Preview real exam questions, verified answers and available explanations before choosing a study plan.
Question 1
Hotspot
HOTSPOT
You have an Azure OpenAI resource named AI1 that hosts three deployments of the GPT 3.5 model. Each deployment is optimized for a unique workload.
You plan to deploy three apps. Each app will access AI1 by using the REST API and will use the deployment that was optimized for the app's intended workload.
You need to provide each app with access to AI1 and the appropriate deployment. The solution must ensure that only the apps can access AI1.
What should you use to provide access to AI1, and what should each app use to connect to its appropriate deployment? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 2
Hotspot
HOTSPOT
You run the following command.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
Reveal answer detailsClose answer details
Question 3
Multiple choice
A customer uses Azure Cognitive Search.
The customer plans to enable a server-side encryption and use customer-managed keys (CMK) stored in Azure.
What are three implications of the planned change? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A
The index size will increase.
B
Query times will increase.
C
A self-signed X.509 certificate is required.
D
The index size will decrease.
E
Query times will decrease.
F
Azure Key Vault is required.
Reveal answer detailsClose answer details
Correct answersA, B, F
Explanation
"Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance." same document also lists Azure Key Vault as a requirement:
You need to ensure that the reading experience is optimized for users who have reduced comprehension and learning differences, such as dyslexia. The solution must minimize development effort.
Which Azure service should you include in the solution?
A
Azure AI Immersive Reader
B
Azure AI Translator
C
Azure AI Document Intelligence
D
Azure AI Language
Reveal answer detailsClose answer details
Correct answerA
Question 5
Hotspot
HOTSPOT
You have an Azure subscription that is linked to a Microsoft Entra tenant. The subscription ID is x1xx11x1- x111-xxxx-xxxx-x1111xxx11x1 and the tenant ID is 1y1y1yyy-1y1y-y1y1-yy11-y1y1y11111y1.
The subscription contains an Azure OpenAI resource named OpenAI1 that has a primary API key of 1111a111a11a111aaa11a1a1a11a11aa. OpenAI1 has a deployment named embeddings1 that uses the text-embedding-ada-002 model.
You need to query OpenAI1 and retrieve embeddings for text input.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 6
Hotspot
HOTSPOT
You are developing an app that will use the Azure AI Vision API to analyze an image.
You need configure the request that will be used by the app to identify whether an image is clipart or a line
drawing.
How should you complete the request? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 7
Drag & drop
DRAG DROP
You have a chatbot that uses a QnA Maker application.
You enable active learning for the knowledge base used by the QnA Maker application.
You need to integrate user input into the model.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Explanation
Step 1: For the knowledge base, select Show active learning suggestions. In order to see the suggested questions, on the Edit knowledge base page, select View Options, then select Show active learning suggestions.
Step 2: Approve and reject suggestions. ✔ Each QnA pair suggests the new question alternatives with a check mark, , to accept the question or an x to reject the suggestions. Select the check mark to add the question.
Step 3: Save and train the knowledge base. Select Save and Train to save the changes to the knowledge base.
Step 4: Publish the knowledge base.
Select Publish to allow the changes to be available from the GenerateAnswer API.
When 5 or more similar queries are clustered, every 30 minutes, QnA Maker suggests the alternate questions for you to accept or reject.
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You have a chatbot that uses question answering in Azure Cognitive Service for Language.
Users report that the responses of the chatbot lack formality when answering spurious questions.
You need to ensure that the chatbot provides formal responses to spurious questions.
Solution: From Language Studio, you change the chitchat source to qna_chitchat_professional.tsv, and then retrain and republish the model.
Does this meet the goal?
A
Yes
B
No
Reveal answer detailsClose answer details
Correct answerA
Explanation
Formal response, it is Personality = Professional, it is file qna_chitchat_professional.tsv . https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices#choosing-a-personality
Question 11
Lab simulation
Simulation
You need to configure and publish bot12345678 to support task management. The intent must be named TaskReminder. The LUDown for the intent is in the C: \Resources\LU folder. To complete this task, use the Microsoft Bot Framework Composer.
Reveal model answerClose model answer
Step 1: Open Microsoft Bot Framework Composer Step 2: Select the bot bot12345678 Step 3: Select Import existing resources. Read the instructions on the right side of the screen and select Next.
Step 4: Browse to the C:\Resources\LU folder and select the available .lu file Step 5: In the pop-up window Importing existing resources, modify the JSON file content based on your resources information: Name the intent TaskReminder Step 6: Select Publish from the Composer menu. In the Publish your bots pane, select the bot to publish (bot12345678), then select a publish profile from the Publish target drop-down list.
You are building an agent by using the Azure Al Foundry Agent Service.
You have the following code.
Reveal answer detailsClose answer details
Explanation
The agent will reason over the uploaded file.## The code will create a run and check the output.## The code will create an agent and enable a file search.## The agent will reason over the uploaded file.
Yes: The code includes file = project_client.agents.upload_file_and_poll(file_path="./data/file1.zip", purpose=FilePurpose.AGENTS). The upload_file_and_poll method with FilePurpose.AGENTS suggests that the file (file1.zip) is uploaded for the agent to process, and agents in the Azure AI Foundry Agent Service are typically designed to reason over uploaded data. This indicates the agent will reason over the uploaded file.
The code will create a run and check the output. No: The provided code snippet does not include any explicit call to create a run (e.g., a method like create_run or start_run) or check the output (e.g., a method to retrieve or poll run results). The code only uploads a file and creates a vector store, but it does not initiate or monitor a run.
The code will create an agent and enable a file search. No: The code does not contain a method to create an agent (e.g., create_agent) or explicitly enable a file search. The create_vector_store_and_poll method creates a vector store, which is typically used for indexing data for search, but there is no indication of enabling a file search or creating an agent in this snippet.
Question 13
Single choice
You need to build a solution that will use optical character recognition (OCR) to scan sensitive documents by using the Computer Vision API. The solution must not be deployed to the public cloud.
What should you do?
A
Build an on-premises web app to query the Computer Vision endpoint.
B
Host the Computer Vision endpoint in a container on an on-premises server.
C
Host an exported Open Neural Network Exchange (ONNX) model on an on-premises server.
D
Build an Azure web app to query the Computer Vision endpoint.
Reveal answer detailsClose answer details
Correct answerB
Explanation
One option to manage your Computer Vision containers on-premises is to use Kubernetes and Helm. Three primary parameters for all Cognitive Services containers are required. The Microsoft Software License Terms must be present with a value of accept. An Endpoint URI and API key are also needed. Incorrect: Not D: This Computer Vision endpoint would be available for the public, unless it is secured. References: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/deploy-computer-vision-on-premises
Question 14
Single choice
Your company uses an Azure Cognitive Services solution to detect faces in uploaded images. The method to detect the faces uses the following code.
You discover that the solution frequently fails to detect faces in blurred images and in images that contain sideways faces.
You need to increase the likelihood that the solution can detect faces in blurred images and images that contain sideways faces.
What should you do?
A
Use a different version of the Face API.
B
Use the Computer Vision service instead of the Face service.
C
Use the Identify method instead of the Detect method.
D
Change the detection model.
Reveal answer detailsClose answer details
Correct answerD
Explanation
Evaluate different models. The best way to compare the performances of the detection models is to use them on a sample dataset. We recommend calling the Face - Detect API on a variety of images, especially images of many faces or of faces that are difficult to see, using each detection model. Pay attention to the number of faces that each model returns.
You are developing an app that will use the Decision and Language APIs.
You need to provision resources for the app. The solution must ensure that each service is accessed by using a single endpoint and credential.
Which type of resource should you create?
A
Language
B
Speech
C
Azure Cognitive Services
D
Content Moderator
Reveal answer detailsClose answer details
Correct answerC
Question 16
Single choice
You have a product knowledgebase that contains multiple PDF documents.
You need to build a chatbot that will provide responses based on data in the knowledgebase. The solution must minimize development effort and costs.
What should you include in the solution?
A
Azure Al Language conversational language understanding (CLU)
B
Azure Al language detection
C
Azure Al Language custom question answering
D
Azure OpenAI
Reveal answer detailsClose answer details
Correct answerC
Question 17
Single choice
You are building a chatbot.
You need to configure the chatbot to query a knowledge base.
Which dialog class should you use?
A
AdaptiveDialog
B
QnAMakerDialog
C
ComponentDialog
D
SkillDialog
Reveal answer detailsClose answer details
Correct answerB
Question 18
Lab simulation
Simulation
You need to create a Text Analytics service named Text12345678, and then enable logging for Text12345678.
The solution must ensure that any changes to Text12345678 will be stored in a Log Analytics workspace.
To complete this task, sign in to the Azure portal.
Reveal model answerClose model answer
Step 1: Sign in to the QnA portal. Step 2: Create an Azure Cognitive multi-service resource:
Step 3: On the Create page, provide the following information.
Name: Text12345678
Step 4: Configure additional settings for your resource as needed, read and accept the conditions (as applicable), and then select Review + create. Step 5: Navigate to the Azure portal. Then locate and select The Text Analytics service resource Text12345678 (which you created in Step 4). Step 6: Next, from the left-hand navigation menu, locate Monitoring and select Diagnostic settings. This screen contains all previously created diagnostic settings for this resource. Step 7: Select + Add diagnostic setting. Step 8: When prompted to configure, select the storage account and OMS workspace that you'd like to use to store you diagnostic logs. Note: If you don't have a storage account or OMS workspace, follow the prompts to create one. Step 9: Select Audit, RequestResponse, and AllMetrics. Then set the retention period for your diagnostic log data. If a retention policy is set to zero, events for that log category are stored indefinitely. Step 10: Click Save. It can take up to two hours before logging data is available to query and analyze. So don't worry if you don't see anything right away.
You develop an application that uses the Face API.
You need to add multiple images to a person group.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Explanation
Box 1: Stream The File.OpenRead(String) method opens an existing file for reading.
