📘 Free AI-103 Sample Questions
Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam
time as you would like to complete each case study. However, there might be additional case studies or other
exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay
attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections
that follow this case study.
To answer the case study questions, you will bed to reference information that is provided in the case. Case studies
and associated questions might contain exhibits or other resources that provide more information about the
scenario described in the case. Information provided in an individual question does not apply to the other questions
in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change
your answers before you move to the next exam section. After you leave this case study, you will NOT be able to
return to it.
To start the case study -
To display the first question in this case study, select the “Next” button. To the left of the question, a menu
provides links to information such as business requirements, the existing environment, and problem statements.
Please read through all this information before answering any questions. When you are ready to answer a question,
select the “Question” button to return to the question.
Overview -
Company Information -
Contoso, Ltd is a multinational retail company that builds, deploys, and manages generative AI and agent-based
solutions by using Microsoft Foundry.
Existing Environment -
Identity Environment -
Contoso uses Microsoft Entra ID for identity management, authentication, and authorization capabilities that
enable agents to access organizational resources and services.
Contoso recently formed a new AI engineering team named Agent1Dev Team to optimize and maintain existing AI
solutions.
The team collaborates with solution architects, DevOps engineers, and security engineers to design, implement.
monitor, and secure AI applications.
Contoso also has a team named Agent1Test Team that is responsible for validating AI solutions before the solution
deployments.
Generative Environment -
Contoso has a Microsoft Foundry deployment that contains two projects named Project1 and Project2.
Project1 -
Project1 contains a customer support agent named Agent1 that assists customers with product inquiries and
troubleshooting requests.
Agent1 has the following configurations:
Agent1 uses a base model deployment.
A safety evaluation pipeline is NOT enabled.
Tool invocation approval workflows are NOT enabled.
Conversation memory constraints are NOT configured.
Agent1 interacts with customers by using digital support channels and answers general questions about Contoso
products.
Project1 is deployed to an Azure region located in the European Union (EU).
Agent1Dev Team will use Project1 to optimize and maintain Agent1.
Project2 -
Project2 contains a deployed video generation model. The marketing department at Contoso has access to
Project2 and plans to use the model to develop a video creation solution.
Development of the solution is incomplete.
Data Environment -
Contoso stores product-related information in Azure resources that support AI applications.
The Azure environment contains an Azure Blob Storage account named storage1 that stores product detail sheets
for all the Contoso products.
The product sheets include specifications, feature descriptions, and product support information that Agent1 can
use to answer customer questions. The product sheets are stored in the PDF format.
Problem Statements -
Contoso identifies the following issues:
Agent1 has only general knowledge of the Contoso products.
A recent chat interaction with Agent1 was analyzed for sentiment. The results of the analysis have NOT been
processed yet.
Agent1 does NOT use the detailed product information in the product sheets stored in storage1 when responding
to customer questions.
The finance department at Contoso reports that vendor invoices must be reviewed manually to ensure that the
invoices match the terms defined in the vendor contracts. The invoices contain tables, logos, and varied layouts
that make the documents difficult to process consistently.
Requirements -
Planned Changes -
Contoso plans to implement the following changes:
Implement a solution for Project1 that analyzes the vendor invoices by evaluating both the visual layout and the
textual content of the invoices, so that the invoice details can be verified against the vendor contract terms.
Update the base model deployment used by Agent1 and standardize the model version to ensure continuity and
consistent responses.
Enable Agent1 to retrieve and use the detailed product information from the product sheets stored in storage1.
Implement an indexing solution for the product sheets that Agent1 can use to answer customer questions.
Complete the development of the video creation solution.
Technical Requirements -
Contoso identifies the following technical requirements:
The model deployment used by Agent1 must support scalable, high-throughput generative AI workloads and
dynamically scale to handle variable customer support traffic, without requiring reserved throughput capacity.
The product sheets must be processed by using an indexing pipeline that enables semantic and vector search, so
that Agent1 can retrieve the relevant product information.
Responses generated by using the product sheet information must be relevant, complete, and accurate.
Agent1 must be able to use the product sheets to answer natural language questions about product details.
The model version used by Agent1 must remain consistent to ensure stable responses.
The data processed by the model must remain within the EU.
Security and Compliance Requirements
Contoso identifies the following security and compliance requirements:
API keys must NOT be used to access Foundry-deployed models.
Access to the Azure resources must follow the principle of least privilege.
The developers at Contoso must authenticate to Microsoft Foundry resources by using Microsoft Entra
authentication.
