C_CPE_2409: SAP Cloud Application Programming Model MCQ Questions for Practice

1 of 60

Which CAP feature allows real-time data synchronization and communication between different parts of an application or with external systems?

- Database Connectivity

- Service Extensibility

- Service Connectivity

- Message Queues and Event Brokers ✔

2 of 60

What are some of the capabilities of the SAP S/4HANA Virtual Data Model? Note: There are 2 correct answers to this question.

- It documents the relationships between entities ✔

- It provides a native UI to query the database tables

- It allows direct access to underlying database tables

- It enriches the entities with business semantics ✔

3 of 60

You have set up the scopes and attributes that are needed to protect your application in the Cloud Foundry environment, but a user is unable to access your application. What might be the reason?

- Role collections aren't assigned to the client application

- Roles aren't assigned to the client application

- Roles aren't assigned to the user ✔

- Role collections aren't assigned to the user

4 of 60

What are scopes in the context of SAP BTP XSUAA?

- Values that express authorizations or access rights ✔

- Entities that aggregate technical roles

- Collections of user credentials

- SAP BTP subaccounts

5 of 60

What is the function of the service metadata document in an OData service?

- To specify the API's security requirements

- To describe the types, sets, functions, and actions ✔

- To list the available entity sets, functions, and singletons

- To provide a human-readable description of the data model

6 of 60

Which open-source tools can be integrated with SAP BTP for enhanced observability? Note: There are 2 correct answers to this question.

- Logstash ✔

- Jenkins

- Terraform

- Prometheus ✔

7 of 60

Which configuration files are updated when you run the command cds add xsuaa'? Note: There are 2 correct answers to this question.

- xs-usertokens.json

- xs-security.json ✔

- Package.json ✔

- Cdsrc.json

8 of 60

What is the purpose of the SAP BTP, Cloud Foundry runtime?

- To manage SAP HANA databases

- To manage API integrations between SAP S/4HANA and legacy systems

- To provide an environment for developing and deploying cloud-native applications ✔

- To configure SAP S/4HANA systems

9 of 60

What features does the SAP Cloud SDK provide as part of Enterprise-specific adaptations of open source frameworks? Note: There are 2 correct answers to this question.

- Code samples

- Multi-tenant persistence ✔

- Feature toggling ✔

- Tightly coupled integration

10 of 60

Which services in SAP BTP can be used to store and retrieve technical information about target external systems?

- Destination Service ✔

- Core Data Service

- Connectivity Service

11 of 60

To consume a service from an on-premise system with CAP, which of the following must be configured?

- Event Mesh

- OAPI Management

- Destination Service

- Cloud Connector ✔

12 of 60

Why are extensions on top of SAP S/4HANA Cloud NOT affected by the quarterly update cycle of SAP S/4HANA Cloud?

- The Virtual Data Model of SAP S/4HANA Cloud remains unchanged.

- SAP provides maintenance agreements to fix any extension issues.

- The public interfaces of SAP S/4HANA represent a stable contract across the versions of SAP S/4HANA Cloud ✔

- The extension application runs only on SAP Business Technology Platform.

13 of 60

What is the primary function of kubectl?

- To set up cloud environments

- To configure storage systems

- To create virtual networks

- To interact with the Kubernetes API to manage cluster resources ✔

14 of 60

Which of the following tools are required to build Spring Boot applications using the SAP Cloud SDK? Note: There are 2 correct answers to this question.

- SAP Mobile Services (MDK)

- Apache Maven version 3.5 or above ✔

- Java SE Development Kit 8 ✔

- Spring Initializr

15 of 60

What are Kubernetes deployments used for?

- To manage Pods directly

- To roll out application updates with zero downtime ✔

- To configure network policies

- To create databases

16 of 60

Which entity in XSUAA holds several scopes?

- Role ✔

- User group

- Scope

- Role collection

17 of 60

You develop an application using the Cloud Foundry environment. What are some steps to restrict access to this application? Note: There are 2 correct answers to this question.

- Set the Scopes element to the required scope name in the xs-security.json file ✔

- Set the role-name attribute of the Security-role element in the web.xml file to the required role template name

- Set the Scopes element to the required scope name in the xs-app.json file

- Define the role template name in the role-templates element of the xs-security.json file ✔

18 of 60

What are the benefits of using Side-by-Side Extensibility? Note: There are 3 correct answers to this question.

- It provides support for hybrid scenarios ✔

- It can be implemented in the same software stack as the extended application

- It uses a complete development platform for creating extension applications ✔

- It uses In-App tools to adapt the standard UI

- It integrates with other cloud/non-cloud solutions when using SAP Business Technology Platform Integration services ✔

19 of 60

When creating a CI/CD job, what does defining Source Control Management (SCM) credentials enable?