Example: Open the stream and read it back. using (FileStream fs = File.OpenRead(path)) Box 2: AddFaceFromStreamAsync
Step 5 on https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces
Case study
Case Study 1
Overview
A company named Wide World Importers is developing an e-commerce platform.
You are working with a solutions architect to design and implement the features of the e-commerce platform. The platform will use microservices and a serverless environment built on Azure.
Wide World Importers has a customer base that includes English, Spanish, and Portuguese speakers.
Existing Environment
Applications
Wide World Importers has an App Service plan that contains the web apps shown in the following table.
Azure Resources
You have the following resources:
An Azure Active Directory (Azure AD) tenant - The tenant supports internal authentication. - All employees belong to a group named AllUsers. - Senior managers belong to a group named LeadershipTeam. An Azure Functions resource
- A function app posts to Azure Event Grid when stock levels of a product change between OK, Low Stock, and Out of Stock. The function app uses the Azure Cosmos DB change feed. An Azure Cosmos DB account - The account uses the Core (SQL) API. - The account stores data for the Product Management app and the Inventory Tracking app. An Azure Storage account - The account contains blob containers for assets related to products. - The assets include images, videos, and PDFs. An Azure Cognitive Services resource named wwics A Video Indexer resource named wwivi
Requirements
Business Goals
Wide World Importers wants to leverage AI technologies to differentiate itself from its competitors.
Planned Changes
Wide World Importers plans to start the following projects:
1. A product creation project: Help employees create accessible and multilingual product entries, while expediting product entry creation. 2. A smart e-commerce project: Implement an Azure Cognitive Search solution to display products for customers to browse. 3. A shopping on-the-go project: Build a chatbot that can be integrated into smart speakers to support customers.
Business Requirements
Wide World Importers identifies the following business requirements for all the projects:
1. Provide a multilingual customer experience that supports English, Spanish, and Portuguese. 2. Whenever possible, scale based on transaction volumes to ensure consistent performance. 3. Minimize costs.
Governance and Security Requirements
Wide World Importers identifies the following governance and security requirements:
1. Data storage and processing must occur in datacenters located in the United States. 2. Azure Cognitive Services must be inaccessible directly from the internet.
Accessibility Requirements
Wide World Importers identifies the following accessibility requirements:
1. All images must have relevant alt text. 2. All videos must have transcripts that are associated to the video and included in product descriptions. 3. Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese.
Product Creation Requirements
Wide World Importers identifies the following requirements for improving the Product Management app:
1. Minimize how long it takes for employees to create products and add assets. 2. Remove the need for manual translations.
Smart E-Commerce Requirements
Wide World Importers identifies the following requirements for the smart e-commerce project:
1. Ensure that the Cognitive Search solution meets a Service Level Agreement (SLA) of 99.9% availability for searches and index writes.
2. Provide users with the ability to search insight gained from the images, manuals, and videos associated with the products. 3. Support autocompletion and autosuggestion based on all product name variants. 4. Store all raw insight data that was generated, so the data can be processed later. 5. Update the stock level field in the product index immediately upon changes. 6. Update the product index hourly.
Shopping On-the-Go Requirements
Wide World Importers identifies the following requirements for the shopping on-the-go chatbot:
1. Answer common questions. 2. Support interactions in English, Spanish, and Portuguese. 3. Replace an existing FAQ process so that all Q&A is managed from a central location. 4. Provide all employees with the ability to edit Q&As. Only senior managers must be able to publish updates. 5. Support purchases by providing information about relevant products to customers. Product displays must include images and warnings when stock levels are low or out of stock.
Product JSON Sample
You have the following JSON sample for a product.
Question 20
Testlet 1Multiple choice
You are developing the smart e-commerce project.
You need to implement autocompletion as part of the Cognitive Search solution.
Which three actions should you perform? Each correct answer presents part of the solution. (Choose three.)
NOTE: Each correct selection is worth one point.
A
Make API queries to the autocomplete endpoint and include suggesterName in the body.
B
Add a suggester that has the three product name fields as source fields.
C
Make API queries to the search endpoint and include the product name fields in the searchFields query parameter.
D
Add a suggester for each of the three product name fields.
E
Set the searchAnalyzer property for the three product name variants.
F
Set the analyzer property for the three product name variants.
Reveal answer detailsClose answer details
Correct answersA, B, F
Explanation
Scenario: Support autocompletion and autosuggestion based on all product name variants.
A: Call a suggester-enabled query, in the form of a Suggestion request or Autocomplete request, using an API. API usage is illustrated in the following call to the Autocomplete REST API.
POST /indexes/myxboxgames/docs/autocomplete?search&api-version=2020-06-30 { "search": "minecraf", "suggesterName": "sg" }
B: In Azure Cognitive Search, typeahead or "search-as-you-type" is enabled through a suggester. A suggester provides a list of fields that undergo additional tokenization, generating prefix sequences to support matches on partial terms. For example, a suggester that includes a City field with a value for "Seattle" will have prefix combinations of "sea", "seat", "seatt", and "seattl" to support typeahead.
F. Use the default standard Lucene analyzer ("analyzer": null) or a language analyzer (for example, "analyzer": "en.Microsoft") on the field.
You have an Azure subscription that contains an Azure OpenA1 resource named AH.
You plan to build an app named App1 that will write press releases by using AM.
You need to deploy an Azure OpenA1 model for Appl. The solution must minimize development effort.
Which three actions should you perform in sequence in Azure OpenAI Studio? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Question 22
Single choice
You are building a chatbot for a travel agent. The bot will ask users for a destination and must repeat the question until a valid input is received, or the user closes the conversation.
Which type of dialog should you use?
A
prompt
B
input
C
adaptive
D
QnA Maker
Reveal answer detailsClose answer details
Correct answerA
Explanation
https://learn.microsoft.com/en-us/azure/bot-service/bot-builder-concept-dialog?view=azure-bot-service-4.0#dialog-types The dialogs library provides a few types of dialogs to make your bot's conversations easier to manage. - prompt dialogs Ask the user for input and return the result. A prompt will repeat until it gets valid input or it's canceled. They're designed to work with waterfall dialogs.
Question 23
Single choice
You need to measure the public perception of your brand on social media by using natural language processing.
Which Azure service should you use?
A
Content Moderator
B
Form Recognizer
C
Computer Vision
D
Language service
Reveal answer detailsClose answer details
Correct answerD
Question 24
Hotspot
HOTSPOT
Select the answer that correctly completes the sentence.
Reveal answer detailsClose answer details
Question 25
Hotspot
HOTSPOT
You have an Azure subscription that contains an Azure Al Content Safety resource named Resource1.
You create the following cURL command.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth point.
Reveal answer detailsClose answer details
Question 26
Hotspot
HOTSPOT
You are designing a conversation flow to be used in a chatbot.
You need to test the conversation flow by using the Microsoft Bot Framework Emulator.
How should you complete the .chat file? To answer, select the appropriate options in the answer area.
You are building an AI solution that will use Sentiment Analysis results from surveys to calculate bonuses for customer service staff.
You need to ensure that the solution meets the Microsoft responsible AI principles.
What should you do?
A
Add a human review and approval step before making decisions that affect the staff's financial situation.
B
Include the Sentiment Analysis results when surveys return a low confidence score.
C
Use all the surveys, including surveys by customers who requested that their account be deleted and their data be removed.
D
Publish the raw survey data to a central location and provide the staff with access to the location.
Reveal answer detailsClose answer details
Correct answerA
Question 28
Single choice
You have an Azure subscription that contains an Azure Al Document Intelligence resource named Aldoc1.
You have an app named App1 that uses Aldoc1. App1 analyzes business cards by calling business card model v2.1.
You need to update App1 to ensure that the app can interpret QR codes. The solution must minimize administrative effort.
What should you do first?
A
Deploy a custom model.
B
Implement the read model.
C
Upgrade the business card model to v3.0
D
Implement the contract model
Reveal answer detailsClose answer details
Correct answerC
Question 29
Lab simulation
Simulation
Use the following login credentials as needed: To enter your username, place your cursor in the Sign in box and click on the username below. To enter your password, place your cursor in the Enter password box and click on the password below.
Azure Password: XXXXXXXXXXXX The following information is for technical support purposes only:
Lab Instance: 12345678
Task You need to create and publish a Language Understanding (classic) model named 1u12345678. The
model will contain an intent of Travel that has an utterance of Boat. To complete this task, sign in to the Language Understanding portal at httptc//www.luis-ai/.
Reveal model answerClose model answer
Create your LUIS model - 1. You should navigate to your LUIS.ai management portal and create a new application. In the portal create a model.
Model name: 1u12345678 - 2. Define one intent as ג€Travelג€ and add an example utterances of Boat.
3. Publish the model In order to use your model, you have to publish it. This is as easy as hitting the Publish tab, selecting between the production or staging environments, and hitting Publish. As you can see from this page, you can also choose to enable sentiment analysis, speech priming to improve speech recognition, or the spell checker. For now, you can leave those unchecked.
You have a Custom Vision resource named acvdev in a development environment.
You have a Custom Vision resource named acvprod in a production environment.
In acvdev, you build an object detection model named obj1 in a project named proj1.
You need to move obj1 to acvprod.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Contoso, Ltd. is an international accounting company that has offices in France, Portugal, and the United Kingdom.
Contoso has a professional services department that contains the roles shown in the following table.
Existing environment
Infrastructure
Contoso has the following subscriptions:
1. Azure 2. Microsoft 365 3. Microsoft Dynamics 365
Azure Active (Azure AD) Directory
Contoso has Azure Active Directory groups for securing role-based access. The company uses the following group naming conventions:
1. [Country]-[Level]-[Role] 2. [Level]-[Role]
Intellectual Property
Contoso has the intellectual property shown in the following table.
Text-based content is provided only in one language and is not translated.
