AI-102 practice questions 251–260

1. Question 251 · 328 in bank

   You create a bot by using the Microsoft Bot Framework SDK. You need to configure the bot to respond to events by using custom text responses. What should you use?

   • Aa dialog
   • Ban activity handler
   • Can adaptive card
   • Da skill

   Show answer

   Answer: B

   Explanation

   B is the correct answer as explained by ChatGPT : B. An activity handler is the correct choice for configuring the bot to respond to events by using custom text responses. An activity handler is a class in the Bot Framework SDK that processes incoming activities (e.g., messages, events, etc.) from the user and generates outgoing activities (e.g., replies). By overriding the OnMessageActivityAsync method of the activity handler, you can provide custom logic for responding to user messages.

   Source: Adapted from community discussion — marti_tremblay000

   References

   • Microsoft Learn

   Next question

2. Question 252 · 328 in bank

   HOTSPOT - You build a bot named app1 by using the Microsoft Bot Framework. You prepare app1 for deployment. You need to deploy app1 to Azure. How should you complete the command? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   webapp config-zip See command az webapp deployment source config-zip --resource-group " " --name " " --src " " at https://learn.microsoft.com/en-us/azure/bot-service/provision-and-publish-a-bot?view=azure-bot-service-4.0&tabs=userassigned%2Ccsharp#publish-your-bot-to-azure

   Source: Adapted from community discussion — james2033

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

3. Question 253 · 328 in bank

   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_friendly.tsv, and then retrain and republish the model. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: B

   Explanation

   The qna_chitchat_professional.tsv is specifically designed to provide responses with a formal tone compared to other chitchat sources. It contains a curated set of question-and-answer pairs that are structured to reflect a professional and formal manner of communication. This makes it more suitable for environments or user interactions where formal responses are preferred, ensuring that the chatbot's replies to spurious or off-topic questions maintain the desired level of professionalism.

   Source: Adapted from community discussion — evangelist

   References

   • Microsoft Learn

   Next question

4. Question 254 · 328 in bank

   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 modify the question and answer pairs for the custom intents, and then retrain and republish the model. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: B

   Explanation

   No, this solution does not meet the goal. The formality of responses to spurious questions is not controlled by modifying the question and answer pairs for the custom intents in Language Studio. These pairs are used to train the model to understand and respond to specific intents, not to control the tone or formality of the responses. To ensure that the chatbot provides formal responses to spurious questions, you would need to adjust the chatbot's response templates or scripts, not the question and answer pairs for the custom intents. This might involve programming the chatbot to use more formal language in its responses, or to respond to unrecognized or spurious inputs with a standard, formal message.

   Source: Adapted from community discussion — EliteAllen

   References

   • Microsoft Learn

   Next question

5. Question 255 · 328 in bank

   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?

   • AYes
   • BNo

   Show answer

   Answer: A

   Explanation

   ChatGPT answer : Yes, changing the chitchat source to "qna_chitchat_professional.tsv" and retraining and republishing the model can meet the goal of ensuring that the chatbot provides formal responses to spurious questions. The "qna_chitchat_professional.tsv" file is a source file for professional chitchat, which includes conversational responses for formal topics, such as business and finance. This file is designed to provide more formal responses to chitchat questions, so changing the source file to this file and retraining the model can improve the formality of responses to spurious questions.

   Source: Adapted from community discussion — marti_tremblay000

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

6. Question 256 · 328 in bank

   Select 3

   You create five bots by using Microsoft Bot Framework Composer. You need to make a single bot available to users that combines the bots. The solution must support dynamic routing to the bots based on user input. Which three actions should you perform? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

   • ACreate a composer extension.
   • BChange the Recognizer/Dispatch type.
   • CCreate an Orchestrator model.
   • DEnable WebSockets.
   • ECreate a custom recognizer JSON file.
   • FInstall the Orchestrator package.

   Show answer

   Answer: BCF

   Explanation

   https://learn.microsoft.com/en-us/composer/how-to-create-orchestrator-bot#add-orchestrator-in-package-manager Orchestrator isn't a default feature in Composer. To use Orchestrator, first add the Orchestrator package to your bot. Composer will download the latest Orchestrator model and make it available to your bot. On the Choose a recognizer type page, select Orchestrator (Intents only) and select Done to change the recognizer.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn

   Next question

7. Question 257 · 328 in bank

   Select 2

   You are building a multilingual chatbot. You need to send a different answer for positive and negative messages. Which two Language service APIs should you use? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

   • ALinked entities from a well-known knowledge base
   • BSentiment Analysis
   • CKey Phrases
   • DDetect Language
   • ENamed Entity Recognition

   Show answer

   Answer: BD

   Next question

8. Question 258 · 328 in bank

   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 are building a chatbot that will use question answering in Azure Cognitive Service for Language. You have a PDF named Doc1.pdf that contains a product catalogue and a price list. You upload Doc1.pdf and train the model. During testing, users report that the chatbot responds correctly to the following question: What is the price of ? The chatbot fails to respond to the following question: How much does cost? You need to ensure that the chatbot responds correctly to both questions. Solution: From Language Studio, you add alternative phrasing to the question and answer pair, and then retrain and republish the model. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: A

   Explanation

   Yes adding alternative phrasing to the question and answer pair in Azure Cognitive Service for Language, then retraining and republishing the model, meets the goal. This approach allows the model to understand and respond to variations in how questions are asked, improving its ability to correctly answer questions with similar meanings but different wordings.

   Source: Adapted from community discussion — evangelist

   References

   • Microsoft Learn
   • Microsoft Learn

   Next question

9. Question 259 · 328 in bank

   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 are building a chatbot that will use question answering in Azure Cognitive Service for Language. You have a PDF named Doc1.pdf that contains a product catalogue and a price list. You upload Doc1.pdf and train the model. During testing, users report that the chatbot responds correctly to the following question: What is the price of ? The chatbot fails to respond to the following question: How much does cost? You need to ensure that the chatbot responds correctly to both questions. Solution: From Language Studio, you enable chit-chat, and then retrain and republish the model. Does this meet the goal?

   • AYes
   • BNo

   Show answer

   Answer: B

   Next question

10. Question 260 · 328 in bank

    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 are building a chatbot that will use question answering in Azure Cognitive Service for Language. You have a PDF named Doc1.pdf that contains a product catalogue and a price list. You upload Doc1.pdf and train the model. During testing, users report that the chatbot responds correctly to the following question: What is the price of ? The chatbot fails to respond to the following question: How much does cost? You need to ensure that the chatbot responds correctly to both questions. Solution: From Language Studio, you create an entity for price, and then retrain and republish the model. Does this meet the goal?

    • AYes
    • BNo

    Show answer

    Answer: B

    Explanation

    B. No Creating an entity for price and retraining the model in Language Studio is not the correct approach to solve the issue with Azure Cognitive Service for Language's question-answering capabilities. Instead, you should use Language Studio to create and train a synonym for the term "price" or build a more comprehensive list of question variations that the chatbot should be able to handle. For example, you can include phrases like "How much does it cost?" or "What is the cost of?" to ensure the model can properly recognize and respond to different ways users might ask about the price. Retrain and republish the model after making these changes to improve the chatbot's ability to answer both questions correctly.

    Source: Adapted from community discussion — kail85

    References

    • Microsoft Learn

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AI-102 practice, question 251. 328 questions available.