- Retrieving your project from SCM when its build is triggered ✔

- Modifying your project source code automatically

- Managing your SCM credentials

20 of 60

Which of the following can you use to define external service APIs in CAP? Note: There are 2 correct answers to this question.

- OpenAPI (Swagger) ✔

- GraphQL schema

- EDMX for OData V2 and V4 ✔

- WSDL

21 of 60

In the context of a CAP application, what is one of the actions of the cds build command?

- To deploy the application to SAP BTP

- To create Docker images

- To compile the application ✔

- To execute test cases

22 of 60

Which command is used to create a Pod in Kubernetes from a YAML file?

- kubectl apply ✔

- kubectl get pod

- kubectl run <file>.yaml

- kubectl create -f ✔

23 of 60

What is the purpose of the .env file in a CAP project?

- To store values for runtime environment variables ✔

- To manage version control settings

- To specify UI component settings

24 of 60

What is the role of SAP Gardener in SAP BTP, Kyma runtime?

- It is a subaccount manager and deploys instances on the hyperscaler of your choice

- It manages Kubernetes clusters across various cloud providers ✔

- It is responsible for deploying SAP applications

25 of 60

When you create a CI/CD job for a low-code project, which options are available in the Release stage? Note: There are 2 correct answers to this question.

- Deploy to Private Server

- Deploy to Cloud Foundry ✔

- Deploy to Cloud Transport Management Service ✔

- Upload to FTP server

26 of 60

In SAP BTP, Cloud Foundry, what is the function of an organization?

- To define specific API endpoints for applications

- To manage users and spaces under a common resource pool ✔

- To allocate memory for applications

- To deploy applications

27 of 60

What is the role of a buildpack in Cloud Foundry?

- It acts as a database manager for applications.

- It binds services to applications.

- It builds a container image for applications during staging ✔

- It builds user roles and permissions.

28 of 60

What are some scenarios where you would use the SAP Cloud SDK in your application? Note: There are 2 correct answers to this question.

- You want to allow key users to create fields

- You want to build extensions using .NET

- You need advanced features in your app such as resilience and caching ✔

- You want to add new features to an existing Java application ✔

29 of 60

What are namespaces used for in CAP data models? Note: There are 2 correct answers to this question.

- To provide additional styling options

- To enhance data retrieval performance

- To manage version control

- To group related entities and types ✔

30 of 60

Which file is used to define the structure and components of a multitarget application (MTA) in SAP BTP?

- mtad.yaml

- mta.json

- manifest.json

- mta.yaml ✔

31 of 60

Out of the box, which of the following can CAP applications use to interact with external APIs and services? Note: There are 2 correct answers to this question.

- REST ✔

- OData ✔

- SOAP

- WebSockets

32 of 60

How do you run a CI/CD build manually without pushing changes to Git?

- Create and run "Build task" in Task Explorer

- Select 'Trigger a Build' in the CI/CD job's context menu ✔

- Select Deploy from the project's context menu in the Project Explorer

- Submit Changes via Sync & Share action

33 of 60

For local development in the SAP Cloud Application Programming Model, which database option is recommended?

- PostgreSQL

- SQLite ✔

- NoSQL

- SAP HANA Cloud

34 of 60

Which file includes by default the configuration for an external OData service in a Node.js CAP project?

- Manifest.json

- Index.js

- Package.json

- service.cds ✔

35 of 60

What are typical components of a Kubernetes worker node? Note: There are 3 correct answers to this question.

- etcd

- kube-proxy ✔

- service-mesh

- Container Runtime ✔

- kubelet ✔

36 of 60

Which of the following are benefits of SAP BTP, Cloud Foundry runtime? Note: There are 2 correct answers to this question.

- Managed security and automatic updates ✔

- Managed service mesh

- High availability with load balancing ✔

- Manual infrastructure scaling

37 of 60

In CAP, what is required to connect a service to the sandbox environment of the SAP API Business Hub for the Business Partner service?

- Service principal

- Client certificate

- Auth token

- API key ✔

38 of 60

Which of the following can be used to implement side-by-side extensions in the Cloud Foundry environment of SAP Business Technology Platform? Note: There are 2 correct answers to this question.

- ABAP

- Java ✔

- ActionScript

- Node.js ✔

39 of 60

Which command is used to set the API endpoint in the Cloud Foundry CLI?

- cftarget

- cf api ✔

- cf endpoint

- cf login

40 of 60

What are some purposes of OData in CAP-based applications? Note: There are 2 correct answers to this question.

