Guide (New 2026) Actual Microsoft AI-900 Exam Questions [Q46-Q70]

Guide (New 2026) Actual Microsoft AI-900 Exam Questions

AI-900 Exam Dumps Pass with Updated 2026 Certified Exam Questions

NEW QUESTION # 46
Select the answer that correctly completes the sentence.

Answer:

Explanation:

Explanation:

NEW QUESTION # 47
You need to develop a web-based AI solution for a customer support system. Users must be able to interact with a web app that will guide them to the best resource or answer.
Which service should you use?

A. QnA Maker
B. Custom Vision
C. Translator Text
D. Face

Answer: A

Explanation:
Explanation
QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a knowledge base by extracting questions and answers from your semistructured content, including FAQs, manuals, and documents. Answer users' questions with the best answers from the QnAs in your knowledge base-automatically. Your knowledge base gets smarter, too, as it continually learns from user behavior.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/qna-maker/

NEW QUESTION # 48
To complete the sentence, select the appropriate option in the answer area.

Answer:

Explanation:

Explanation:

According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore natural language processing (NLP) in Azure", Natural Language Processing (NLP) is a branch of artificial intelligence that focuses on enabling computers to understand, interpret, and generate human language. NLP is used to extract meaning and intent from text or speech, perform sentiment analysis, identify entities, and classify content based on context.
One of the primary applications of NLP is text classification, where an AI model automatically categorizes text documents or messages into predefined classes. Classifying emails as work-related or personal is a textbook example of this NLP capability. It involves analyzing the words, phrases, and structure of the text to determine the email's category. Microsoft Learn highlights this type of problem as document classification, an essential NLP use case often implemented through Azure Cognitive Services such as Text Analytics or Language Studio.
Let's examine why the other options are incorrect:
* Predict the number of future car rentals - This is a time series forecasting or regression task, not NLP.
* Predict which website visitors will make a transaction - This is a predictive analytics or machine learning classification problem based on behavioral data, not language understanding.
* Stop a process in a factory when extremely high temperatures are registered - This relates to IoT automation or sensor-based anomaly detection, not NLP.
Therefore, based on Microsoft's AI-900 materials, Natural Language Processing is best used for tasks involving understanding and classifying text, such as classifying email messages as work-related or personal.
This example perfectly aligns with NLP's goal-to enable machines to process and derive insights from human language inputs.

NEW QUESTION # 49
To complete the sentence, select the appropriate option in the answer area.

Answer:

Explanation:

Explanation:
Features

NEW QUESTION # 50
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Explanation

Box 1: Yes
Automated machine learning, also referred to as automated ML or AutoML, is the process of automating the time consuming, iterative tasks of machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and productivity all while sustaining model quality.
Box 2: No
Box 3: Yes
During training, Azure Machine Learning creates a number of pipelines in parallel that try different algorithms and parameters for you. The service iterates through ML algorithms paired with feature selections, where each iteration produces a model with a training score. The higher the score, the better the model is considered to
"fit" your data. It will stop once it hits the exit criteria defined in the experiment.
Box 4: No
Apply automated ML when you want Azure Machine Learning to train and tune a model for you using the target metric you specify.
The label is the column you want to predict.
Reference:
https://azure.microsoft.com/en-us/services/machine-learning/automatedml/#features

NEW QUESTION # 51
Match the types of AI workloads to the appropriate scenarios.
To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Reference:
https://docs.microsoft.com/en-us/learn/paths/get-started-with-artificial-intelligence-on-azure/

NEW QUESTION # 52
You plan to use Azure Cognitive Services to develop a voice controlled personal assistant app.
Match the Azure Cognitive Services to the appropriate tasks.
To answer, drag the appropriate service from the column on the left to its description on the right Each service may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Explanation:
A screenshot of a computer Description automatically generated

NEW QUESTION # 53
In which two scenarios can you use a speech synthesis solution? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.