Access to Project1 must be assigned to the members of Agent1Dev Team by using a security group named
SC_Agent1_Dev.
Access to Project1 must be assigned to the members of Agent1Test Team by using a security group named
SC_Agent1_Test.
Agent1 must never reveal customer information, even if a document that contains customer data is added
erroneously to the product sheet repository in storage1.
The product sheets might contain images that include embedded text. Agent1 must be protected from malicious
instructions potentially hidden within the images.
Business Requirements -
Contoso identifies the following business requirements:
Users that interact with Agent1 must have a personalized experience in future interactions, including the ability for
Agent1 to retain conversation context and recall relevant information from previous interactions.
Agent1 must answer questions only about the products sold by Contoso.
You need to configure the model deployment for Agent1 to meet the technical requirements.
What should you configure? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
Standard .
A Standard deployment:
Uses a pay-as-you-go model.
Automatically scales based on demand.
Does not require purchasing reserved throughput.
Opt out of automatic model version upgrades .
Stable behavior.
Predictable outputs.
Runs within the selected Azure region, helping satisfy the EU data residency requirement.
This keeps the deployment on the selected model version until administrators manually upgrade it.
Consistent testing and validation.
Full control over upgrades.
Case Study -
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam
time as you would like to complete each case study. However, there might be additional case studies or other
exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay
attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections
that follow this case study.
To answer the case study questions, you will bed to reference information that is provided in the case. Case studies
and associated questions might contain exhibits or other resources that provide more information about the
scenario described in the case. Information provided in an individual question does not apply to the other questions
in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change
your answers before you move to the next exam section. After you leave this case study, you will NOT be able to
return to it.
To start the case study -
To display the first question in this case study, select the “Next” button. To the left of the question, a menu
provides links to information such as business requirements, the existing environment, and problem statements.
Please read through all this information before answering any questions. When you are ready to answer a question,
select the “Question” button to return to the question.
Overview -
Company Information -
Contoso, Ltd is a multinational retail company that builds, deploys, and manages generative AI and agent-based
solutions by using Microsoft Foundry.
Existing Environment -
Identity Environment -
Contoso uses Microsoft Entra ID for identity management, authentication, and authorization capabilities that
enable agents to access organizational resources and services.
Generative Environment -
troubleshooting requests.
Agent1 has the following configurations:
Agent1 uses a base model deployment.
A safety evaluation pipeline is NOT enabled.
products.
Project2 -
Contoso recently formed a new AI engineering team named Agent1Dev Team to optimize and maintain existing AI
solutions.
The team collaborates with solution architects, DevOps engineers, and security engineers to design, implement.
monitor, and secure AI applications.
Contoso also has a team named Agent1Test Team that is responsible for validating AI solutions before the solution
deployments.
Contoso has a Microsoft Foundry deployment that contains two projects named Project1 and Project2.
Project1 -
Project1 contains a customer support agent named Agent1 that assists customers with product inquiries and
Tool invocation approval workflows are NOT enabled.
Conversation memory constraints are NOT configured.
Agent1 interacts with customers by using digital support channels and answers general questions about Contoso
Project1 is deployed to an Azure region located in the European Union (EU).
Agent1Dev Team will use Project1 to optimize and maintain Agent1.
Project2 contains a deployed video generation model. The marketing department at Contoso has access to
Project2 and plans to use the model to develop a video creation solution.
Development of the solution is incomplete.
Data Environment -
Contoso stores product-related information in Azure resources that support AI applications.
The Azure environment contains an Azure Blob Storage account named storage1 that stores product detail sheets
for all the Contoso products.
The product sheets include specifications, feature descriptions, and product support information that Agent1 can
use to answer customer questions. The product sheets are stored in the PDF format.
Problem Statements -
Contoso identifies the following issues:
Agent1 has only general knowledge of the Contoso products.
A recent chat interaction with Agent1 was analyzed for sentiment. The results of the analysis have NOT been
processed yet.
Agent1 does NOT use the detailed product information in the product sheets stored in storage1 when responding
to customer questions.
The finance department at Contoso reports that vendor invoices must be reviewed manually to ensure that the
invoices match the terms defined in the vendor contracts. The invoices contain tables, logos, and varied layouts
that make the documents difficult to process consistently.
Requirements -
Planned Changes -
Contoso plans to implement the following changes:
Implement a solution for Project1 that analyzes the vendor invoices by evaluating both the visual layout and the
textual content of the invoices, so that the invoice details can be verified against the vendor contract terms.
Update the base model deployment used by Agent1 and standardize the model version to ensure continuity and
consistent responses.