- To define request and response headers, status codes

- To create user interfaces for applications

- To perform CRUD operations using HTTP verbs ✔

- To provide real-time analytics

41 of 60

In CAP, which file is used to define destinations for connecting to external services? Note: There are 2 correct answers to this question.

- Destinations.json ✔

- Package.json

- Services.xml

- manifest.json ✔

42 of 60

Into which environment does the Test step in a job allow you to deploy your application?

- Cloud Foundry ✔

- Local workspace

- Private server

- Mobile Services

43 of 60

Which HTTP method is used by OData to partially update an existing resource?

- POST

- PATCH ✔

- PUT

44 of 60

How can developers deploy a multitarget application (MTA) in SAP BTP, Cloud Foundry? Note: There are 2 correct answers to this question.

- By using the Cloud Foundry CLI with cf push directly ✔

- By manually creating and deploying the mta.yaml file

- By using SAP HANA Cloud tools

- By using SAP Business Application Studio ✔

45 of 60

What are Kubernetes pods? Note: There are 2 correct answers to this question.

- A thin wrapper for one or more container ✔

- A smallest manageable unit ✔

- A thin wrapper for one container

- A persistent storage system that containers can share across nodes.

46 of 60

Which metrics are provided out-of-the-box by the @cap-js/telemetry tool? Note: There are 2 correct answers to this question.

- Database pool statistics ✔

- Network latency and jitter

- Memory usage metrics ✔

- CPU allocation and thread management

47 of 60

What is Kubernetes commonly used for?

- To manage operating systems

- To develop web applications directly

- To manage application deployment and scaling ✔

- To create virtual machines

48 of 60

What is the prerequisite before you can create a CI/CD job for a project?

- The project has been shared to a remote Git repository ✔

- The project has been previewed

- The project has been deployed

49 of 60

Which of the following modules are available in Kyma project? Note: There are 3 correct answers to this question.

- Storage

- API Gateway ✔

- Data Warehouse

- Themetry ✔

- Serverless ✔

50 of 60

You use the Nest Framework and Visual Studio Code to develop an extension application. Which activities can you perform in the development environment? Note: There are 2 correct answers to this question.

- Run the Java program and make it stop at breakpoints

- Automatic re-deploy of a JavaScript program when the source code is modified ✔

- Run the JavaScript program and make it stop at breakpoints ✔

- Automatic re-build of a TypeScript program when the source code is modified

51 of 60

Which of the following are benefits of using the OData Virtual Data Model of the SAP Cloud SDK? Note: There are 3 correct answers to this question.

- Database procedures provided out of the box

- Commonly used SQL query technology

- Auto-completion of function names and properties ✔

- Type safety for functions ✔

- Easy access to create, update, and delete operations ✔

52 of 60

What is the benefit of using SAP BTP, Kyma runtime instead of a standard Kubernetes cluster?

- Unlimited number of nodes

- Elimination of infrastructure management ✔

- Support of machine learning pipelines

- Automatic migration of workloads

53 of 60

You need to secure your application in the Cloud Foundry environment. Which file do you maintain routes during design time?

- xs-app.json ✔

- mta.yaml

- xs-security.json

- manifest.yml

54 of 60

Which of the following describe a multitenant application in Cloud Foundry? Note: There are 2 correct answers to this question.

- It stores data on the local file system of each instance

- It provides automatic scaling based on tenant requirements

- It allows multiple consumers to access the application via unique URLs ✔

- It uses shared memory for tenant-specific data

55 of 60

Which of the following are use cases for SAP Business Technology Platform? Note: There are 3 correct answers to this question.

- Supports only Cloud scenarios with seamless interoperability with hyperscalers

- Build innovative digital apps ✔

- Build tightly coupled applications

- Extend cloud and on-premise apps ✔

- Integrate apps, data, and processes ✔

56 of 60

Why should you use SAP Fiori annotations in CAP projects?

- To enable automatic database schema migration

- To facilitate real-time data synchronization

- To improve frontend loading time

- To enrich the service with UI-specific instructions ✔

57 of 60

What is the Kyma project primarily designed to do?

- To manage virtual machines

- To develop standalone applications

- To extend Kubernetes with additional tools and features ✔

- To replace Kubernetes as a container management system

58 of 60

To expose a data model to an application, which of the following must be defined?

- Aspects

- Associations

- Data model entity

- Service model entities ✔

59 of 60

Which of the following can you use to configure authorization and trust management in a CAP project? Note: There are 2 correct answers to this question.