Requirements
Planned Projects
Contoso plans to develop the following:
1. A document processing workflow to extract information automatically from PDFs and images of financial documents 2. A customer-support chatbot that will answer questions by using FAQs 3. A searchable knowledgebase of all the intellectual property
Technical Requirements
Contoso identifies the following technical requirements:
1. All content must be approved before being published. 2. All planned projects must support English, French, and Portuguese. 3. All content must be secured by using role-based access control (RBAC). 4. RBAC role assignments must use the principle of least privilege. 5. RBAC roles must be assigned only to Azure Active Directory groups. 6. AI solution responses must have a confidence score that is equal to or greater than 70 percent. 7. When the response confidence score of an AI response is lower than 70 percent, the response must be improved by human input.
Chatbot Requirements
Contoso identifies the following requirements for the chatbot:
1. Provide customers with answers to the FAQs. 2. Ensure that the customers can chat to a customer service agent. 3. Ensure that the members of a group named Management-Accountants can approve the FAQs. 4. Ensure that the members of a group named Consultant-Accountants can create and amend the FAQs. 5. Ensure that the members of a group named the Agent-CustomerServices can browse the FAQs. 6. Ensure that access to the customer service agents is managed by using Omnichannel for Customer Service. 7. When the response confidence score is low, ensure that the chatbot can provide other response options to the customers.
Document Processing Requirements
Contoso identifies the following requirements for document processing:
The document processing solution must be able to process standardized financial documents that have the following characteristics: - Contain fewer than 20 pages. - Be formatted as PDF or JPEG files. - Have a distinct standard for each office. The document processing solution must be able to extract tables and text from the financial documents. The document processing solution must be able to extract information from receipt images. Members of a group named Management-Bookkeeper must define how to extract tables from the financial documents. Members of a group named Consultant-Bookkeeper must be able to process the financial documents.
Knowledgebase Requirements
Contoso identifies the following requirements for the knowledgebase:
1. Supports searches for equivalent terms 2. Can transcribe jargon with high accuracy 3. Can search content in different formats, including video 4. Provides relevant links to external resources for further research
Question 31
Testlet 2Single choice
You are developing the knowledgebase.
You use Azure Video Analyzer for Media (previously Video indexer) to obtain transcripts of webinars.
You need to ensure that the solution meets the knowledgebase requirements.
What should you do?
A
Create a custom language model
B
Configure audio indexing for videos only
C
Enable multi-language detection for videos
D
Build a custom Person model for webinar presenters
Reveal answer detailsClose answer details
Correct answerA
Explanation
https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-overview Azure Video Indexer supports automatic speech recognition through integration with the Microsoft Custom Speech Service. You can customize the Language model by uploading adaptation text, namely text from the domain whose vocabulary you'd like the engine to adapt to. Once you train your model, new words appearing in the adaptation text will be recognized, assuming default pronunciation, and the Language model will learn new probable sequences of words.
Question 32
Single choice
You are training a Language Understanding model for a user support system.
You create the first intent named GetContactDetails and add 200 examples.
You need to decrease the likelihood of a false positive.
What should you do?
A
Enable active learning.
B
Add a machine learned entity.
C
Add additional examples to the GetContactDetails intent.
You need to configure bot12345678 support the French (FR-FR) language. Export the bot to C:\Resources\Bot\Bot1.zip. To complete this task, use the Microsoft Bot Framework Composer.
Reveal model answerClose model answer
Step 1: Open Microsoft Bot Framework Composer Step 2: Select the bot bot12345678 Step 3: Select Configure. Step 4: Select the Azure Language Understanding tab Step 5: Select the Set up Language Understanding button. The Set up Language Understanding window will appear, shown below:
Step 6: Select Use existing resources and then select Next at the bottom of the window. Step 7: Now select the Azure directory, Azure subscription, and Language Understanding resource name (French). Step 8: Select Next on the bottom. Your Key and Region will appear on the next on the next window, shown below:
You are building a transcription service for technical podcasts.
Testing reveals that the service fails to transcribe technical terms accurately.
You need to improve the accuracy of the service.
Which five actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Explanation
https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/custom-speech-overview#how-does-it-work With Custom Speech, you can upload your own data, test and train a custom model, compare accuracy between models, and deploy a model to a custom endpoint. - Create a project and choose a model. Use a Speech resource that you create in the Azure portal. If you will train a custom model with audio data, choose a Speech resource region with dedicated hardware for training audio data. - Upload test data. Upload test data to evaluate the speech to text offering for your applications, tools, and products. - Train a model. Provide written transcripts and related text, along with the corresponding audio data. Testing a model before and after training is optional but recommended. - Deploy a model. Once you're satisfied with the test results, deploy the model to a custom endpoint. With the exception of batch transcription, you must deploy a custom endpoint to use a Custom Speech model.
Question 35
Drag & drop
DRAG DROP
You have a collection of Microsoft Word documents and PowerPoint presentations in German.
You need to create a solution to translate the files to French. The solution must meet the following requirements:
Preserve the original formatting of the files. Support the use of a custom glossary.
You create a blob container for German files and a blob container for French files. You upload the original files to the container for German files.
Which three actions should you perform in sequence to complete the solution? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Question 36
Hotspot
HOTSPOT
You have a collection of press releases stored as PDF files.
You need to extract text from the files and perform sentiment analysis.
Which service should you use for each task? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 37
Hotspot
HOTSPOT
Select the answer that correctly completes the sentence.
Reveal answer detailsClose answer details
Question 38
Hotspot
HOTSPOT
You have a chatbot that uses the Azure Al Language custom question answering service.
You need to test the chatbot. The solution must ensure that the chatbot responds only when an answer has a confidence score of at least 95 percent.
How should you complete the cURL statement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 39
Lab simulation
Simulation
Use the following login credentials as needed: To enter your username, place your cursor in the Sign in box and click on the username below. To enter your password, place your cursor in the Enter password box and click on the password below.
Azure Password: XXXXXXXXXXXX The following information is for technical support purposes only:
Lab Instance: 12345678
Task You plan to analyze stock photography and automatically generate captions for the images. You need to create a service in Azure to analyze the images. The service must be named caption12345678 and must be in the East US Azure region. The solution must use the Free pricing tier. In the C:\Resources\Caption\Params.json folder, enter the value for Key 1 and the endpoint for the new service. To complete this task, sign in to the Azure portal.
Reveal model answerClose model answer
Step 1: Provision a Cognitive Services resource If you don't already have one in your subscription, you'll need to provision a Cognitive Services resource. 1. Open the Azure portal at https://portal.azure.com, and sign in using the Microsoft account associated with your Azure subscription.
2. Select the Create a resource button, search for cognitive services, and create a Cognitive Services resource with the following settings: Subscription: Your Azure subscription Resource group: Choose or create a resource group (if you are using a restricted subscription, you may not have permission to create a new resource group - use the one provided)
Region: East US Azure region -
Name: caption12345678 -
Pricing tier: Free F0 - 3. Select the required checkboxes and create the resource. Wait for deployment to complete, and then view the deployment details. 4. When the resource has been deployed, go to it and view its Keys and Endpoint page. You will need the endpoint and one of the keys from this page in the next procedure. Step 2: Save Key and Endpoint values in Params.json Open the configuration file, C:\Resources\Caption\Params.json. and update the configuration values it contains to reflect the endpoint and an authentication key for your cognitive services resource. Save your changes.
You have an Azure subscription that contains an Azure OpenAI resource named AH.
You build a chatbot that will use AI1 to provide generative answers to specific questions.
You need to ensure that the responses are more creative and less deterministic.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 41
Hotspot
HOTSPOT
You are building an Azure web app named App1 that will translate text from English to Spanish.
You need to use the Text Translation REST API to perform the translation. The solution must ensure that you have data sovereignty in the United States.
How should you complete the URI? To answer, select the appropriate options in the answer area.
https://learn.microsoft.com/en-us/azure/cognitive-services/Translator/reference/v3-0-reference#base-urls Requests to Translator are, in most cases, handled by the datacenter that is closest to where the request originated. If there's a datacenter failure when using the global endpoint, the request may be routed outside of the geography. To force the request to be handled within a specific geography, use the desired geographical endpoint. All requests are processed among the datacenters within the geography. - United States api-nam.cognitive.microsofttranslator.com
https://learn.microsoft.com/en-us/azure/cognitive-services/translator/reference/rest-api- guide - translate Translate specified source language text into the target language text.
Question 42
Single choice
You have an Azure subscription that contains an Azure OpenAI resource.
You plan to build an agent by using the Azure Ai Agent Service.
The agent will perform the following actions:
1. Interpret written and spoken questions from users. 2. Generate answers to the questions. 3. Output the answers as speech.
You need to create the project for the agent.
What should you use?
A
Language Studio
B
Azure Al Foundry
C
Speech studio
D
the Azure portal
Reveal answer detailsClose answer details
Correct answerC
Question 43
Drag & drop
DRAG DROP
You are building a bot.
You need to test the bot in the Bot Framework Emulator. The solution must ensure that you can debug the bot interactively.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Explanation
https://learn.microsoft.com/en-us/azure/bot-service/using-trace-activities?view=azure-bot-service-4.0&tabs=csharp A trace activity is an activity that your bot can send to the Bot Framework Emulator. You can use trace activities to interactively debug a bot, as they allow you to view information about your bot while it runs locally.
Trace activities are sent only to the Emulator and not to any other client or channel. The Emulator displays them in the log but not the main chat panel.
Question 44
Drag & drop
DRAG DROP
You are building a retail chatbot that will use a QnA Maker service.
You upload an internal support document to train the model. The document contains the following question: "What is your warranty period?"
Users report that the chatbot returns the default QnA Maker answer when they ask the following question: "How long is the warranty coverage?"
The chatbot returns the correct answer when the users ask the following question: 'What is your warranty period?"
Both questions should return the same answer.
You need to increase the accuracy of the chatbot responses.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. (Choose three.)
Reveal answer detailsClose answer details
Explanation
Step 1: Add alternative phrasing to the question and answer (QnA) pair. Add alternate questions to an existing QnA pair to improve the likelihood of a match to a user query.
Step 2: Retrain the model. Periodically select Save and train after making edits to avoid losing changes.