Enable Agent1 to retrieve and use the detailed product information from the product sheets stored in storage1.
Implement an indexing solution for the product sheets that Agent1 can use to answer customer questions.
Complete the development of the video creation solution.
Technical Requirements -
Contoso identifies the following technical requirements:
The model deployment used by Agent1 must support scalable, high-throughput generative AI workloads and
dynamically scale to handle variable customer support traffic, without requiring reserved throughput capacity.
The product sheets must be processed by using an indexing pipeline that enables semantic and vector search, so
that Agent1 can retrieve the relevant product information.
Responses generated by using the product sheet information must be relevant, complete, and accurate.
Agent1 must be able to use the product sheets to answer natural language questions about product details.
The model version used by Agent1 must remain consistent to ensure stable responses.
The data processed by the model must remain within the EU.
Security and Compliance Requirements
Contoso identifies the following security and compliance requirements:
API keys must NOT be used to access Foundry-deployed models.
Access to the Azure resources must follow the principle of least privilege.
The developers at Contoso must authenticate to Microsoft Foundry resources by using Microsoft Entra
authentication.
Access to Project1 must be assigned to the members of Agent1Dev Team by using a security group named
SC_Agent1_Dev.
Access to Project1 must be assigned to the members of Agent1Test Team by using a security group named
SC_Agent1_Test.
Agent1 must never reveal customer information, even if a document that contains customer data is added
erroneously to the product sheet repository in storage1.
The product sheets might contain images that include embedded text. Agent1 must be protected from malicious
instructions potentially hidden within the images.
Business Requirements -
Contoso identifies the following business requirements:
Users that interact with Agent1 must have a personalized experience in future interactions, including the ability for
Agent1 to retain conversation context and recall relevant information from previous interactions.
Agent1 must answer questions only about the products sold by Contoso.
You need to configure Agent1 to meet the security and compliance requirements.
What should you use?
A
self-harm content filtering
B
prompt shields
C
Personally identifiable information (PII) Detection
D
violence content filtering
Correct Answer:
B. prompt shields
Explanation:
Prompt Shields.
Prompt Shields in Azure Al Foundry / Azure OpenAl are specifically designed to detect and mitigate:
Direct prompt injection attacks
Indirect prompt injection attacks
Malicious instructions hidden in retrieved content
Hidden instructions in documents and multimodal inputs (including images)
You are planning a Microsoft Foundry project named Project1 that will contain multiple agents. Each agent will
access the same Azure AI Search resource.
You need to recommend a solution to centrally manage the Azure AI Search credentials within Project1. The
solution must be implemented across all the agents.
What should you recommend?
A
. Enable role-based access control (RBAC) for the Azure AI Search resource.
B
Disable key-based access control on the Azure AI Search resource.
C
Add a connection to the Azure AI Search resource.
D
Create a managed private endpoint that connects to the Azure AI Search resource.
Correct Answer:
C. Add a connection to the Azure AI Search resource.
Explanation:
C. Add a connection to the Azure AI Search resource .
and
In Microsoft Foundry (Azure AI Foundry), a connection is used to centrally store and manage credentials and
access information for external resources such as:
Azure AI Search
Azure OpenAI
Azure Storage
Databases
Other Azure services
The question states:
"Multiple agents will access the same Azure AI Search resource."
"Centrally manage the Azure AI Search credentials within Project1."
By creating one project-level connection to the Azure AI Search resource:
Credentials are stored and managed centrally.
All agents in Project1 can reuse the same connection.
You avoid configuring credentials separately for each agent.
Credential rotation and management become easier.
This is exactly what connections are designed for.
Why the other options are incorrect:
A. Enable RBAC for the Azure AI Search resource .
RBAC controls authorization (who can access the resource).
While RBAC is a security best practice, it does not centrally manage credentials within Foundry projects and
does not provide a reusable project-wide configuration for agents.
The question is specifically about managing Azure AI Search credentials across multiple agents.
B. Disable key-based access control on the Azure AI Search resource .
Disabling key-based access control forces the use of Entra ID authentication.
Although this improves security, it does not:
Create a reusable configuration for agents.
Centrally manage the Azure AI Search connection inside Project1.
D. Create a managed private endpoint .
A managed private endpoint provides:
Private network connectivity
Network isolation
It addresses networking requirements, not credential management.
The agents would still need a configured connection to use Azure AI Search.
HOTSPOT -
Your company is piloting a customer support agent in a Microsoft Foundry project name Project1. Project1 is
connected to an existing Application Insights resource, and the company's support team reviews runs in the Traces
tab.