- XSUAA service ✔

- SAP Cloud Identity Services ✔

- Role collections in mta.yaml

- Predefined roles in SAP BTP

60 of 60

In which type of system environments do the side-by-side extensions typically run? Note: There are 2 correct answers to this question.

- Centralized

- Distributed ✔

- Heterogenic ✔

- Autonomous

AI Validation ( 2 may be incorrect )

29 of 60
✔ D. To group related entities and types
⚠️ C. To manage version control — This is not a primary purpose of namespaces in CAP
❌ One answer is incorrect

54 of 60
✔ C. It allows multiple consumers to access the application via unique URLs
✅ Correct
❌ B. It provides automatic scaling based on tenant requirements — This is not a guaranteed feature of multitenancy in Cloud Foundry.

C_AIG_2412 SAP Certified Associate - SAP Generative AI Developer Sample Questions

C_AIG_2412 SAP Certified Associate - SAP Generative AI Developer

Questions and Answers

Question 1

Match the components of a Retrieval Augmented Generation architecture to the diagram.

• (✗) Box - Models- Vector Database   Box-> Applications- Backend and Frontend   Box-> Retrieval- Embedding Model and LLM
• (✗) Box - Models- Embedding Model and LLM   Box-> Applications- Vector Database   Box- Retrieval- Backend and Frontend
• (✗) Box - Models- Backend and Frontend   Box-> Applications- Embedding Model and LLM   Box-> Retrieval- Vector Database
• (✓) Box - Models- Embedding Model and LLM   Box- Applications- Backend and Frontend   Box- Retrieval- Vector Database

Question 2

Which of the following steps must be performed to deploy LLMs in the generative Al hub?

• (✗) 1. Provision SAP Al   2. Core Create a configuration   3. Run the booster
• (✗) 1. Run the booster   2. Create service keys   3. Select the executable ID
• (✓) 1. Provision SAP Al Core   2. Check for foundation model scenario   3. Create a configuration   4. Create a deployment
• (✗) 1. Check for foundation model scenario   2. Create a deployment   3. Configuring entitlements

Question 3

You want to extract useful information from customer emails to augment existing applications in your company. How can you use generative-ai-hub-sdk in this context?

• (✗) Generate random email content and send them to customers.
• (✓) Generate JSON strings based on extracted information.
• (✗) Generate a new SAP application based on the mail data.
• (✗) Train custom models based on the mail data.

Question 4

What are some benefits of the SAP Al Launchpad? Note: There are 2 correct answers to this question.

• [✓] Centralized Al lifecycle management for all Al scenarios.
• [✗] Direct deployment of Al models to SAP HANA.
• [✗] Integration with non-SAP platforms like Azure and AWS.
• [✓] Simplified model retraining and performance improvement.

Question 5

Why would a user include formatting instructions within a prompt?

• (✗) To increase the faithfulness of the output
• (✗) To force the model to separate relevant and irrelevant output
• (✗) To redirect the output to another software program
• (✓) To ensure the model's response follows a desired structure or style

Question 6

Where can you configure language models in generative Al hub?

• (✗) The Configuration tab of the SAP BTP cockpit
• (✗) The Orchestration tab in SAP AI Launchpad
• (✓) The Configuration tab within ML Operations in SAP AI Launchpad
• (✗) The Models tab in Prompt Editor

Question 7

Which of the following are features of the SAP Al Foundation? Note: There are 2 correct answers to this question.

• [✓] Al runtimes and lifecycle management
• [✓] Ready-to-use Al services
• [✗] Joule integration in SAP SuccessFactors
• [✗] Open source Al model repository

Question 8

How does SAP deal with vulnerability risks created by generative Al? Note: There are 2 correct answers to this question.

• [✓] By implementing responsible Al use guidelines and strong product security standards.
• [✗] By relying on external vendors to manage security threats.
• [✓] By identifying human, technical, and exfiltration risks through an Al Security Taskforce.
• [✗] By focusing on technological advancement only.

Question 9

What contract type does SAP offer for Al ecosystem partner solutions?

• (✗) Annual subscription-only contracts
• (✗) Pay-as-you-go for each partner service
• (✓) All-in-one contracts, with services that are contracted through SAP
• (✗) Bring Your Own License (BYOL) for embedded partner solution

Question 10

How does the Al API support SAP Al scenarios? Note: There are 2 correct answers to this question.

• [✓] By integrating Al services into business applications
• [✓] By providing a unified framework for operating Al services
• [✗] By managing Kubernetes clusters automatically
• [✗] By integrating Al models into third-party platforms like AWS

Question 11

Which of the following steps is NOT a requirement to use the Orchestration service?