Step 3: Republish the model
Note: A knowledge base consists of question and answer (QnA) pairs. Each pair has one answer and a pair contains all the information associated with that answer.
You are building an app that will answer customer calls about the status of an order. The app will query a database for the order details and provide the customers with a spoken response.
You need to identify which Azure AI service APIs to use. The solution must minimize development effort.
Which object should you use for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 46
Single choice
You have an Azure subscription that contains an Anomaly Detector resource.
You deploy a Docker host server named Server 1 to the on-premises network.
You need to host an instance of the Anomaly Detector service on Server 1.
Which parameter should you include in the docker run command?
A
Fluentd
B
Billing
C
Http Proxy
D
Mounts
Reveal answer detailsClose answer details
Correct answerB
Question 47
Single choice
You develop a custom question answering project in Azure Cognitive Service for Language. The project will be used by a chatbot. You need to configure the project to engage in multi-turn conversations.
What should you do?
A
Add follow-up prompts.
B
Enable active learning.
C
Add alternate questions.
D
Enable chit-chat.
Reveal answer detailsClose answer details
Correct answerA
Question 48
Lab simulation
Simulation
You need to add a question pair to the published knowledge base used by a QnA Maker service named QNA12345678. The question must be: `What will be the next version of Windows?` The answer must be: `Windows 11`. To complete this task, sign in to the QnA Maker portal.
Reveal model answerClose model answer
Answer: Windows 11 Step 1: Sign in to the QnA portal, then select the knowledge base to add the QnA pair to. Step 2: On the EDIT page of the knowledge base, select Add QnA pair to add a new QnA pair.
Step 3: In the new QnA pair row, add the required question and answer fields. The other fields are optional. All fields can be changed at any time. Question: What will be the next version of Windows? Step 4: Select Save and train to see predictions including the new QnA pair.
You have an Azure subscription that contains an Azure Al Document Intelligence resource named DM.
You build an app named App1 that analyzes PDF files for handwritten content by using DM.
You need to ensure that App1 will recognize the handwritten content.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 51
Multiple choice
You are building an app by using the Semantic Kernel.
You need to include complex objects in the prompt templates of the app. The solution must support objects that contain sub-properties.
Which two prompt templates can you use? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A
Liquid
B
JSONL
C
Handlebars
D
YAML
E
Semantic Kernel
Reveal answer detailsClose answer details
Correct answersA, E
Question 52
Single choice
You build a Language Understanding model by using the Language Understanding portal.
You export the model as a JSON file as shown in the following sample.
To what does the Weather.Historic entity correspond in the utterance?
A
by month
B
chicago
C
rain
D
location
Reveal answer detailsClose answer details
Correct answerA
Question 53
Single choice
You have an Azure subscription that contains an Azure OpenAI resource named OpenAI1 and a user named User1.
You need to ensure that User1 can upload datasets to OpenAI1 and finetune the existing models. The solution must follow the principle of least privilege.
Which role should you assign to User1?
A
Cognitive Services Contributor
B
Contributor
C
Cognitive Services OpenAI User
D
Cognitive Services OpenAI Contributor
Reveal answer detailsClose answer details
Correct answerD
Question 54
Single choice
You have an Azure subscription that contains a Language service resource named ta1 and a virtual network named vnet1. You need to ensure that only resources in vnet1 can access ta1.
What should you configure?
A
a network security group (NSG) for vnet1
B
Azure Firewall for vnet1
C
the virtual network settings for ta1
D
a Language service container for ta1
Reveal answer detailsClose answer details
Correct answerC
Question 55
Single choice
You successfully run the following HTTP request.
POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups/RG1/providers/Microsoft.CognitiveServices/accounts/contosol/regenerateKey?api-version=2017-04-18
Body{"keyName": "Key2"}
What is the result of the request?
A
A key for Azure Cognitive Services was generated in Azure Key Vault.
B
A new query key was generated.
C
The primary subscription key and the secondary subscription key were rotated.
D
The secondary subscription key was reset.
Reveal answer detailsClose answer details
Correct answerD
Question 56
Hotspot
HOTSPOT
You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must meet the following requirements:
Use a single key and endpoint to access multiple services. Consolidate billing for future services that you
might use. Support the use of Computer Vision in the future.
How should you complete the HTTP request to create the new resource? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 57
Drag & drop
DRAG DROP
You have an Azure subscription that contains a storage account named sa1 and an Azure AI Document Intelligence resource named DI1.
You need to create and train a custom model in DI1 by using Document Intelligence Studio. The solution must minimize development effort.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Reveal answer detailsClose answer details
Question 58
Hotspot
HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 59
Single choice
You are building an app named App1 that will use Azure AI Document Intelligence to extract the following data from scanned documents:
1. Shipping address 2. Billing address 3. Customer ID 4. Amount due 5. Due date 6. Total tax 7. Subtotal
You need to identify which model to use for App1. The solution must minimize development effort.
Which model should you use?
A
custom extraction model
B
contract
C
invoice
D
general document
Reveal answer detailsClose answer details
Correct answerC
Question 60
Single choice
You have an Azure subscription. The subscription contains an Azure OpenAI resource that hosts a GPT- 3.5 Turbo model named Model1.
You configure Model1 to use the following system message: "You are an AI assistant that helps people solve mathematical puzzles. Explain your answers as if the request is by a 4-year-old."
Which type of prompt engineering technique is this an example of?
A
few-shot learning
B
affordance
C
chain of thought
D
priming
Reveal answer detailsClose answer details
Correct answerD
Question 61
Hotspot
HOTSPOT
In Azure OpenAI Studio, you are prototyping a chatbot by using Chat playground.
You need to configure the chatbot to meet the following requirements:
1. Reduce the repetition of words in conversations. 2. Reduce the randomness of each response.
Which two parameters should you modify? To answer, select the appropriate parameters in the answer area.
NOTE: Each correct answer is worth one point.
Reveal answer detailsClose answer details
Question 62
Single choice
You have an app named App1 that uses a custom Azure AI Document Intelligence model to recognize contract documents.
You need to ensure that the model supports an additional contract format. The solution must minimize development effort.
What should you do?
A
Lower the confidence score threshold of App1.
B
Create a new training set and add the additional contract format to the new training set.
C
Add the additional contract format to the existing training set. Retrain the model.
D
Create and train a new custom model.
E
Lower the accuracy threshold of App1.
Reveal answer detailsClose answer details
Correct answerC
Question 63
Single choice
You are building a social media messaging app.
You need to identify in real time the language used in messages.
A
Azure AI Foundry Content Safety
B
Azure AI Speech
C
Azure AI Language
D
Azure AI Translator
Reveal answer detailsClose answer details
Correct answerD
Explanation
For a social media messaging app that needs to determine the language of short text in real time, the most appropriate service is Azure AI Translator. Translator provides a low-latency language detection operation for text, returning the detected language code and a confidence score, and it's optimized for interactive scenarios like chat and messaging. You can use detection on its own or feed the result directly into translation if needed.
Why not the others: Azure AI Speech is for audio (speech-to-text, text-to-speech, speech translation), not text-only language detection. Azure AI Language has language detection within its Text Analytics features, but Translator's detect endpoint is the recommended, streamlined choice for real-time translation pipelines and chat apps. Azure AI Foundry Content Safety is for moderation (toxicity, harassment, hate), not language identification.
Microsoft References Azure AI Translator -- Text Translation overview (includes language detection). https://learn.microsoft.com/azure/ai-services/translator/ Text Translation REST API v3.0 -- Detect operation. https://learn.microsoft.com/azure/ai-services /translator/reference/v3-0-detect Quickstart: Use the Translator text client libraries (shows detect + translate flow). https://learn.microsoft.com/azure/ai-services/translator/quickstart-text-sdk
Question 64
Single choice
You have an Azure Cognitive Search solution and a collection of handwritten letters stored as JPEG files.
You plan to index the collection. The solution must ensure that queries can be performed on the contents of the letters.
You need to create an indexer that has a skillset.
Which skill should you include?
A
image analysis
B
optical character recognition (OCR)
C
key phrase extraction
D
document extraction
Reveal answer detailsClose answer details
Correct answerB
Explanation
To ensure that queries can be performed on the contents of the letters, the skill that should be included in the indexer is optical character recognition (OCR).
Option B, optical character recognition (OCR), is a technology that can recognize text within an image and convert it into machine-readable text. This skill will enable the search engine to read the handwritten letters and convert them into searchable text that can be indexed by Azure Cognitive Search.
Option A, image analysis, is a useful skill for analyzing images to extract metadata, but it does not directly enable text recognition.
Option C, key phrase extraction, extracts important phrases and concepts from text, but it requires the text to be already recognized and extracted by OCR or other text extraction techniques.
Option D, document extraction, is a skill that extracts specific pieces of information from documents, but it does not address the challenge of recognizing and extracting text from handwritten letters.
Question 65
Single choice
You have a local folder that contains the files shown in the following table.
You need to analyze the files by using Azure AI Video Indexer.
Which files can you upload to the Video Indexer website?
A
File1, File2, and File4 only
B
File1 and File2 only
C
File1, File2, and File3 only
D
File1, File2, File3 and File4
E
File1 and File3 only
Reveal answer detailsClose answer details
Correct answerD
Question 66
Hotspot
HOTSPOT
You have an Azure subscription that contains an Azure OpenAI resource named AI1.
You build a chatbot that will use AI1 to provide generative answers to specific questions.
You need to ensure that the responses are more creative and less deterministic.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 67
Hotspot
HOTSPOT
You have 100,000 images.
You need to build an app that will perform the following actions:
1. Identify road signs in the images and generate a short description of each road sign. 2. Analyze the descriptions to generate a report about the different types of road signs and how often each type occurred.
The solution must minimize costs.
What should you use for each action? To answer, select the appropriate options in the answer area.
NOTE; Each correct selection is worth one point.
Reveal answer detailsClose answer details
Question 68
Single choice
You have the following files:
1. File1.pdf 2. File2.jpg 3. File3.docx
4. File4.webp 5. FileS.png
Which files can you analyze by using Azure Al Content Understanding?