The Foundry Agent Service is configured to perform the following actions:
Retrieve the Application Insights connection string by calling
project_client.telemetry.get_application_insights_connection_string().
Call configure_azure_monitor(connection_string =... ) to enable telemetry.
A separate LangChain service is configured to use OpenTelemetry and has the following configurations:
Uses AzureAlOpenTelemetryTracer(connection_string =... , enable_content_recording=False)
Passes the tracer by using config= "callbacks":[azure_tracer]
Company policy has the following requirements:
Telemetry from LangChain and OpenTelemetry must be distinguishable within the same Application Insights
resource.
Secrets and credentials must NOT be stored in prompts, tool arguments, or span attributes.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
To determine the correct answers, we analyze the configuration of telemetry within the Microsoft Foundry
project and LangChain service:1. "The LangChain service will record sensitive information in the traces.": The
LangChain service uses `AzureAIOpenTelemetryTracer` with `enable_content_recording=False`. This setting
explicitly prevents the recording of prompts, tool arguments, and span attributes (which contain sensitive
information). Therefore, it will not record sensitive information. Answer: No.2. "Telemetry data from the
Foundry Agent Service and the LangChain service will be distinguishable in Application Insights.": The
Foundry Agent Service uses the standard Azure Monitor OpenTelemetry SDK (via `configure_azure_monitor`),
while the LangChain service uses a separate tracer instance. Because these are two different
processes/services reporting to the same Application Insights resource, they will be distinguished by their
`cloud_RoleName` attribute (defaulting to the service/process name). Additionally, if they are not explicitly
configured to override it, they are distinct entities. However, standard practice in Application Insights for
identifying service sources is via the cloud role. Since they are distinct services, they are distinguishable.
Answer: Yes.3. "The LangChain service must use a separate Application Insights resource to distinguish
telemetry from the Foundry Agent Service.": This is false. Application Insights is designed to aggregate
telemetry from multiple sources into a single resource, using the `cloud_RoleName` attribute to distinguish
between different services. Answer: No.Correct Answer:NoYesNo
DRAG DROP -
You have a Microsoft Foundry project that processes procurement documents submitted by suppliers.
You need to implement two pipelines by using Azure Content Understanding in Foundry Tools. The solution must
meet the following requirements:
Include a pipeline named Pipeline1 that supports cost-effective, high-volume processing of standalone PDF
invoices.
Include a pipeline named Pipeline2 that supports cross-document validation by using multi-step reasoning and
reference data.
How should you configure each pipeline? To answer, drag the appropriate configurations to the correct pipelines.
Each configuration may be used once, more than once, of not at all. You may need to drag the split bar between
panes or scroll to view content.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
Pipeline1: Multi-file task in pro mode
Pipeline2: Single-file task in standard mode
activates Pro mode.
Pro Mode (Multi-file task): This mode is specifically designed for advanced scenarios that require multi-step
reasoning, validation, context enrichment, and cross-referencing over multiple input files (multi-content
inputs) in a single request. When creating a task in the AI Foundry wizard, selecting Multi-file automatically
Standard Mode (Single-file task): This is the default, highly cost-effective mode tailored for processing and
extracting structured fields out of a single file at a time (e.g., individual documents, video streams, or audio
recordings) without needing cross-file data aggregation or complex sequential logic. Selecting Single-file
activates Standard mode.
HOTSPOT -
You have a Python application named App1 that integrates with a Microsoft Foundry project named Project1.
You need to ensure that App1 meets the following requirements:
Authenticates by using a Microsoft Entra managed identity
Sends prompts to a deployed model by using the Azure OpenAl Responses API
How should you complete the Python code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
DefaultAzureCredential: The script explicitly imports DefaultAzureCredential from the azure.identity package
at the very top. This is the recommended SDK credential workflow for seamless environment variable,
managed identity, or Azure CLI token handling.
create: The client library exposes the openai_client.responses interface matching the standard OpenAI SDK
architecture format. To initiate a stateless request, the generation pattern uses the .create( ... ) method to post
the input instruction string payload to the target inference engine.
HOTSPOT -
You have a Microsoft Foundry project that contains a workflow for a customer support triage process.
You have an Ask a question node that stores user responses in a local variable named Var01.