A. generating live captions for a news broadcast
B. extracting key phrases from the audio recording of a meeting
C. an Al character in a computer game that speaks audibly to a player
D. an automated voice that reads back a credit card number entered into a telephone by using a numeric keypad

Answer: C,D

Explanation:
According to the Microsoft Learn module "Explore speech capabilities of Azure AI" and the AI-900 Official Study Guide, speech synthesis (also known as text-to-speech) is the process of converting written text into spoken audio output. Azure's Speech service provides this functionality, allowing applications to produce human-like voices dynamically.
Let's evaluate each scenario:
* A. Automated voice that reads back a credit card number entered into a telephone keypad # YesThis is a classic text-to-speech (TTS) use case. The application converts numeric or textual input (such as a credit card number) into audio output that the caller hears. Azure Speech service can handle such voice responses in automated phone systems or IVR (Interactive Voice Response) setups.
* B. Generating live captions for a news broadcast # NoThis is a speech-to-text scenario (speech recognition), not speech synthesis. It involves converting audio speech into written text.
* C. Extracting key phrases from an audio recording of a meeting # NoThis involves speech-to-text followed by text analytics, not speech synthesis.
* D. An AI character in a computer game that speaks audibly to a player # YesThis is a direct example of speech synthesis, where the character's dialog text is converted into realistic spoken output for immersive interaction.
Therefore, based on Microsoft's AI-900 curriculum, speech synthesis is used in applications that convert text into audible speech, such as automated voice systems or interactive digital characters.

NEW QUESTION # 54
You build a machine learning model by using the automated machine learning user interface (UI).
You need to ensure that the model meets the Microsoft transparency principle for responsible AI.
What should you do?

A. Set Max concurrent iterations to 0.
B. Set Validation type to Auto.
C. Enable Explain best model.
D. Set Primary metric to accuracy.

Answer: C

Explanation:
Explanation
Model Explain Ability.
Most businesses run on trust and being able to open the ML "black box" helps build transparency and trust. In heavily regulated industries like healthcare and banking, it is critical to comply with regulations and best practices. One key aspect of this is understanding the relationship between input variables (features) and model output. Knowing both the magnitude and direction of the impact each feature (feature importance) has on the predicted value helps better understand and explain the model. With model explain ability, we enable you to understand feature importance as part of automated ML runs.
Reference:
https://azure.microsoft.com/en-us/blog/new-automated-machine-learning-capabilities-in-azure-machine-learning

NEW QUESTION # 55
To complete the sentence, select the appropriate option in the answer area.

Answer:

Explanation:

NEW QUESTION # 56
You plan to build a conversational Al solution that can be surfaced in Microsoft Teams. Microsoft Cortana, and Amazon Alex a. Which service should you use?

A. Speech
B. Language service
C. Azure Bot Service
D. Azure Cognitive Search

Answer: C

NEW QUESTION # 57
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Reference:
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-overview-introduction?view=azure-bot-service-4.0

NEW QUESTION # 58
Select the answer that correctly completes the sentence.

Answer:

Explanation:

NEW QUESTION # 59
To complete the sentence, select the appropriate option in the answer area.

Answer:

Explanation:

Explanation:
Reliability and safety: To build trust, it's critical that AI systems operate reliably, safely, and consistently under normal circumstances and in unexpected conditions. These systems should be able to operate as they were originally designed, respond safely to unanticipated conditions, and resist harmful manipulation.
Reference:
https://docs.microsoft.com/en-us/learn/modules/responsible-ai-principles/4-guiding-principles

NEW QUESTION # 60
What is an example of a Microsoft responsible Al principle?

A. Al systems should use black-box models.
B. Al systems should treat people fairly.
C. Al systems should NOT reveal the details of their design.
D. Al systems should protect the interests of developers.

Answer: B

NEW QUESTION # 61
You are building a Language Understanding model for an e-commerce business.
You need to ensure that the model detects when utterances are outside the intended scope of the model.
What should you do?