A
File1 .pdf and File3.docx only
B
File1.pdf, File2jpg, and File5.png only
C
File1.pdf, File2.jpg. and File3.docx only
D
File1.pdf, File2.jpg. File3.docx, and FileS.png only
E
File1.pdf. File2.jpg, File3.docx. File4.webp, and File5.png
Reveal answer detailsClose answer details
Correct answerD
MICROSOFT
Designing and Implementing a Microsoft Azure AI Solution
You have an Azure OpenAI resource named AI1 that hosts three deployments of the GPT 3.5 model. Each deployment is optimized for a unique workload.
You plan to deploy three apps. Each app will access AI1 by using the REST API and will use the deployment that was optimized for the app's intended workload.
You need to provide each app with access to AI1 and the appropriate deployment. The solution must ensure that only the apps can access AI1.
What should you use to provide access to AI1, and what should each app use to connect to its appropriate deployment? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 2
HOTSPOT
You run the following command.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
Correct Answer:
QUESTION 3
A customer uses Azure Cognitive Search.
The customer plans to enable a server-side encryption and use customer-managed keys (CMK) stored in Azure.
What are three implications of the planned change? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A.
The index size will increase.
B.
Query times will increase.
C.
A self-signed X.509 certificate is required.
D.
The index size will decrease.
E.
Query times will decrease.
F.
Azure Key Vault is required.
Correct Answer: ABF
Explanation
Explanation/Reference:
"Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance." same document also lists Azure Key Vault as a requirement:
You need to ensure that the reading experience is optimized for users who have reduced comprehension and learning differences, such as dyslexia. The solution must minimize development effort.
Which Azure service should you include in the solution?
A.
Azure AI Immersive Reader
B.
Azure AI Translator
C.
Azure AI Document Intelligence
D.
Azure AI Language
Correct Answer: A
QUESTION 5
HOTSPOT
You have an Azure subscription that is linked to a Microsoft Entra tenant. The subscription ID is x1xx11x1- x111-xxxx-xxxx-x1111xxx11x1 and the tenant ID is 1y1y1yyy-1y1y-y1y1-yy11-y1y1y11111y1.
The subscription contains an Azure OpenAI resource named OpenAI1 that has a primary API key of 1111a111a11a111aaa11a1a1a11a11aa. OpenAI1 has a deployment named embeddings1 that uses the text-embedding-ada-002 model.
You need to query OpenAI1 and retrieve embeddings for text input.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 6
HOTSPOT
You are developing an app that will use the Azure AI Vision API to analyze an image.
You need configure the request that will be used by the app to identify whether an image is clipart or a line
drawing.
How should you complete the request? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 7
DRAG DROP
You have a chatbot that uses a QnA Maker application.
You enable active learning for the knowledge base used by the QnA Maker application.
You need to integrate user input into the model.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
Explanation
Explanation/Reference:
Step 1: For the knowledge base, select Show active learning suggestions. In order to see the suggested questions, on the Edit knowledge base page, select View Options, then select Show active learning suggestions.
Step 2: Approve and reject suggestions. ✔ Each QnA pair suggests the new question alternatives with a check mark, , to accept the question or an x to reject the suggestions. Select the check mark to add the question.
Step 3: Save and train the knowledge base. Select Save and Train to save the changes to the knowledge base.
Step 4: Publish the knowledge base.
Select Publish to allow the changes to be available from the GenerateAnswer API.
When 5 or more similar queries are clustered, every 30 minutes, QnA Maker suggests the alternate questions for you to accept or reject.
Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You have a chatbot that uses question answering in Azure Cognitive Service for Language.
Users report that the responses of the chatbot lack formality when answering spurious questions.
You need to ensure that the chatbot provides formal responses to spurious questions.
Solution: From Language Studio, you change the chitchat source to qna_chitchat_professional.tsv, and then retrain and republish the model.
Does this meet the goal?
A.
Yes
B.
No
Correct Answer: A
Explanation
Explanation/Reference:
Formal response, it is Personality = Professional, it is file qna_chitchat_professional.tsv . https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/best-practices#choosing-a-personality
QUESTION 11
Simulation
You need to configure and publish bot12345678 to support task management. The intent must be named TaskReminder. The LUDown for the intent is in the C: \Resources\LU folder. To complete this task, use the Microsoft Bot Framework Composer.
Correct Answer:
Step 1: Open Microsoft Bot Framework Composer Step 2: Select the bot bot12345678 Step 3: Select Import existing resources. Read the instructions on the right side of the screen and select Next.
Step 4: Browse to the C:\Resources\LU folder and select the available .lu file Step 5: In the pop-up window Importing existing resources, modify the JSON file content based on your resources information: Name the intent TaskReminder Step 6: Select Publish from the Composer menu. In the Publish your bots pane, select the bot to publish (bot12345678), then select a publish profile from the Publish target drop-down list.
You are building an agent by using the Azure Al Foundry Agent Service.
You have the following code.
Correct Answer:
Explanation
Explanation/Reference:
The agent will reason over the uploaded file.## The code will create a run and check the output.## The code will create an agent and enable a file search.## The agent will reason over the uploaded file.
Yes: The code includes file = project_client.agents.upload_file_and_poll(file_path="./data/file1.zip", purpose=FilePurpose.AGENTS). The upload_file_and_poll method with FilePurpose.AGENTS suggests that the file (file1.zip) is uploaded for the agent to process, and agents in the Azure AI Foundry Agent Service are typically designed to reason over uploaded data. This indicates the agent will reason over the uploaded file.
The code will create a run and check the output. No: The provided code snippet does not include any explicit call to create a run (e.g., a method like create_run or start_run) or check the output (e.g., a method to retrieve or poll run results). The code only uploads a file and creates a vector store, but it does not initiate or monitor a run.
The code will create an agent and enable a file search. No: The code does not contain a method to create an agent (e.g., create_agent) or explicitly enable a file search. The create_vector_store_and_poll method creates a vector store, which is typically used for indexing data for search, but there is no indication of enabling a file search or creating an agent in this snippet.
QUESTION 13
You need to build a solution that will use optical character recognition (OCR) to scan sensitive documents by using the Computer Vision API. The solution must not be deployed to the public cloud.
What should you do?
A.
Build an on-premises web app to query the Computer Vision endpoint.
B.
Host the Computer Vision endpoint in a container on an on-premises server.
C.
Host an exported Open Neural Network Exchange (ONNX) model on an on-premises server.
D.
Build an Azure web app to query the Computer Vision endpoint.
Correct Answer: B
Explanation
Explanation/Reference:
One option to manage your Computer Vision containers on-premises is to use Kubernetes and Helm. Three primary parameters for all Cognitive Services containers are required. The Microsoft Software License Terms must be present with a value of accept. An Endpoint URI and API key are also needed. Incorrect: Not D: This Computer Vision endpoint would be available for the public, unless it is secured. References: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/deploy-computer-vision-on-premises
QUESTION 14
Your company uses an Azure Cognitive Services solution to detect faces in uploaded images. The method to detect the faces uses the following code.
You discover that the solution frequently fails to detect faces in blurred images and in images that contain sideways faces.
You need to increase the likelihood that the solution can detect faces in blurred images and images that contain sideways faces.
What should you do?
A.
Use a different version of the Face API.
B.
Use the Computer Vision service instead of the Face service.
C.
Use the Identify method instead of the Detect method.
D.
Change the detection model.
Correct Answer: D
Explanation
Explanation/Reference:
Evaluate different models. The best way to compare the performances of the detection models is to use them on a sample dataset. We recommend calling the Face - Detect API on a variety of images, especially images of many faces or of faces that are difficult to see, using each detection model. Pay attention to the number of faces that each model returns.
You are developing an app that will use the Decision and Language APIs.
You need to provision resources for the app. The solution must ensure that each service is accessed by using a single endpoint and credential.
Which type of resource should you create?
A.
Language
B.
Speech
C.
Azure Cognitive Services
D.
Content Moderator
Correct Answer: C
QUESTION 16
You have a product knowledgebase that contains multiple PDF documents.
You need to build a chatbot that will provide responses based on data in the knowledgebase. The solution must minimize development effort and costs.
What should you include in the solution?
A.
Azure Al Language conversational language understanding (CLU)
B.
Azure Al language detection
C.
Azure Al Language custom question answering
D.
Azure OpenAI
Correct Answer: C
QUESTION 17
You are building a chatbot.
You need to configure the chatbot to query a knowledge base.
Which dialog class should you use?
A.
AdaptiveDialog
B.
QnAMakerDialog
C.
ComponentDialog
D.
SkillDialog
Correct Answer: B
QUESTION 18
Simulation
You need to create a Text Analytics service named Text12345678, and then enable logging for Text12345678.
The solution must ensure that any changes to Text12345678 will be stored in a Log Analytics workspace.
To complete this task, sign in to the Azure portal.
Correct Answer:
Step 1: Sign in to the QnA portal. Step 2: Create an Azure Cognitive multi-service resource:
Step 3: On the Create page, provide the following information.
Name: Text12345678
Step 4: Configure additional settings for your resource as needed, read and accept the conditions (as applicable), and then select Review + create. Step 5: Navigate to the Azure portal. Then locate and select The Text Analytics service resource Text12345678 (which you created in Step 4). Step 6: Next, from the left-hand navigation menu, locate Monitoring and select Diagnostic settings. This screen contains all previously created diagnostic settings for this resource. Step 7: Select + Add diagnostic setting. Step 8: When prompted to configure, select the storage account and OMS workspace that you'd like to use to store you diagnostic logs. Note: If you don't have a storage account or OMS workspace, follow the prompts to create one. Step 9: Select Audit, RequestResponse, and AllMetrics. Then set the retention period for your diagnostic log data. If a retention policy is set to zero, events for that log category are stored indefinitely. Step 10: Click Save. It can take up to two hours before logging data is available to query and analyze. So don't worry if you don't see anything right away.
You develop an application that uses the Face API.