You need to create the following Power Fx expressions:
An if/else condition expression that ensures that Var01 contains a value
A Send message expression that returns the stored user response in uppercase
How should you configure the expressions? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
If/else condition expression: Not(IsBlank(Local.Var01)) Send message expression: Upper(Local.Var01) Core
ConceptsChecking for a Value: In Power Fx, the IsBlank() function checks whether a text variable or value is
blank. To build an condition that explicitly ensures the variable contains a value before proceeding, you must
wrap it in a logical negation using Not(...). IsEmpty() is incorrect because it is used strictly to check whether a
table or collection contains records, not for checking scalar text variable inputs. Text Formatting & Scope:
When embedding code formatting or formulas into a Send Message node, string interpolation brackets are
used to dynamic pull the variable. The scope of a locally scoped workflow variable requires the Local. prefix,
and the Upper() function ensures that the string payload is converted entirely into uppercase characters.
HOTSPOT -
You have a Microsoft Foundry project that contains a customer support agent built by using the Foundry Agent
Service.
The agent uploads user-provided screenshots to Azure Storage through a ticketing tool and receives a blob URL
for additional reasoning.
You need to use image moderation during agent runs and prevent harmful content from being returned during
runs. Azure AI Content Safety must access the images by using the blob URL. The solution must follow the
principle of least privilege.
What should you configure for Content Safety? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
A
Correct Answer:
A.
Explanation:
Guardrails: Select User input, Output, Tool response, and Tool call and set Action to Block.
Storage access: A system-assigned managed identity that is assigned the Storage Blob Data Reader role
1. Guardrails Configuration
Microsoft AI Foundry's Agent Service supports content moderation intervention at four foundational cycle
lifecycle points: User input, Output, Tool call, and Tool response.
Because this workflow handles user-submitted media (screenshots) processed through an external tool (the
ticketing system) and returns a blob URL for model reasoning, harmful data could pass through at any stage.
Setting the action to Block across all four touchpoints ensures that if unsafe or unmoderated content is
detected anywhere in the execution loop (from the initial prompt to the tool's returned blob URL), the request
is immediately halted rather than allowed to propagate.
2. Storage Access Configuration
To evaluate an image supplied via an Azure Blob Storage URL, Azure AI Content Safety needs a secure
mechanism to read the image file without using unmanaged connection keys.
violates the principle of least privilege).
Least Privilege: Since Content Safety only needs to look at and analyze the screenshots, it requires read-only
permissions. The Storage Blob Data Reader role provides the exact minimum permissions required to pull the
image file. (Note: Storage Blob Data Contributor is incorrect as it grants write/delete permissions, which
Managed Identity: Utilizing a system-assigned managed identity eliminates the need to manage credentials,
access keys, or connection strings within the code.
You have a Microsoft Foundry project that contains three agents as shown in the following table.
You need to orchestrate the agents to ensure that the customer requests meet the following requirements:
Support a deterministic, step-based process that uses conditional branching and shared state across the agents.
Optionally trigger a ticket action based on the triage result.
The solution must minimize development effort.
What should you include in the solution?
A
a workflow
B
threads and runs without a workflow
C
a multi-agent group chat session
D
separate agent runs coordinated in the application code
Correct Answer:
A. a workflow
Explanation:
A. Workflow .
A workflow allows you to:
Define a sequence of agent steps.
Pass data (shared state) between steps.
Use conditions and branching logic.
Invoke actions/tools based on outcomes.
Orchestrate multiple agents declaratively rather than writing custom code.
You have a Microsoft Foundry project that contains an agent. The agent uses Azure Speech in Foundry Tools.
You fine-tune a baseline speech to text model for the en-us locale and publish the model.
The agent calls the Speech to text REST API and returns an error message indicating that the project ID is invalid.
You need to set the project property to the correct ID.
To what should you set the project property?
A
the project URL
B
. the custom speech project ID
C
the project ID
D
the custom speech endpoint URL
Correct Answer:
B. . the custom speech project ID
Explanation:
B. the custom speech project ID.
You fine-tuned a baseline Speech-to-Text model for the en-us locale.
You published the custom model.
The agent uses Azure Speech in Foundry Tools.
The Speech-to-Text REST API returns:
"project ID is invalid"
Speech project that contains the trained model.
Why the other options are incorrect:
A. Project URL
C. Project ID
In Azure AI Speech, when using a custom Speech-to-Text model, the project property refers to the Custom
A URL identifies the web resource, not the project identifier expected by the Speech API.
This is ambiguous. In a Foundry environment, the Foundry project ID is different from the Custom Speech
project ID used by the Speech service. The Speech API expects the Custom Speech project's identifier.
D. Custom Speech endpoint URL
The endpoint URL specifies where requests are sent. It is not used as the value of the project property.
Questions: 1-10 out of 65
Continue Full Practice..
GET ALL 65 QUESTIONS