A. Create a prebuilt task entity
B. Add utterances to the None intent
C. Test the model by using new utterances
D. Create a new model

Answer: B

Explanation:
Explanation
The None intent is filled with utterances that are outside of your domain.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/LUIS/luis-concept-intent

NEW QUESTION # 62
To complete the sentence, select the appropriate option in the answer area.

Answer:

Explanation:

Explanation:

Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately extract text, key/value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your documents, both on-premises and in the cloud.
Turn forms into usable data at a fraction of the time and cost, so you can focus more time acting on the information rather than compiling it.
Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/form-recognizer/

NEW QUESTION # 63
When training a model, why should you randomly split the rows into separate subsets?

A. to train the model twice to attain better accuracy
B. to train multiple models simultaneously to attain better performance
C. to test the model by using data that was not used to train the model

Answer: C

Explanation:
Explanation
The goal is to produce a trained (fitted) model that generalizes well to new, unknown data. The fitted model is evaluated using "new" examples from the held-out datasets (validation and datasets) to estimate the model's accuracy in classifying new
https://en.wikipedia.org/wiki/Training,_validation,_and_test_sets#:~:text=Training%20dataset,- A%20training%20dataset&text=The%20goal%20is%20to%20produce,accuracy%20in%20classifying%20new%

NEW QUESTION # 64
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Reference:
https://docs.microsoft.com/en-gb/azure/cognitive-services/text-analytics/overview
https://azure.microsoft.com/en-gb/services/cognitive-services/speech-services/
https://docs.microsoft.com/en-us/learn/modules/analyze-text-with-text-analytics-service/2-get-started-azure

NEW QUESTION # 65
Select the answer that correctly completes the sentence.

Answer:

Explanation:

Explanation:
Azure Kubernetes Service (AKS).
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn documentation on Azure Machine Learning, the Azure Kubernetes Service is commonly used to host and deploy machine learning models, including Automated ML models, into production environments. Once a model is trained using Azure Machine Learning (Azure ML), it must be deployed as a web service endpoint so it can receive data and return predictions.
Azure ML offers two primary options for hosting and deploying models:
* Azure Kubernetes Service (AKS) - for high-scale, production-grade deployments that require fast response times, high availability, and scalability.
* Azure Container Instances (ACI) - for testing or low-scale workloads where cost and simplicity are more important than performance.
AKS provides a managed Kubernetes cluster that allows for automated container orchestration, load balancing, scaling, and monitoring of deployed machine learning models. When you use Automated ML in Azure ML Studio, the generated model can be containerized and deployed directly to AKS, making it accessible as a REST API endpoint. This enables applications, systems, or users to send data and receive predictions in real time.
The other options serve different purposes:
* Azure Data Factory is used for data integration and pipeline orchestration, not model hosting.
* Azure Automation focuses on automating administrative tasks and runbooks, not ML deployment.
* Azure Logic Apps is used to automate workflows and integrate services, not to serve ML models.
Therefore, the correct service to host automated machine learning (AutoML) models in production is Azure Kubernetes Service (AKS), as it provides a reliable, scalable, and secure environment for real-time inference and enterprise AI workloads.

NEW QUESTION # 66
correctly completes the sentence.

Answer:

Explanation:

NEW QUESTION # 67
For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point.

Answer:

Explanation:

NEW QUESTION # 68
Match the facial recognition tasks to the appropriate questions.
To answer, drag the appropriate task from the column on the left to its question on the right. Each task may be used once, more than once, or not at all.
NOTE: Each correct selection is worth one point.

Answer:

Explanation:

Reference:
https://azure.microsoft.com/en-us/services/cognitive-services/face/#features

NEW QUESTION # 69
Match the Azure Al service to the appropriate actions.
To answer, drag the appropriate service from the column on the left to its action on the right Each service may be used once, more than once, or not at all.
NOTE: Each correct match is worth one point.