You need to add multiple images to a person group.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
Explanation
Explanation/Reference:
Box 1: Stream The File.OpenRead(String) method opens an existing file for reading.
Example: Open the stream and read it back. using (FileStream fs = File.OpenRead(path)) Box 2: AddFaceFromStreamAsync
Step 5 on https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces
Case Study 1
Case Study Questions
Overview
A company named Wide World Importers is developing an e-commerce platform.
You are working with a solutions architect to design and implement the features of the e-commerce platform. The platform will use microservices and a serverless environment built on Azure.
Wide World Importers has a customer base that includes English, Spanish, and Portuguese speakers.
Existing Environment
Applications
Wide World Importers has an App Service plan that contains the web apps shown in the following table.
Azure Resources
You have the following resources:
An Azure Active Directory (Azure AD) tenant - The tenant supports internal authentication. - All employees belong to a group named AllUsers. - Senior managers belong to a group named LeadershipTeam. An Azure Functions resource
- A function app posts to Azure Event Grid when stock levels of a product change between OK, Low Stock, and Out of Stock. The function app uses the Azure Cosmos DB change feed. An Azure Cosmos DB account - The account uses the Core (SQL) API. - The account stores data for the Product Management app and the Inventory Tracking app. An Azure Storage account - The account contains blob containers for assets related to products. - The assets include images, videos, and PDFs. An Azure Cognitive Services resource named wwics A Video Indexer resource named wwivi
Requirements
Business Goals
Wide World Importers wants to leverage AI technologies to differentiate itself from its competitors.
Planned Changes
Wide World Importers plans to start the following projects:
1. A product creation project: Help employees create accessible and multilingual product entries, while expediting product entry creation. 2. A smart e-commerce project: Implement an Azure Cognitive Search solution to display products for customers to browse. 3. A shopping on-the-go project: Build a chatbot that can be integrated into smart speakers to support customers.
Business Requirements
Wide World Importers identifies the following business requirements for all the projects:
1. Provide a multilingual customer experience that supports English, Spanish, and Portuguese. 2. Whenever possible, scale based on transaction volumes to ensure consistent performance. 3. Minimize costs.
Governance and Security Requirements
Wide World Importers identifies the following governance and security requirements:
1. Data storage and processing must occur in datacenters located in the United States. 2. Azure Cognitive Services must be inaccessible directly from the internet.
Accessibility Requirements
Wide World Importers identifies the following accessibility requirements:
1. All images must have relevant alt text. 2. All videos must have transcripts that are associated to the video and included in product descriptions. 3. Product descriptions, transcripts, and all text must be available in English, Spanish, and Portuguese.
Product Creation Requirements
Wide World Importers identifies the following requirements for improving the Product Management app:
1. Minimize how long it takes for employees to create products and add assets. 2. Remove the need for manual translations.
Smart E-Commerce Requirements
Wide World Importers identifies the following requirements for the smart e-commerce project:
1. Ensure that the Cognitive Search solution meets a Service Level Agreement (SLA) of 99.9% availability for searches and index writes.
2. Provide users with the ability to search insight gained from the images, manuals, and videos associated with the products. 3. Support autocompletion and autosuggestion based on all product name variants. 4. Store all raw insight data that was generated, so the data can be processed later. 5. Update the stock level field in the product index immediately upon changes. 6. Update the product index hourly.
Shopping On-the-Go Requirements
Wide World Importers identifies the following requirements for the shopping on-the-go chatbot:
1. Answer common questions. 2. Support interactions in English, Spanish, and Portuguese. 3. Replace an existing FAQ process so that all Q&A is managed from a central location. 4. Provide all employees with the ability to edit Q&As. Only senior managers must be able to publish updates. 5. Support purchases by providing information about relevant products to customers. Product displays must include images and warnings when stock levels are low or out of stock.
Product JSON Sample
You have the following JSON sample for a product.
QUESTION 20
You are developing the smart e-commerce project.
You need to implement autocompletion as part of the Cognitive Search solution.
Which three actions should you perform? Each correct answer presents part of the solution. (Choose three.)
NOTE: Each correct selection is worth one point.
A.
Make API queries to the autocomplete endpoint and include suggesterName in the body.
B.
Add a suggester that has the three product name fields as source fields.
C.
Make API queries to the search endpoint and include the product name fields in the searchFields query parameter.
D.
Add a suggester for each of the three product name fields.
E.
Set the searchAnalyzer property for the three product name variants.
F.
Set the analyzer property for the three product name variants.
Correct Answer: ABF
Explanation
Explanation/Reference:
Scenario: Support autocompletion and autosuggestion based on all product name variants.
A: Call a suggester-enabled query, in the form of a Suggestion request or Autocomplete request, using an API. API usage is illustrated in the following call to the Autocomplete REST API.
POST /indexes/myxboxgames/docs/autocomplete?search&api-version=2020-06-30 { "search": "minecraf", "suggesterName": "sg" }
B: In Azure Cognitive Search, typeahead or "search-as-you-type" is enabled through a suggester. A suggester provides a list of fields that undergo additional tokenization, generating prefix sequences to support matches on partial terms. For example, a suggester that includes a City field with a value for "Seattle" will have prefix combinations of "sea", "seat", "seatt", and "seattl" to support typeahead.
F. Use the default standard Lucene analyzer ("analyzer": null) or a language analyzer (for example, "analyzer": "en.Microsoft") on the field.
You have an Azure subscription that contains an Azure OpenA1 resource named AH.
You plan to build an app named App1 that will write press releases by using AM.
You need to deploy an Azure OpenA1 model for Appl. The solution must minimize development effort.
Which three actions should you perform in sequence in Azure OpenAI Studio? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
QUESTION 22
You are building a chatbot for a travel agent. The bot will ask users for a destination and must repeat the question until a valid input is received, or the user closes the conversation.
Which type of dialog should you use?
A.
prompt
B.
input
C.
adaptive
D.
QnA Maker
Correct Answer: A
Explanation
Explanation/Reference:
https://learn.microsoft.com/en-us/azure/bot-service/bot-builder-concept-dialog?view=azure-bot-service-4.0#dialog-types The dialogs library provides a few types of dialogs to make your bot's conversations easier to manage. - prompt dialogs Ask the user for input and return the result. A prompt will repeat until it gets valid input or it's canceled. They're designed to work with waterfall dialogs.
QUESTION 23
You need to measure the public perception of your brand on social media by using natural language processing.
Which Azure service should you use?
A.
Content Moderator
B.
Form Recognizer
C.
Computer Vision
D.
Language service
Correct Answer: D
QUESTION 24
HOTSPOT
Select the answer that correctly completes the sentence.
Correct Answer:
QUESTION 25
HOTSPOT
You have an Azure subscription that contains an Azure Al Content Safety resource named Resource1.
You create the following cURL command.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth point.
Correct Answer:
QUESTION 26
HOTSPOT
You are designing a conversation flow to be used in a chatbot.
You need to test the conversation flow by using the Microsoft Bot Framework Emulator.
How should you complete the .chat file? To answer, select the appropriate options in the answer area.
You are building an AI solution that will use Sentiment Analysis results from surveys to calculate bonuses for customer service staff.
You need to ensure that the solution meets the Microsoft responsible AI principles.
What should you do?
A.
Add a human review and approval step before making decisions that affect the staff's financial situation.
B.
Include the Sentiment Analysis results when surveys return a low confidence score.
C.
Use all the surveys, including surveys by customers who requested that their account be deleted and their data be removed.
D.
Publish the raw survey data to a central location and provide the staff with access to the location.
Correct Answer: A
QUESTION 28
You have an Azure subscription that contains an Azure Al Document Intelligence resource named Aldoc1.
You have an app named App1 that uses Aldoc1. App1 analyzes business cards by calling business card model v2.1.
You need to update App1 to ensure that the app can interpret QR codes. The solution must minimize administrative effort.
What should you do first?
A.
Deploy a custom model.
B.
Implement the read model.
C.
Upgrade the business card model to v3.0
D.
Implement the contract model
Correct Answer: C
QUESTION 29
Simulation
Use the following login credentials as needed: To enter your username, place your cursor in the Sign in box and click on the username below. To enter your password, place your cursor in the Enter password box and click on the password below.
Azure Password: XXXXXXXXXXXX The following information is for technical support purposes only:
Lab Instance: 12345678
Task You need to create and publish a Language Understanding (classic) model named 1u12345678. The
model will contain an intent of Travel that has an utterance of Boat. To complete this task, sign in to the Language Understanding portal at httptc//www.luis-ai/.
Correct Answer:
Create your LUIS model - 1. You should navigate to your LUIS.ai management portal and create a new application. In the portal create a model.
Model name: 1u12345678 - 2. Define one intent as ג€Travelג€ and add an example utterances of Boat.
3. Publish the model In order to use your model, you have to publish it. This is as easy as hitting the Publish tab, selecting between the production or staging environments, and hitting Publish. As you can see from this page, you can also choose to enable sentiment analysis, speech priming to improve speech recognition, or the spell checker. For now, you can leave those unchecked.
You have a Custom Vision resource named acvdev in a development environment.
You have a Custom Vision resource named acvprod in a production environment.
In acvdev, you build an object detection model named obj1 in a project named proj1.
You need to move obj1 to acvprod.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Contoso, Ltd. is an international accounting company that has offices in France, Portugal, and the United Kingdom.
Contoso has a professional services department that contains the roles shown in the following table.
Existing environment
Infrastructure
Contoso has the following subscriptions:
1. Azure 2. Microsoft 365 3. Microsoft Dynamics 365
Azure Active (Azure AD) Directory
Contoso has Azure Active Directory groups for securing role-based access. The company uses the following group naming conventions:
1. [Country]-[Level]-[Role] 2. [Level]-[Role]
Intellectual Property
Contoso has the intellectual property shown in the following table.
Text-based content is provided only in one language and is not translated.
