
differentiator for
generative AI applications
Your data is the difference between having a generic application and one that knows
your company and customers deeply. Because of this, you will have to determine how
to best use your data to capture and showcase your company’s uniqueness. For most
companies, the starting point for deploying gen AI applications is an out-of-the-box FM.
A small number of companies will choose to build their own FMs to power their gen AI
applications, but that requires extensive computing resources and highly specialized staff.

While FMs are powerful out of the box, they’re generalized by design. They are—as the
name implies—foundational. This means they are not tuned to your business needs
because they can’t access your most recent company data or perform domain-specific
tasks to fulfill user requests. Your own data is key to aligning gen AI applications to your
customer experience, internal knowledge, brand voice, and ethical parameters.

For instance, if you are an online travel agency that wants to provide better travel
recommendations to your customers through a gen AI application, you would likely want
to leverage data that is specific to your individual customers, such as past trips, web
histories, and travel preferences. You would also want to access aggregate data on similar
traveler patterns and trip inventories to create a better recommendation. By using your
own data, you can create a personalized and unique customer experience.

Also, out-of-the-box FMs are widely available, so customizing them with your own data
allows you to differentiate your gen AI applications. Let’s say you are also using an out-
of-the-box FM to draft marketing copy for your online travel agency. Your competitors
may be using the same model to the same effect. These models largely pull from the
same general knowledge pool. So, without customization, you could end up creating
content that is nearly identical your competitors’ and the other way around.

Customization creates a sustainable competitive advantage. You can customize your FM

using a few methods, including fine-tuning and in-context learning.

7
Customer spotlight

2.5s
Food delivery company DoorDash applies Retrieval Augmented
Generation (RAG) to its gen AI to improve self-service and enhance the
experience of its independent contractors (“Dashers”), who submit a
high volume of requests for assistance.
Reduced average response
DoorDash collaborates with AWS to supplement its traditional call
time to 2.5 seconds or less
center with a voice-operated self-service contact center solution. For the
core of its gen AI solution, DoorDash uses Anthropic’s Claude models
and Amazon Bedrock, an AWS service that helps organizations build and
scale gen AI applications quickly and easily.

Using RAG to customize the Claude 3 Haiku model, Amazon Bedrock

enables DoorDash to access a deep, diverse knowledge base with
relevant data from company sources to provide relevant, accurate
responses to Dashers, reducing average response time to 2.5 seconds or
less. DoorDash’s gen AI–powered contact center now fields hundreds of
thousands of calls every day, and users have praised the change.

8
Emerging generative AI data patterns

Training your own model

Training of models on domain-
specific data

Deep domain-specific applications

trained on specific data

Examples: molecular sequences,

programming languages

Model fine-tuning In-context learning

Further training of pre-trained Guide pre-trained models with private
models with domain-specific data domain-specific contextual data

Domain-intensive knowledge agents Virtual agents with limited d

 omain-
specific requirements
Examples: technical support chatbots
Examples: consumer support, billing

Fine-tuning
With an out-of-the-box FM, you must leverage your data to customize the model for your
unique business needs. Fine-tuning is a good option for domain-intensive applications,
such as technical support agents or content creation unique to your business. With
Amazon Bedrock, you can securely customize an FM with your data and use other built-in
tools to build applications that know your business, your data, and your customers.

Imagine a content marketing manager who works at a leading fashion retailer and
needs to develop fresh, targeted ads and campaign copy for an upcoming new line of
handbags. To do this, they provide Amazon Bedrock with a few labeled examples housed
in a data lake on Amazon Simple Storage Service (Amazon S3) of their best-performing
taglines from past campaigns, along with the associated product descriptions. Amazon
Bedrock makes a separate copy of the base model that is accessible only to the customer
for model training. After training, Amazon Bedrock automatically generates effective
social media, display ads, and web copy for the new handbags.

9
In-context learning
FMs are trained at a moment in time. It is not practical to fine-tune them every time
a dataset changes. Once FMs are trained, they’re no longer ingesting new knowledge
or data. They are also unable to locate and access real-time information if they need
additional context to solve a problem.