• (✗) Create a deployment for orchestration
• (✗) Create an instance of an Al model
• (✓) Modify the underlying Al models
• (✗) Get an auth token for orchestration

Question 12

What is a significant risk associated with using LLMs?

• (✗) Immediate accuracy without fine-tuning.
• (✗) Lack of scalability in business applications.
• (✗) Reduced computational requirements.
• (✓) Potential biases in generated content.

Question 13

What are some benefits of using an SDK for evaluating prompts within the context of generative AI? Note: There are 3 correct answers to this question.

• [✓] Creating custom evaluators that meet specific business needs
• [✓] Automating prompt testing across various scenarios
• [✓] Providing metrics to quantitatively assess response quality
• [✗] Supporting low code evaluations using graphical user interface
• [✗] Maintaining data privacy by using data masking techniques

Question 14

Which of the following statements accurately describe the RAG process? Note: There are 2 correct answers to this question.

• [✓] The retrieved content is combined with the LLM's capabilities to generate a response.
• [✓] The user's question is used to search a knowledge base or a set of documents.
• [✗] The embedding model stores the generated answers for future reference.
• [✗] The LLM directly answers the user's question without accessing external information.

Question 15

You want to use the orchestration service through SAP's generative-Al-hub-sdk. What does the following code do?

python

from gen_ai_hub.orchestration.models.11m import LLM 

llm = LLM(name="gpt-40", version="latest", parameters={"max_tokens": 256, "temperature": 0.2})

• (✗) Create the Orchestration Configuration
• (✓) Define the LLM
• (✗) Define the Template and Default Input Values
• (✗) Run the Orchestration Request

Question 16

What are some advantages of using agents in training models? Note: There are 2 correct answers to this question.

• [✗] To eliminate the need for human oversight
• [✓] To streamline LLM workflows
• [✓] To improve the quality of results
• [✗] To guarantee accurate decision making in complex scenarios

Question 17

What is the primary function of the generative Al hub in SAP's Al Foundation?

• (✗) To provide ready-to-use Al services for document processing
• (✗) To serve as an abstraction layer to access a range of foundation Al models
• (✗) To store embeddings of unstructured data for semantic data retrieval
• (✓) To manage the Al lifecycle efforts end-to-end

Question 18

What does the Prompt Management feature of the SAP Al Iaunchpad allow users to do?

• (✗) Create and edit prompts
• (✗) Provide personalized user interactions
• (✗) Interact with models through a conversational interface
• (✓) Access and manage saved prompts and their versions

Question 19

Which statement best describes the Chain-of-Thought (COT) prompting technique?

• (✗) Writing a series of connected prompts creating a chain of related information.
• (✗) Linking multiple Al models in sequence, where each model's output becomes the input for the next model in the chain.
• (✗) Connecting related concepts by having the LLM generate chains of ideas.
• (✓) Concatenating multiple related prompts to form a chain, guiding the model through sequential reasoning steps.

Question 20

How do resource groups in SAP Al Core improve the management of machine learning workloads? Note: There are 2 correct answers to this question.

• [✗] They enable simultaneous orchestration of Kubernetes clusters.
• [✓] They ensure workload separation for different tenants or departments.
• [✗] They enhance pipeline execution speeds through workload distribution.
• [✓] They provide isolation for datasets and Al artifacts.

Question 21

Which of the following describes Large Language Models (LLMs)?

• (✓) They utilize deep learning to process and generate human-like text.
• (✗) They are rule-based systems designed for specific tasks.
• (✗) They cannot process large datasets efficiently.
• (✗) They rely on predefined scripts for decision-making.

Question 22

How does SAP ensure the enterprise-readiness of its Al solutions?

• (✗) By using generic Al models without business context complying with Al ethics standards
• (✗) By ensuring that Al models make bias-free decisions without human input
• (✓) By implementing rigorous product standards for Al capabilities

Question 23

Which of the following are functionalities provided by the generative-Al-hub-SDK? Note: There are 2 correct answers to this question.

• [✓] Create chat responses and embeddings
• [✓] Interact with LLMs
• [✗] Configure SAP BTP credentials
• [✗] Customize SAP Al Launchpad

Question 24

What is one primary benefit of using LLMs in business applications?

• (✗) They eliminate the need for data security measures.
• (✓) They enhance automation and scalability of processes.
• (✗) They are only applicable for customer support scenarios.
• (✗) They require minimal computing power for training.

Question 25

Which of the following must you do before connecting to a dataset in order to train a machine learning model in SAP Al Core? Note: There are 2 correct answers to this question.