Requirements
Planned Projects
Contoso plans to develop the following:
1. A document processing workflow to extract information automatically from PDFs and images of financial documents 2. A customer-support chatbot that will answer questions by using FAQs 3. A searchable knowledgebase of all the intellectual property
Technical Requirements
Contoso identifies the following technical requirements:
1. All content must be approved before being published. 2. All planned projects must support English, French, and Portuguese. 3. All content must be secured by using role-based access control (RBAC). 4. RBAC role assignments must use the principle of least privilege. 5. RBAC roles must be assigned only to Azure Active Directory groups. 6. AI solution responses must have a confidence score that is equal to or greater than 70 percent. 7. When the response confidence score of an AI response is lower than 70 percent, the response must be improved by human input.
Chatbot Requirements
Contoso identifies the following requirements for the chatbot:
1. Provide customers with answers to the FAQs. 2. Ensure that the customers can chat to a customer service agent. 3. Ensure that the members of a group named Management-Accountants can approve the FAQs. 4. Ensure that the members of a group named Consultant-Accountants can create and amend the FAQs. 5. Ensure that the members of a group named the Agent-CustomerServices can browse the FAQs. 6. Ensure that access to the customer service agents is managed by using Omnichannel for Customer Service. 7. When the response confidence score is low, ensure that the chatbot can provide other response options to the customers.
Document Processing Requirements
Contoso identifies the following requirements for document processing:
The document processing solution must be able to process standardized financial documents that have the following characteristics: - Contain fewer than 20 pages. - Be formatted as PDF or JPEG files. - Have a distinct standard for each office. The document processing solution must be able to extract tables and text from the financial documents. The document processing solution must be able to extract information from receipt images. Members of a group named Management-Bookkeeper must define how to extract tables from the financial documents. Members of a group named Consultant-Bookkeeper must be able to process the financial documents.
Knowledgebase Requirements
Contoso identifies the following requirements for the knowledgebase:
1. Supports searches for equivalent terms 2. Can transcribe jargon with high accuracy 3. Can search content in different formats, including video 4. Provides relevant links to external resources for further research
QUESTION 31
You are developing the knowledgebase.
You use Azure Video Analyzer for Media (previously Video indexer) to obtain transcripts of webinars.
You need to ensure that the solution meets the knowledgebase requirements.
What should you do?
A.
Create a custom language model
B.
Configure audio indexing for videos only
C.
Enable multi-language detection for videos
D.
Build a custom Person model for webinar presenters
Correct Answer: A
Explanation
Explanation/Reference:
https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-overview Azure Video Indexer supports automatic speech recognition through integration with the Microsoft Custom Speech Service. You can customize the Language model by uploading adaptation text, namely text from the domain whose vocabulary you'd like the engine to adapt to. Once you train your model, new words appearing in the adaptation text will be recognized, assuming default pronunciation, and the Language model will learn new probable sequences of words.
QUESTION 32
You are training a Language Understanding model for a user support system.
You create the first intent named GetContactDetails and add 200 examples.
You need to decrease the likelihood of a false positive.
What should you do?
A.
Enable active learning.
B.
Add a machine learned entity.
C.
Add additional examples to the GetContactDetails intent.
You need to configure bot12345678 support the French (FR-FR) language. Export the bot to C:\Resources\Bot\Bot1.zip. To complete this task, use the Microsoft Bot Framework Composer.
Correct Answer:
Step 1: Open Microsoft Bot Framework Composer Step 2: Select the bot bot12345678 Step 3: Select Configure. Step 4: Select the Azure Language Understanding tab Step 5: Select the Set up Language Understanding button. The Set up Language Understanding window will appear, shown below:
Step 6: Select Use existing resources and then select Next at the bottom of the window. Step 7: Now select the Azure directory, Azure subscription, and Language Understanding resource name (French). Step 8: Select Next on the bottom. Your Key and Region will appear on the next on the next window, shown below:
You are building a transcription service for technical podcasts.
Testing reveals that the service fails to transcribe technical terms accurately.
You need to improve the accuracy of the service.
Which five actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
Explanation
Explanation/Reference:
https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/custom-speech-overview#how-does-it-work With Custom Speech, you can upload your own data, test and train a custom model, compare accuracy between models, and deploy a model to a custom endpoint. - Create a project and choose a model. Use a Speech resource that you create in the Azure portal. If you will train a custom model with audio data, choose a Speech resource region with dedicated hardware for training audio data. - Upload test data. Upload test data to evaluate the speech to text offering for your applications, tools, and products. - Train a model. Provide written transcripts and related text, along with the corresponding audio data. Testing a model before and after training is optional but recommended. - Deploy a model. Once you're satisfied with the test results, deploy the model to a custom endpoint. With the exception of batch transcription, you must deploy a custom endpoint to use a Custom Speech model.
QUESTION 35
DRAG DROP
You have a collection of Microsoft Word documents and PowerPoint presentations in German.
You need to create a solution to translate the files to French. The solution must meet the following requirements:
Preserve the original formatting of the files. Support the use of a custom glossary.
You create a blob container for German files and a blob container for French files. You upload the original files to the container for German files.
Which three actions should you perform in sequence to complete the solution? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
QUESTION 36
HOTSPOT
You have a collection of press releases stored as PDF files.
You need to extract text from the files and perform sentiment analysis.
Which service should you use for each task? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 37
HOTSPOT
Select the answer that correctly completes the sentence.
Correct Answer:
QUESTION 38
HOTSPOT
You have a chatbot that uses the Azure Al Language custom question answering service.
You need to test the chatbot. The solution must ensure that the chatbot responds only when an answer has a confidence score of at least 95 percent.
How should you complete the cURL statement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 39
Simulation
Use the following login credentials as needed: To enter your username, place your cursor in the Sign in box and click on the username below. To enter your password, place your cursor in the Enter password box and click on the password below.
Azure Password: XXXXXXXXXXXX The following information is for technical support purposes only:
Lab Instance: 12345678
Task You plan to analyze stock photography and automatically generate captions for the images. You need to create a service in Azure to analyze the images. The service must be named caption12345678 and must be in the East US Azure region. The solution must use the Free pricing tier. In the C:\Resources\Caption\Params.json folder, enter the value for Key 1 and the endpoint for the new service. To complete this task, sign in to the Azure portal.
Correct Answer:
Step 1: Provision a Cognitive Services resource If you don't already have one in your subscription, you'll need to provision a Cognitive Services resource. 1. Open the Azure portal at https://portal.azure.com, and sign in using the Microsoft account associated with your Azure subscription.
2. Select the Create a resource button, search for cognitive services, and create a Cognitive Services resource with the following settings: Subscription: Your Azure subscription Resource group: Choose or create a resource group (if you are using a restricted subscription, you may not have permission to create a new resource group - use the one provided)
Region: East US Azure region -
Name: caption12345678 -
Pricing tier: Free F0 - 3. Select the required checkboxes and create the resource. Wait for deployment to complete, and then view the deployment details. 4. When the resource has been deployed, go to it and view its Keys and Endpoint page. You will need the endpoint and one of the keys from this page in the next procedure. Step 2: Save Key and Endpoint values in Params.json Open the configuration file, C:\Resources\Caption\Params.json. and update the configuration values it contains to reflect the endpoint and an authentication key for your cognitive services resource. Save your changes.
You have an Azure subscription that contains an Azure OpenAI resource named AH.
You build a chatbot that will use AI1 to provide generative answers to specific questions.
You need to ensure that the responses are more creative and less deterministic.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 41
HOTSPOT
You are building an Azure web app named App1 that will translate text from English to Spanish.
You need to use the Text Translation REST API to perform the translation. The solution must ensure that you have data sovereignty in the United States.
How should you complete the URI? To answer, select the appropriate options in the answer area.
https://learn.microsoft.com/en-us/azure/cognitive-services/Translator/reference/v3-0-reference#base-urls Requests to Translator are, in most cases, handled by the datacenter that is closest to where the request originated. If there's a datacenter failure when using the global endpoint, the request may be routed outside of the geography. To force the request to be handled within a specific geography, use the desired geographical endpoint. All requests are processed among the datacenters within the geography. - United States api-nam.cognitive.microsofttranslator.com
https://learn.microsoft.com/en-us/azure/cognitive-services/translator/reference/rest-api- guide - translate Translate specified source language text into the target language text.
QUESTION 42
You have an Azure subscription that contains an Azure OpenAI resource.
You plan to build an agent by using the Azure Ai Agent Service.
The agent will perform the following actions:
1. Interpret written and spoken questions from users. 2. Generate answers to the questions. 3. Output the answers as speech.
You need to create the project for the agent.
What should you use?
A.
Language Studio
B.
Azure Al Foundry
C.
Speech studio
D.
the Azure portal
Correct Answer: C
QUESTION 43
DRAG DROP
You are building a bot.
You need to test the bot in the Bot Framework Emulator. The solution must ensure that you can debug the bot interactively.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
Explanation
Explanation/Reference:
https://learn.microsoft.com/en-us/azure/bot-service/using-trace-activities?view=azure-bot-service-4.0&tabs=csharp A trace activity is an activity that your bot can send to the Bot Framework Emulator. You can use trace activities to interactively debug a bot, as they allow you to view information about your bot while it runs locally.
Trace activities are sent only to the Emulator and not to any other client or channel. The Emulator displays them in the log but not the main chat panel.
QUESTION 44
DRAG DROP
You are building a retail chatbot that will use a QnA Maker service.
You upload an internal support document to train the model. The document contains the following question: "What is your warranty period?"
Users report that the chatbot returns the default QnA Maker answer when they ask the following question: "How long is the warranty coverage?"
The chatbot returns the correct answer when the users ask the following question: 'What is your warranty period?"
Both questions should return the same answer.
You need to increase the accuracy of the chatbot responses.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. (Choose three.)
Correct Answer:
Explanation
Explanation/Reference:
Step 1: Add alternative phrasing to the question and answer (QnA) pair. Add alternate questions to an existing QnA pair to improve the likelihood of a match to a user query.
Step 2: Retrain the model. Periodically select Save and train after making edits to avoid losing changes.