To make responses more relevant and contextual, you can ground your FM with data
through in-context learning, a technique in which the FM is guided to domain-specific,
contextual data either through prompt engineering or RAG. Many companies will use
RAG as their main method to perform in-context learning. RAG enables your FM to
access your company’s most recent data to provide a more accurate and more relevant
response. Often, RAG uses vector embeddings, which are numerical representations of
words, phrases, or images. Embeddings encode the semantic meaning of the source text
or images so that FMs can more easily find relationships between similar vectors and
improve responses to prompts.

While you can use each of these techniques separately, the combination of fine-tuning and
RAG can help you turn your data into a differentiator for your gen AI applications.

Search relevant Knowledge

information sources

2 Query

Relevant
1 information
3 for
Prompt enhanced
+ context
Query Generated
text 5
response

Prompt
+
4 Query
+
Enhanced
context Large language model endpoint

10
Establish a data foundation
for generative AI
Your data is the key to creating value with gen AI applications. It then
becomes crucial to customizing your models with high-quality, relevant,
readily accessible, and available-to-use data. You meet these benchmarks A data foundation is:
by first having a strong data foundation. This foundation includes a
comprehensive, integrated set of data services for all workloads, use cases, Comprehensive
and types of data and tools to govern that data. The following is a high-
level overview of what this data foundation looks like: Integrated

Comprehensive Secure and governed

For gen AI, you need to store various types of data, including unstructured,
structured, streaming, and vector that can be used for building and
customizing models and adding context to prompts with or without RAG.
A comprehensive set of data services makes it possible to store all of this
data and query and analyze it at scale.

Typically, a comprehensive set of data services for gen AI includes a highly

durable and scalable data lake. This data lake stores the domain-specific
data you need to build and customize your FMs. AWS has been helping
customers build a strong foundation for data lakes to store structured and
unstructured data with services like Amazon S3, AWS Glue, and AWS Lake
Formation for years. Customers use Amazon S3 to create hundreds of
thousands of data lakes.

A data foundation for gen AI also includes high-performance knowledge

stores for RAG. AWS provides several options depending on your use case.
For instance, NoSQL databases store conversation state and history so
a chatbot can remember prior responses. Transactional databases store
context and customer information to create more personalized responses.
You can also use a knowledge store, such as Amazon Kendra, that
connects to multiple structured and unstructured content repositories,
providing a document-based knowledge source for your FMs. Or, you can
use databases that have vector search capabilities specifically designed to
be efficient at storing and retrieving embeddings. Being able to use vector
search within the databases you already use has several advantages. For
instance, it eliminates the steep learning curve for new programming

11
tools, APIs, and SDKs. You can also feel confident knowing that your existing databases
are proven in production and meet requirements for scalability, availability, storage, and
compute. And when your vectors and business data are stored in the same place, your
applications can run faster—there’s no data sync or data movement to worry about. AWS
offers vector search capabilities for many of our popular data stores to give customers
even more flexibility as they build their gen AI applications.

A comprehensive data foundation accounts for both data analytics and data storage. You
can use data warehouses to customize your FMs and use cases that require up-to-date
operational data, such as building an FM or other LLM to provide insights on business
data through NLQs. Amazon Redshift is a fast, petabyte-scale data warehouse delivering
up to six times better price performance than other cloud data warehouses.³ Amazon
Redshift integrates with many of your data sources, including Amazon S3 and Amazon
Aurora, so you can get a more complete look at your data.

“Companies that have not yet found ways to effectively

harmonize and provide ready access to their data will
be unable to fine-tune generative AI to unlock more
of its potentially transformative uses.”
What every CEO should know about generative AI, McKinsey Digital, May 2023

Integrated
Data integration gives you a complete view of your business and ensures your
data is readily accessible for your gen AI applications. With direct integrations between
AWS services, we’re reducing and eliminating the extract, transform, and load (ETL)
process for common use cases so teams can move faster. You can also use AWS Glue, our
serverless and scalable ETL and data integration service that makes it easier to discover,
prepare, move, and integrate data from multiple sources for analytics and ML. AWS
connects to hundreds of data sources, including software as a service (SaaS), on premises,
and other clouds, in addition to third-party data from more than 300 data providers.

