HOTSPOT
-
You are building a model to detect objects in images.
The performance of the model based on training data is shown in the following exhibit.
Use the drop-down menus to select the answer choice that completes each statement based on the information presented in the graphic.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: 0%
25%
Explanation: Precision is 100%, so false positives are 0%. Recall equals true positives divided by true positives plus false negatives, which is shown as 25%.
Question 7
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 an Azure subscription that contains an Azure OpenAI resource named AI1 and an Azure AI Content Safety resource named CS1.
You build a chatbot that uses AI1 to provide generative answers to specific questions and CS1 to check input and output for objectionable content.
You need to optimize the content filter configurations by running tests on sample questions.
Solution: From Content Safety Studio, you use the Safety metaprompt feature to run the tests.
Does this meet the requirement?
A. Yes
B. No
Show Answer
Correct Answer: B
Explanation: The Safety metaprompt feature in Content Safety Studio is used to guide or constrain model behavior with safety instructions, not to test or tune content filter configurations using sample inputs and outputs. Testing and optimizing content filters requires moderation/testing features, not safety metaprompts. Therefore, the solution does not meet the requirement.
Question 7
DRAG DROP
-
You build a bot by using the Microsoft Bot Framework SDK.
You need to test the bot interactively on a local machine.
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.
NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct orders you select.
Show Answer
Correct Answer: Build and run the bot
Open the Bot Framework Emulator
Connect to the bot endpoint
Explanation: To test a bot locally, the bot must be running first. The Bot Framework Emulator is then opened to simulate a client, and finally it connects to the local bot endpoint to enable interactive testing.
Question 8
DRAG DROP
-
You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1 and a storage account named sa1. The sa1 account contains a blob container named blob1 and an Azure Files share named share1.
You plan to build a custom model named Model1 in DI1.
You create sample forms and JSON files for Model1.
You need to train Model1 and retrieve the ID of 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.
NOTE: More than one order of answer choices is correct. You will receive credit for any of the correct orders you select.
Show Answer
Correct Answer: Upload the forms and JSON files to blob1.
Create a shared access signature (SAS) URL for blob1.
Call the Build model REST API function.
Call the Get model REST API function.
Explanation: Custom model training in Azure AI Document Intelligence requires training data in an Azure Blob container. A SAS URL grants DI1 access to the blobs. The Build model API trains the model, and the Get model API retrieves the trained model information, including the model ID.
Question 8
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.
NOTE: Each correct selection is worth one point.
Hot Area:
Show Answer
Correct Answer: Typing
carousel
adaptivecard
Explanation: Typing activity is used with a delay to simulate the bot thinking.
Multiple image attachments are displayed using a carousel layout.
The detailed item response is best sent as an Adaptive Card.
Question 9
HOTSPOT
-
You have an Azure subscription.
You plan to build a solution that will analyze scanned documents and export relevant fields to a database.
You need to recommend an Azure AI Document Intelligence model for the following types of documents:
• Expenditure request authorization forms
• Structured and unstructured survey forms
• Structured employment application forms
The solution must minimize development effort and costs.
Which type of model should you recommend for each document type? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Explanation: Custom template fits repeatable authorization forms with limited training. Prebuilt contract already extracts common applicant-style entities with minimal setup. Custom neural handles mixed structured/unstructured surveys and varying layouts best while avoiding multiple templates.
Question 9
DRAG DROP -
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.
Select and Place:
Show Answer
Correct Answer: Use the GetProjects endpoint on acvdev.
Use the ExportProject endpoint on acvdev.
Use the ImportProject endpoint on acvprod.
Explanation: To move a Custom Vision model between resources, you first identify the project in the source resource, export the entire project (which includes the trained model and iterations) from development, and then import it into the production resource.
Question 10
You have an Azure subscription that contains an Azure OpenAI resource named AI1.
You build a chatbot that uses AI1 to provide generative answers to specific questions.
You need to ensure that the chatbot checks all input and output for objectionable content.
Which type of resource should you create first?
A. Microsoft Defender Threat Intelligence (Defender TI)
B. Azure AI Content Safety
C. Log Analytics
D. Azure Machine Leaning
Show Answer
Correct Answer: B
Explanation: Azure AI Content Safety is specifically designed to analyze and filter both input prompts and AI-generated outputs for harmful, unsafe, or objectionable content. It integrates directly with Azure OpenAI workloads to enforce content moderation policies. The other options do not provide content moderation capabilities for generative AI.
Question 10
HOTSPOT -
You are building a chatbot that will provide information to users as shown in the following exhibit.
Use the drop-down menus to select the answer choice that completes each statement based on the information presented in the graphic.
NOTE: Each correct selection is worth one point.
Hot Area:
Show Answer
Correct Answer: an Adaptive Card
an image
Explanation: The displayed chatbot content shows a complex, structured layout with formatted text, icons, dates, and currency, which matches an Adaptive Card rather than Hero or Thumbnail cards. The visual flight itinerary is rendered as a single image element within the card, not an image group, media, or action set.
Question 11
You have an Azure subscription and 10,000 ASCII files.
You need to identify files that contain specific phrases. The solution must use cosine similarity.
Which Azure OpenAI model should you use?
A. text-embedding-ada-002
B. GPT-4
C. GPT-35 Turbo
D. GPT-4-32k
Show Answer
Correct Answer: A
Explanation: The requirement is to identify files containing specific phrases using cosine similarity. Cosine similarity operates on vector embeddings, so an embedding model is required. text-embedding-ada-002 is designed to convert text into numerical vectors optimized for similarity search and semantic matching. GPT-4, GPT-35 Turbo, and GPT-4-32k are generative models, not embedding models, and are not suitable for cosine similarity–based search.
$19
Get all 278 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.