Step 3: Republish the model
Note: A knowledge base consists of question and answer (QnA) pairs. Each pair has one answer and a pair contains all the information associated with that answer.
You are building an app that will answer customer calls about the status of an order. The app will query a database for the order details and provide the customers with a spoken response.
You need to identify which Azure AI service APIs to use. The solution must minimize development effort.
Which object should you use for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 46
You have an Azure subscription that contains an Anomaly Detector resource.
You deploy a Docker host server named Server 1 to the on-premises network.
You need to host an instance of the Anomaly Detector service on Server 1.
Which parameter should you include in the docker run command?
A.
Fluentd
B.
Billing
C.
Http Proxy
D.
Mounts
Correct Answer: B
QUESTION 47
You develop a custom question answering project in Azure Cognitive Service for Language. The project will be used by a chatbot. You need to configure the project to engage in multi-turn conversations.
What should you do?
A.
Add follow-up prompts.
B.
Enable active learning.
C.
Add alternate questions.
D.
Enable chit-chat.
Correct Answer: A
QUESTION 48
Simulation
You need to add a question pair to the published knowledge base used by a QnA Maker service named QNA12345678. The question must be: `What will be the next version of Windows?` The answer must be: `Windows 11`. To complete this task, sign in to the QnA Maker portal.
Correct Answer:
Answer: Windows 11 Step 1: Sign in to the QnA portal, then select the knowledge base to add the QnA pair to. Step 2: On the EDIT page of the knowledge base, select Add QnA pair to add a new QnA pair.
Step 3: In the new QnA pair row, add the required question and answer fields. The other fields are optional. All fields can be changed at any time. Question: What will be the next version of Windows? Step 4: Select Save and train to see predictions including the new QnA pair.
You have an Azure subscription that contains an Azure Al Document Intelligence resource named DM.
You build an app named App1 that analyzes PDF files for handwritten content by using DM.
You need to ensure that App1 will recognize the handwritten content.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 51
You are building an app by using the Semantic Kernel.
You need to include complex objects in the prompt templates of the app. The solution must support objects that contain sub-properties.
Which two prompt templates can you use? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A.
Liquid
B.
JSONL
C.
Handlebars
D.
YAML
E.
Semantic Kernel
Correct Answer: AE
QUESTION 52
You build a Language Understanding model by using the Language Understanding portal.
You export the model as a JSON file as shown in the following sample.
To what does the Weather.Historic entity correspond in the utterance?
A.
by month
B.
chicago
C.
rain
D.
location
Correct Answer: A
QUESTION 53
You have an Azure subscription that contains an Azure OpenAI resource named OpenAI1 and a user named User1.
You need to ensure that User1 can upload datasets to OpenAI1 and finetune the existing models. The solution must follow the principle of least privilege.
Which role should you assign to User1?
A.
Cognitive Services Contributor
B.
Contributor
C.
Cognitive Services OpenAI User
D.
Cognitive Services OpenAI Contributor
Correct Answer: D
QUESTION 54
You have an Azure subscription that contains a Language service resource named ta1 and a virtual network named vnet1. You need to ensure that only resources in vnet1 can access ta1.
What should you configure?
A.
a network security group (NSG) for vnet1
B.
Azure Firewall for vnet1
C.
the virtual network settings for ta1
D.
a Language service container for ta1
Correct Answer: C
QUESTION 55
You successfully run the following HTTP request.
POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups/RG1/providers/Microsoft.CognitiveServices/accounts/contosol/regenerateKey?api-version=2017-04-18
Body{"keyName": "Key2"}
What is the result of the request?
A.
A key for Azure Cognitive Services was generated in Azure Key Vault.
B.
A new query key was generated.
C.
The primary subscription key and the secondary subscription key were rotated.
D.
The secondary subscription key was reset.
Correct Answer: D
QUESTION 56
HOTSPOT
You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must meet the following requirements:
Use a single key and endpoint to access multiple services. Consolidate billing for future services that you
might use. Support the use of Computer Vision in the future.
How should you complete the HTTP request to create the new resource? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 57
DRAG DROP
You have an Azure subscription that contains a storage account named sa1 and an Azure AI Document Intelligence resource named DI1.
You need to create and train a custom model in DI1 by using Document Intelligence Studio. The solution must minimize development effort.
Which four actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Correct Answer:
QUESTION 58
HOTSPOT
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 59
You are building an app named App1 that will use Azure AI Document Intelligence to extract the following data from scanned documents:
1. Shipping address 2. Billing address 3. Customer ID 4. Amount due 5. Due date 6. Total tax 7. Subtotal
You need to identify which model to use for App1. The solution must minimize development effort.
Which model should you use?
A.
custom extraction model
B.
contract
C.
invoice
D.
general document
Correct Answer: C
QUESTION 60
You have an Azure subscription. The subscription contains an Azure OpenAI resource that hosts a GPT- 3.5 Turbo model named Model1.
You configure Model1 to use the following system message: "You are an AI assistant that helps people solve mathematical puzzles. Explain your answers as if the request is by a 4-year-old."
Which type of prompt engineering technique is this an example of?
A.
few-shot learning
B.
affordance
C.
chain of thought
D.
priming
Correct Answer: D
QUESTION 61
HOTSPOT
In Azure OpenAI Studio, you are prototyping a chatbot by using Chat playground.
You need to configure the chatbot to meet the following requirements:
1. Reduce the repetition of words in conversations. 2. Reduce the randomness of each response.
Which two parameters should you modify? To answer, select the appropriate parameters in the answer area.
NOTE: Each correct answer is worth one point.
Correct Answer:
QUESTION 62
You have an app named App1 that uses a custom Azure AI Document Intelligence model to recognize contract documents.
You need to ensure that the model supports an additional contract format. The solution must minimize development effort.
What should you do?
A.
Lower the confidence score threshold of App1.
B.
Create a new training set and add the additional contract format to the new training set.
C.
Add the additional contract format to the existing training set. Retrain the model.
D.
Create and train a new custom model.
E.
Lower the accuracy threshold of App1.
Correct Answer: C
QUESTION 63
You are building a social media messaging app.
You need to identify in real time the language used in messages.
A.
Azure AI Foundry Content Safety
B.
Azure AI Speech
C.
Azure AI Language
D.
Azure AI Translator
Correct Answer: D
Explanation
Explanation/Reference:
For a social media messaging app that needs to determine the language of short text in real time, the most appropriate service is Azure AI Translator. Translator provides a low-latency language detection operation for text, returning the detected language code and a confidence score, and it's optimized for interactive scenarios like chat and messaging. You can use detection on its own or feed the result directly into translation if needed.
Why not the others: Azure AI Speech is for audio (speech-to-text, text-to-speech, speech translation), not text-only language detection. Azure AI Language has language detection within its Text Analytics features, but Translator's detect endpoint is the recommended, streamlined choice for real-time translation pipelines and chat apps. Azure AI Foundry Content Safety is for moderation (toxicity, harassment, hate), not language identification.
Microsoft References Azure AI Translator -- Text Translation overview (includes language detection). https://learn.microsoft.com/azure/ai-services/translator/ Text Translation REST API v3.0 -- Detect operation. https://learn.microsoft.com/azure/ai-services /translator/reference/v3-0-detect Quickstart: Use the Translator text client libraries (shows detect + translate flow). https://learn.microsoft.com/azure/ai-services/translator/quickstart-text-sdk
QUESTION 64
You have an Azure Cognitive Search solution and a collection of handwritten letters stored as JPEG files.
You plan to index the collection. The solution must ensure that queries can be performed on the contents of the letters.
You need to create an indexer that has a skillset.
Which skill should you include?
A.
image analysis
B.
optical character recognition (OCR)
C.
key phrase extraction
D.
document extraction
Correct Answer: B
Explanation
Explanation/Reference:
To ensure that queries can be performed on the contents of the letters, the skill that should be included in the indexer is optical character recognition (OCR).
Option B, optical character recognition (OCR), is a technology that can recognize text within an image and convert it into machine-readable text. This skill will enable the search engine to read the handwritten letters and convert them into searchable text that can be indexed by Azure Cognitive Search.
Option A, image analysis, is a useful skill for analyzing images to extract metadata, but it does not directly enable text recognition.
Option C, key phrase extraction, extracts important phrases and concepts from text, but it requires the text to be already recognized and extracted by OCR or other text extraction techniques.
Option D, document extraction, is a skill that extracts specific pieces of information from documents, but it does not address the challenge of recognizing and extracting text from handwritten letters.
QUESTION 65
You have a local folder that contains the files shown in the following table.
You need to analyze the files by using Azure AI Video Indexer.
Which files can you upload to the Video Indexer website?
A.
File1, File2, and File4 only
B.
File1 and File2 only
C.
File1, File2, and File3 only
D.
File1, File2, File3 and File4
E.
File1 and File3 only
Correct Answer: D
QUESTION 66
HOTSPOT
You have an Azure subscription that contains an Azure OpenAI resource named AI1.
You build a chatbot that will use AI1 to provide generative answers to specific questions.
You need to ensure that the responses are more creative and less deterministic.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Correct Answer:
QUESTION 67
HOTSPOT
You have 100,000 images.
You need to build an app that will perform the following actions:
1. Identify road signs in the images and generate a short description of each road sign. 2. Analyze the descriptions to generate a report about the different types of road signs and how often each type occurred.
The solution must minimize costs.
What should you use for each action? To answer, select the appropriate options in the answer area.
NOTE; Each correct selection is worth one point.
Correct Answer:
QUESTION 68
You have the following files:
1. File1.pdf 2. File2.jpg 3. File3.docx
4. File4.webp 5. FileS.png
Which files can you analyze by using Azure Al Content Understanding?
A.
File1 .pdf and File3.docx only
B.
File1.pdf, File2jpg, and File5.png only
C.
File1.pdf, File2.jpg. and File3.docx only
D.
File1.pdf, File2.jpg. File3.docx, and FileS.png only
E.
File1.pdf. File2.jpg, File3.docx. File4.webp, and File5.png