3
Amazon Redshift Price Performance
12
Secure and governed
Your data needs to be secure and governed throughout the lifecycle of
building a gen AI application. AWS offers several tools to help ensure
data quality, privacy, and access controls so the data you use for gen AI
applications is high-quality and compliant.

With Amazon Bedrock, all your data is encrypted at rest using your own
key management service (KMS) keys, which provide full control and
visibility into how you store and access your data and custom models.
With AWS PrivateLink, you can pass your data on AWS to Amazon
Bedrock exclusively through the AWS network and never via public
internet. You can privately customize an FM on your own virtual private
cloud (VPC) so no data is ever leaked and no data is ever used to train or
customize a model that would be available to other companies. Amazon
Nova FMs are built to detect and remove harmful content in the data you
want to use for customization, reject inappropriate content in the user
input, and filter the model’s outputs that contain inappropriate content,
such as profanity or hate speech.

Earlier in this whitepaper, we discussed the importance of customizing

your FM to reflect your specific brand and customer experience and
to root out inaccurate or irrelevant content. While customization is
important to address these challenges, so is data governance in the
form of human oversight and feedback. You will need people to ensure
your output reflects how you want the world to perceive your business.
For example, reinforcement learning from the human feedback method
enables you to train an FM to make decisions and act while receiving
guidance from human experts. These experts look for potential
complications, such as bias in the data, data quality issues, and data gaps,
and help align your FM to your brand voice, corporate guidelines, ethics,
and policies.

13
Think beyond technology
to create a competitive
advantage
Technology is a fantastic enabler for gen AI, but it’s only one component
of a strategy to embed data as a strategic asset in your company.
At AWS, we define a data-
At AWS, we take a modern view of data strategy that is more expansive driven organization as:
in nature. An end-to-end data strategy is one that encompasses
technology, in addition to mindset, people, and process. This “An organization
combination paves the way for your company to become data-driven by
weaving data into every aspect of your business and operations.
that harnesses
data as an asset,
Mindset to drive sustained
innovation and create
Mindset refers to the way a company thinks about and treats data. A
company’s mindset is reflected in the beliefs, values, and behaviors that actionable insights
create its data-driven culture with aligned use cases. to supercharge the
Traditionally, leaders have built their data strategies with the mindset experience for their
that data is a platform and a means to build solutions. This viewpoint customers so they
consistently results in a mismatch between IT investment and improved
demand more.”
business outcomes.
Accelerating Business Value
As interest in gen AI grows, we’re seeing more of this type of thinking.
with a Modern Data Strategy,
This trend is understandable, as leaders want to do something with gen AWS, 2023
AI and ensure they can remain competitive. However, first explore how
these applications can help you solve a problem or differentiate your
business. Approach gen AI as an evolving data product that adds value
to your business. In doing so, you put the focus on your customers, not
solutions, and close the critical gap between your data initiatives and
business results.

14
The flywheel approach
We help our customers bring data-driven products to life for their use cases through a
flywheel approach. This approach accelerates the pace by which you identify a high-value
business or customer opportunity and create a data product or experience to address it.
Once the flywheel starts spinning, you continue to identify new use cases to deliver more
products or experiences.

The flywheel speeds transformation and creates incremental value. We summarize it as

“think big, start small, and scale fast” and have illustrated it briefly in the following example:

Next
flywheel
turn
1. Convene 2. Create a
stakeholders production-
to develop ready, high-
a “think velocity
big” vision engagement
for a challenging
business use case

4. Scale with a 3. Build experience

Deliver new 9–12 month activating data
business road map of products while
value priority implementing a
projects cloud-based data
foundation

NatWest Group, one of the largest banks in the United Kingdom, wanted to deploy
personalized solutions at an enterprise scale. During a series of workshops with
AWS, the bank identified areas of improvement within its ML landscape and created a
comprehensive plan for development. The resulting solution was an enterprise-wide,
centralized ML workflow powered by Amazon SageMaker.