• [✗] Store the dataset in the SAP HANA Vector Engine.
• [✗] Grant access rights to the SAP BTP cockpit.
• [✓] Store the dataset in a hyperscaler object store.
• [✓] Provide the storage secret to access the dataset.

Question 26

Which of the following capabilities does the generative Al hub provide to developers? Note: There are 2 correct answers to this question.

• [✗] Code generation to extend SAP BTP applications
• [✓] Tools for prompt engineering and experimentation
• [✗] Proprietary LLMs exclusively
• [✓] Integration of foundation models into applications

Question 27

What can be done once the training of a machine learning model has been completed in SAP Al Core? Note: There are 2 correct answers to this question.

• [✓] The model can be deployed for inferencing.
• [✗] The model can be deployed in SAP HANA.
• [✓] The model can be registered in the hyperscaler object store.
• [✗] The model's accuracy can be optimized directly in SAP HANA.

Question 28

Which of the following sequence of steps does SAP recommend you use to solve a business problem using generative Al hub?

• (✓) 1. Create a basic prompt in SAP Al Launchpad   2. Scale the solution using generative-ai-hub-sdk   3. Create a baseline evaluation method for the simple prompt   4. Enhance the prompts   5. Evaluate various models for the problem using generative-ai-hub-sdk
• (✗) 1. Create a basic prompt in SAP AI Launchpad   2. Evaluate various models for the problem using generative-ai-hub-sdk   3. Scale the solution using generative-ai-hub-sdk   4. Create a baseline evaluation method for the simple prompt   5. Enhance the prompts.
• (✗) 1. Create a basic prompt in SAP Al Launchpad   2. Enhance the prompts   3. Create a baseline evaluation method for the simple prompt   4. Evaluate various models for the problem using generative-ai-hulb-sdk   5. Scale the solution using generative-ai-hulb-sdk

Question 29

What is Machine Learning (ML)?

• (✗) A technology that equips machines with human-like capabilities such as problem-solving, visual perception, and decision-making.
• (✓) A subset of Al that focuses on enabling computer systems to learn and improve from experience or data.
• (✗) A form of Al that only focuses on creating new content, including text, images, sound, and videos.
• (✗) A statistical method for data processing that does not involve any Al techniques.

Question 30

What must be defined in an executable to train a machine learning model using SAP Al Core? Note: There are 2 correct answers to this question.

• [✓] Infrastructure resources such as CPUs or GPUs
• [✓] Pipeline containers to be used
• [✗] Deployment templates for SAP Al Launchpad
• [✗] User scripts to manually execute pipeline steps

Question 31

Which of the following is a principle of effective prompt engineering?

• (✗) Combine multiple complex tasks into a single prompt.
• (✓) Use precise language and providing detailed context in prompts.
• (✗) Write vague and open-ended instructions to encourage creativity.
• (✗) Keep prompts as short as possible to avoid confusion.

Question 32

Why is generative Al gaining significant attention and investment in the current business landscape? Note: There are 2 correct answers to this question.

• [✓] It only requires natural language skills to use.
• [✗] It can run entire business operations without human intervention.
• [✓] It lowers barriers to adoption.
• [✗] It can replicate complex technical skills without training or quality control.

Question 33

Which of the following are grounding principles included in SAP's Al Ethics framework? Note: There are 3 correct answers to this question.

• [✓] Human agency and oversight
• [✗] Maximize business profits
• [✗] Store all user data for legal proceedings
• [✓] Avoid bias and discrimination
• [✓] Transparency and explainability

Question 34

What advantage can you gain by leveraging different models from multiple providers through the SAP's generative Al hub?

• (✓) Enhance the accuracy and relevance of Al applications that use SAP's data assets
• (✗) Design new product interfaces for SAP application
• (✗) Get more training data for new models
• (✗) Train new models using SAP and non-SAP data

Question 35

Which of the following techniques uses a prompt to generate or complete subsequent prompts (streamlining the prompt development process), and to effectively guide Al model responses?

• (✗) Chain-of-thought prompting
• (✗) Few-shot prompting
• (✗) One-shot prompting
• (✓) Meta prompting

Question 36

What is a Large Language Model (LLM)?

• (✗) A rule-based expert system to analyze and generate grammatically correct sentences.
• (✗) A gradient boosted decision tree algorithm for predicting text.
• (✓) An Al model that specializes in processing, understanding, and generating human language.
• (✗) A database system optimized for storing large volumes of textual data.

Question 37

Which of the following executables in generative Al hub works with Anthropic models?

