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 remove all the chit-chat question and answer pairs, and then retrain and republish the model.
Does this meet the goal?
A. Yes
B. No
Show Answer
Correct Answer: B
Explanation: Removing all chit-chat Q&A pairs does not ensure formal responses; it eliminates chit-chat altogether rather than controlling tone. Azure Question Answering provides predefined chit-chat personalities (such as Professional) specifically to enforce a formal style for spurious or chit-chat questions. Therefore, the proposed solution does not meet the goal.
Question 126
You have an Azure subscription that contains an Anomaly Detector resource.
You deploy a Docker host server named Server1 to the on-premises network.
You need to host an instance of the Anomaly Detector service on Server1.
Which parameter should you include in the docker run command?
A. Fluentd
B. Billing
C. Http Proxy
D. Mounts
Show Answer
Correct Answer: B
Explanation: When running Azure Anomaly Detector as a Docker container, Microsoft requires specific environment parameters for the container to start: Eula=accept, ApiKey, and Billing. The Billing parameter links the on‑premises container to the Azure Cognitive Services endpoint for metering and billing. Without Billing, the container will not run. Other options (Fluentd, Http Proxy, Mounts) are optional or unrelated.
Question 127
HOTSPOT
-
You have a chatbot.
You need to test the bot by using the Bot Framework Emulator. The solution must ensure that you are prompted for credentials when you sign in to the bot.
Which three settings should you configure? To answer, select the appropriate settings in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Enter the local path to ngrok
Enable Run ngrok when the Emulator starts up
Enable Use version 1.0 authentication tokens
Explanation: OAuth sign-in testing requires a public callback endpoint. Configuring and running ngrok exposes the local bot to the internet, and enabling v1.0 authentication tokens ensures the Emulator prompts for credentials during sign-in.
Question 128
You are building a flight booking bot by using the Microsoft Bot Framework SDK.
The bot will ask users for the departure date. The bot must repeat the question until a valid date is given, or the users cancel the transaction.
Which type of dialog should you use?
A. prompt
B. adaptive
C. waterfall
D. action
Show Answer
Correct Answer: A
Explanation: In the Microsoft Bot Framework, a Prompt dialog is specifically designed to ask for a particular type of input (such as a date) and automatically re-prompt the user until valid input is provided or the dialog is canceled. DatePrompt includes built-in validation and retry behavior, which exactly matches the requirement to repeat the question until a valid departure date is given or the user cancels. Waterfall dialogs orchestrate multiple steps but rely on prompts to handle validated, repeatable user input.
Question 129
HOTSPOT
-
You have a bot that was built by using the Microsoft Bot Framework composer 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.
Show Answer
Correct Answer: identify New York as a city entity
Language Understanding Intent recognized
Explanation: The utterance matches a GetWeather trigger phrase with a city entity, so New York is extracted as the city. The dialog is started by a Language Understanding intent being recognized.
Question 130
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.
Show Answer
Correct Answer: In the code for the bot, create a new trace activity.
In the code for the bot, send a trace activity.
Run the bot app on a local host.
Explanation: To debug interactively in the Bot Framework Emulator, the bot must include trace activity logic first. You then send the trace activity from the bot code, and finally run the bot locally so the Emulator can connect and display the trace output.
Question 132
You develop a Conversational Language Understanding model by using Language Studio.
During testing, users receive incorrect responses to requests that do NOT relate to the capabilities of the model.
You need to ensure that the model identifies spurious requests.
What should you do?
A. Enable active learning.
B. Add entities.
C. Add examples to the None intent.
D. Add examples to the custom intents.
Show Answer
Correct Answer: C
Explanation: Requests that do not relate to the model’s capabilities are out-of-scope utterances. In Conversational Language Understanding, these should be handled by the None intent. Adding representative examples to the None intent trains the model to recognize spurious or irrelevant requests and avoid mapping them to custom intents, reducing incorrect responses.
Question 133
HOTSPOT
-
You have a chatbot.
You need to ensure that the bot conversation resets if a user fails to respond for 10 minutes.
How should you complete the code? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: send_activity
clear_state
Explanation: When the inactivity threshold is exceeded, the bot must send a new message to the user, which is done with send_activity(). To reset the conversation and start over, all stored conversation data must be removed using conversation_state.clear_state(turn_context).
Question 134
DRAG DROP
-
You are building a customer support chatbot.
You need to configure the bot to identify the following:
• Code names for internal product development
• Messages that include credit card numbers
The solution must minimize development effort.
Which Azure Cognitive Service for Language feature should you use for each requirement? To answer, drag the appropriate features to the correct requirements. Each feature may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Show Answer
Correct Answer: Identify code names for internal product development:
Custom named entity recognition (NER)
Identify messages that include credit card numbers:
Personally Identifiable Information (PII) detection
Explanation: Internal code names are domain-specific and require training a custom entity model. Credit card numbers are a standard sensitive data type already supported by built-in PII detection, minimizing development effort.
Question 135
DRAG DROP
-
You have a question answering project in Azure Cognitive Service for Language.
You need to move the project to a Language service instance in a different Azure region.
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.
Show Answer
Correct Answer: From the original Language service instance, export the existing project.
From the new Language service instance, import the project file.
From the new Language service instance, train and publish the model.
Explanation: Projects are moved across regions by exporting from the source instance and importing into the target instance. After import, the model must be retrained and published in the new Language service instance before it can be used.
$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.