The workflow equipped the NatWest data science teams with easier access to data
and ML tools, giving them the space to build numerous ML use cases in just four
months. The use cases included a solution that tailors marketing campaigns to specific
customer segments and an application that automates simple fraud detection tasks so
investigators can focus on difficult, high-value use cases. Using a flywheel approach,
NatWest was able to reduce its time to value and increase its number of use cases.

15
Empower your people
Gen AI—and AI in general—can help your teams move faster and more purposefully
with data. This shift can ultimately lead your company to realize greater efficiency and
productivity and better employee and customer experiences.

For example, Omnicom Group, a leading global marketing and corporate communications
company, uses gen AI and ML services on AWS to help accelerate the transformation
of its advertising campaign development. Omnicom Group will advance its AI-powered
platform, Omni, by creating new FMs that help automate activities such as developing
creative briefs, media plans, ad creative, audience segmentation, and performance
measurement.

Philips uses Amazon Bedrock to accelerate the development of cloud-based gen AI

applications that provide clinical decision support, help enable more accurate diagnoses,
and automate administrative tasks. These new ways of working help simplify radiologists’
workflows and reduce cognitive burden and clinician burnout.

Emerging roles in AI and machine learning

Generative AI Engineer: Specializes in developing and implementing gen

AI models and systems, including designing, training, fine-tuning, and
optimizing models for specific applications

Data Curator: Responsible for sourcing, collecting, and organizing high-

quality datasets that are diverse, representative, and properly labeled

Generative AI Consultant: Provides expert guidance and advice on using

gen AI technologies a
 cross various industries

Generative AI Artist: Explores the creative possibilities of gen AI

technologies to produce unique and innovative art pieces, music
compositions, or visual designs

AI Policy and Regulation Specialist: Shapes policies, guidelines, and

regulations that govern the responsible development, deployment, and
use of gen AI systems

16
Accenture currently uses Amazon Q Developer (previously Amazon
CodeWhisperer), an AI coding companion, to accelerate coding as part of its

30%
software engineering best practices initiative in its Velocity platform. The
Velocity team was able to reduce its development efforts by 30 percent and
is now focusing more on improving security, quality, and performance.

Gen AI can help make it possible for more employees to innovate with The Velocity team was able
data. To prevent roadblocks and bottlenecks, you must make it easier for to reduce its development
them to discover, consume, share, and manage data—with appropriate efforts by 30%
policies. Traditionally, the IT department has held almost complete
control over the dissemination of data in an organization. An end-to-
end data strategy pushes this responsibility to the edges, giving it to the
teams that produce and consume data. The next generation of Amazon
SageMaker brings together virtually all of the components you need for
data exploration, preparation and integration, petabyte-scale big data
processing, fast SQL analytics, model development and training, data
and AI governance, and gen AI development, reducing complexity and
operational overhead.

SageMaker addresses the challenges of harnessing all organizational

data—regardless of where it lives—for analytics and AI through unified
data access and governance. It enables teams to securely find, prepare,
and collaborate on data assets and build analytics and gen AI applications
through a single platform, accelerating the path from data to value.

New skills and roles

Gen AI will open the door for entirely new roles and create greater
demand for existing roles. According to the World Economic Forum’s
Future of Jobs Report 2023, the majority of the fastest-growing roles
are technology-based and include AI and ML specialists, as well as data
analysts, data scientists, and information security analysts.

Currently, however, the talent pool for AI, ML, and cloud expertise is
limited. Companies often lack the skilled and diverse workforce to fully
adopt their data strategies. To ensure you keep moving ahead, you need
to invest in upskilling your current workforce, including those outside of
the IT department in teams such as finance or marketing. Training these
teams to interact with data removes bottlenecks by giving them access to
the right data products at the right time to make business decisions.