• (✗) Azure OpenAl Service
• (✗) GCP Vertex Al
• (✓) AWS Bedrock
• (✗) SAP Al Core

Question 38

What are the applications of generative Al that go beyond traditional chatbot applications? Note: There are 2 correct answers to this question.

• [✓] To produce outputs based on software input.
• [✓] To interpret human instructions and control software systems always producing output for human consumption.
• [✗] To follow a specific schema - human input, Al processing, and output for human consumption.
• [✗] To interpret human instructions and control software systems without necessarily producing output for human consumption.

Question 39

What is the purpose of splitting documents into smaller overlapping chunks in a RAG system?

• (✓) To enable the matching of different relevant passages to user queries
• (✗) To reduce the storage space required for the vector database
• (✗) To simplify the process of training the embedding model
• (✗) To improve the efficiency of encoding queries into vector representations

Question 40

What are some use cases for fine-tuning of a model? Note: There are 2 correct answers to this question.

• [✓] To sanitize model outputs
• [✗] To introduce new knowledge to a model in a resource-efficient way
• [✗] To quickly create iterations on a new use case
• [✓] To customize outputs for specific types of inputs

Question 41

How can few-shot learning enhance LLM performance?

• (✗) By reducing overfitting through regularization techniques
• (✗) By providing a large training set to improve generalization
• (✓) By offering input-output pairs that exemplify the desired behavior
• (✗) By enhancing the model's computational efficiency

Question 42

What is the primary function of the embedding model in a RAG system?

• (✓) To encode queries and documents into vector representations for comparison
• (✗) To store vector representations of documents and search for relevant passages
• (✗) To generate responses based on retrieved documents and user queries
• (✗) To evaluate the faithfulness and relevance of generated answers

Question 43

How can Joule improve workforce productivity? Note: There are 2 correct answers to this question.

• [✗] By offering generic task recommendations unrelated to specific roles.
• [✗] By resolving hardware malfunctions.
• [✓] By maintaining strict adherence to data privacy regulations.
• [✓] By providing context-based role-specific task assistance.

Question 44

What are some metrics to evaluate the effectiveness of a Retrieval Augmented Generation system? Note: There are 2 correct answers to this question.

• [✓] Relevance
• [✗] Speed
• [✗] Carbon footprint
• [✓] Faithfulness

Question 45

You want to assign urgency and sentiment categories to a large number of customer emails. You want to get a valid json string output for creating custom applications. You decide to develop a prompt for the same using generative Al hub. What is the main purpose of the following code in this context?

python

prompt_test = """Your task is to extract and categorize messages. Here are some examples:

{{?technique_examples}}

Use the examples when extract and categorize the following message:

{{?input}}

Extract and return a json with the following keys and values:

- "urgency" as one of {{?urgency}}

- "sentiment" as one of {{?sentiment}}

"categories" list of the best matching support category tags from: {{?categories}}

Your complete message should be a valid json string that can be read directly and onlycontains the keys mentioned in t

import random

random.seed(42)

k = 3

examples random. sample (dev_set, k)

example_template = """<example> {example_input}

examples

'\n---\n'.join([example_template.format(example_input=example ["message"],example_output=json.dumps (example[

f_test = partial (send_request, prompt=prompt_test, technique_examples examples,**option_lists)

response = f_test(input=mail["message"])

 

• (✓) Evaluate the performance of a language model using few-shot learning
• (✗) Generate random examples for language model training
• (✗) Preprocess a dataset for machine learning
• (✗) Train a language model from scratch

Question 46

What capabilities does the Exploration and Development feature of the generative Al hub provide? Note: There are 2 correct answers to this question.

• [✓] Al playground and chat
• [✓] Prompt editor and management
• [✗] Automatic model selection
• [✗] Develop and debug ABAP code

Question 47

What are some examples of generative Al technologies? Note: There are 2 correct answers to this question.

• [✗] Rule-based algorithms
• [✗] Robotic process automation
• [✓] Al models that generate new content based on training data
• [✓] Foundation models

Question 48

What defines SAP's approach to LLMs?

• (✗) Using proprietary transformer-based models exclusively.
• (✓) Ensuring ethical AI practices and seamless business integration.
• (✗) Prioritizing only the performance of open-source models.
• (✗) Avoiding partnerships with external AI providers.

Question 49

Which of the following is unique about SAP's approach to Al?

• (✓) SAP's deep integration of Al with business processes and analytics.
• (✗) Utilizing Al mainly for marketing purposes.
• (✗) Offering Al capabilities in their future products as of 2025.
• (✗) Focusing Al solely on customer support services.

Question 50

What are the benefits of SAP's generative Al hub? Note: There are 2 correct answers to this question.