Upskilling employees is an important part of your data strategy. These

exercises are an investment but aren’t the heavy lift some leaders may
imagine. Again, thanks to AI and ML, you can more easily equip employees
who have all levels of technical skill with the tools to analyze data,

17
uncover insights, and construct narratives. For example, Amazon Q,
our new gen AI assistant, helps you in Amazon QuickSight to author
dashboards and create compelling visual stories from your dashboard
data using natural language. We also announced that Amazon Q can
help you create data integration pipelines using natural language. For
example, you can ask Amazon Q to “read JSON files from S3, join on
‘accountid’, and load into DynamoDB,” and it will return an end-to-
end data integration job to perform this action. With Amazon Q, data
analysts, scientists, and engineers can also be more productive using gen
AI text-to-SQL functionality in Amazon Redshift to query data in your
data warehouse.

Amazon SageMaker addresses the challenges of harnessing all

organizational data—regardless of where it lives—for AI through unified
data access and governance. It enables teams to securely find, prepare,
and collaborate on data assets and build analytics and gen AI applications
through a single platform, accelerating the path from data to value.

Create new processes or optimize

existing ones to keep up with innovation
Gen AI has brought the phrase responsible AI to the forefront and added
a new dimension to data governance. You must still consider issues not
only of data sharing, security, and privacy but also those related to bias,
ethics, and false information.

In the previous section, we discussed some of the tools that can help
mitigate the common risks associated with gen AI. But, as data leaders
know, data governance is more about strategy than tool selection.
Data governance needs to be architected to support wider data and
AI strategy but implemented incrementally based on use cases and
business priorities.

Data leaders often tell us they find it challenging to show business

value resulting from their data governance initiatives. When they look
more broadly at their data strategy and align it with business priorities,
however, they move closer to showing this value.

A broad data strategy is important because it ensures data governance

policies are in step with organizational structures. To innovate and move
quickly with gen AI, your teams need ready access to data. They also
need to operate within the confines of security, sharing, and privacy
policies. You need to strike a balance between the non-negotiables and
autonomy and speed. You can achieve this balance when you view data
governance as an enabler of your broader data strategy.

18
Tap into your data in
a new way to deliver
more value
We’re just beginning to uncover the possibilities for gen AI but we can already
sense how it will transform nearly every application, industry, and company. Gen
AI offers fresh and exciting ways to tap into your existing data and gain more
value from it. It can enable you to unlock new data products and experiences
that delight your customers and set your brand apart.

We know that nearly every leader wants to explore the potential of gen AI, and
we also know that your next steps will be critical. Rather than use a generic
application, focus on what makes your company unique and use it to guide your
decision making. That uniqueness exists within your data. And to fully use your
data as a strategic asset, you need to create a data strategy that encompasses
not just your technology but also your mindset, people, and process. Each layer
of this strategy firmly cements your data as a differentiator for how you build
and customize your gen AI applications and how you empower your entire
organization to innovate.

Learn more about building a data foundation to

gain a competitive advantage with gen AI

19
Glossary
Generative AI is a type of AI that can create new content like text, code, images,
and video using patterns it has learned by training on extensive public data with ML
techniques.

Foundation models (FMs) are deep learning models trained on vast quantities of
unstructured, unlabeled data that can be used for a wide range of tasks out of the box
or adapted to specific tasks through customization.

Large language models (LLMs) make up a class of FMs that can process massive
amounts of unstructured text and learn the relationships between words or portions of
words. This enables LLMs to generate natural language text, performing tasks such as
summarization or knowledge extraction.

Retrieval Augmented Generation (RAG) is the process of increasing the contextual

knowledge of LLMs and reducing factual errors or hallucinations by enabling prompts
to be augmented with context and domain-specific data, such as through vector
databases.

Customization is the process of adapting a pre-trained FM to perform better on a

specific task via a short period of training on a smaller labeled dataset. This additional
training allows the model to learn and adapt to the nuances, terminology, and specific
patterns found in the smaller dataset.

Prompt engineering refers to the process of designing, refining, and optimizing input
prompts to guide an FM toward producing desired (that is, accurate) outputs.

©️ 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. 20