• [✗] Send your data to various LLM providers for training feedback
• [✓] Build custom Al solutions and extend SAP applications
• [✗] Provide libraries for no-code development
• [✓] Accelerate Al development with flexible access to a broad range of models

Question 51

What are some drivers for the rapid adoption of generative AI? Note: There are 2 correct answers to this question.

• [✓] Ease of use
• [✗] Significant hardware cost savings
• [✓] Wide availability
• [✗] Availability of skilled developers

Question 52

What are some features of Joule? Note: There are 3 correct answers to this question.

• [✗] Downloading and processing data.
• [✓] Streamlining tasks with an Al assistant that knows your unique role.
• [✗] Generating standalone applications.
• [✓] Maintaining data privacy while offering generative Al capabilities.
• [✓] Providing coding assistance and content generation.

Question 53

Which neural network architecture is primarily used by LLMs?

• (✗) Sequential encoder-decoder architecture
• (✗) Recurrent neural network architecture
• (✗) Convolutional Neural Networks (CNNs)
• (✓) Transformer architecture with self-attention mechanisms

Question 54

What are some characteristics of the SAP generative Al hub? Note: There are 2 correct answers to this question.

• [✓] It provides instant access to a wide range of large language models (LLMSs).
• [✗] It operates independently of SAP's partners and ecosystem.
• [✓] It ensures relevant, reliable, and responsible business Al.
• [✗] It only supports traditional machine learning models.

Question 55

What is a part of LLM context optimization?

• (✗) Enhancing the computational speed of the model
• (✗) Adjusting the model's output format and style
• (✓) Providing the model with domain-specific knowledge needed to solve a problem
• (✗) Reducing the model's size to improve efficiency

Question 56

What are some components of the training pipeline in SAP AI Core? Note: There are 2 correct answers to this question.

• [✗] The SAP HANA database for model storage
• [✓] Input datasets stored in a hyperscaler object store
• [✗] Automated deployment to Kubernetes clusters
• [✓] Executables that define the training process

Question 57

What are some SAP recommendations to evaluate pricing and rate information of model usage within SAP's generative Al hub? Note: There are 2 correct answers to this question.

• [✓] Weigh the cost of using advanced models against the expected return on investment
• [✗] Avoid subscription-based pricing models
• [✗] Use pricing models that have fixed rates irrespective of the usage patterns
• [✓] Adopt best practice pricing strategies, such as outcome-based pricing

Question 58

Which technique is used to supply domain-specific knowledge to an LLM?

• (✗) Prompt template expansion
• (✗) Fine-tuning the model on general data
• (✓) Retrieval-Augmented Generation
• (✗) Domain-adaptation training

Question 59

What are some functionalities provided by SAP Al Core? Note: There are 3 correct answers to this question.

• [✓] Integration of Al services with business applications using a standardized API
• [✗] Monitoring and retraining models in SAP Al Core
• [✗] Management of SAP S/4HANA cloud infrastructure
• [✓] Orchestration of Al workflows such as model training and inference
• [✓] Continuous delivery and tenant isolation for scalability

Question 60

What is the goal of prompt engineering?

• (✓) To craft inputs that guide Al systems in generating desired outputs
• (✗) To optimize hardware performance for Al computations
• (✗) To develop new neural network architectures for Al models
• (✗) To replace human decision-making with automated processes

Question 61

What are some benefits of SAP Business Al? Note: There are 3 correct answers to this question.

• [✓] Intelligent business document processing
• [✗] Automatic human emotion recognition
• [✓] Personalized recommendations based on Al algorithms
• [✓] Al-powered forecasting and predictions
• [✗] Face detection and face recognition

Question 62

What does SAP recommend you do before you start training a machine learning model in SAP Al Core? Note: There are 3 correct answers to this question.

• [✓] Define the required infrastructure resources for training.
• [✓] Register the input dataset in SAP Al Core.
• [✗] Perform manual data integration with SAP HANA.
• [✓] Configure the training pipeline using templates.
• [✗] Configure the model deployment in SAP AI Launchpad.

Question 63

Which of the following is a benefit of using Retrieval Augmented Generation?

• (✗) It enables LLMs to learn new languages without additional training.
• (✗) It reduces the computational resources required for language modeling.
• (✗) It eliminates the need for fine-tuning LLMs for specific tasks.
• (✓) It allows LLMs to access and utilize information beyond their initial training data.

Question 64

You want to download a json output for a prompt and the response.

Which of the following interfaces can you use in SAP's generative Al hub in SAP AI Launchpad?

• (✗) Prompt Editor
• (✗) Prompt management
• (✓) Chat
• (✗) Administration