Free AI-900 Questions for Microsoft Azure AI Fundamentals AI-900 Exam as PDF & Practice Test Engine
Which parameter should you configure to produce more verbose responses from a chat solution that uses the Azure OpenAI GPT-3.5 model?
Correct Answer: D
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
Your website has a chatbot to assist customers.
You need to detect when a customer is upset based on what the customer types in the chatbot.
Which type of AI workload should you use?
You need to detect when a customer is upset based on what the customer types in the chatbot.
Which type of AI workload should you use?
Correct Answer: A
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
NOTE: Each correct selection is worth one point.
Correct Answer:
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Azure Machine Learning documentation, Automated Machine Learning (AutoML) is a feature designed to help users build, train, and tune machine learning models automatically without requiring deep knowledge of programming or data science.
* First Statement: "Automated machine learning provides you with the ability to include custom Python scripts in a training pipeline."This is False (No). AutoML automates the model selection and tuning process but does not allow the inclusion of custom Python scripts within its workflow. Custom Python integration is supported in Azure Machine Learning designer pipelines or SDK-based training, not in AutoML.
* Second Statement: "Automated machine learning implements machine learning solutions without the need for programming experience."This is True (Yes). One of AutoML's core benefits is that it enables non-programmers to train and evaluate models by simply selecting data, choosing a target column, and letting Azure automatically test algorithms and hyperparameters. This aligns with Microsoft's AI-900 objective to democratize AI development.
* Third Statement: "Automated machine learning provides you with the ability to visually connect datasets and modules on an interactive canvas."This is False (No). That feature belongs to Azure Machine Learning Designer, not AutoML. The designer offers a drag-and-drop visual interface for connecting datasets and modules, whereas AutoML provides a wizard-driven approach focused on automation.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
NOTE: Each correct selection is worth one point.
Correct Answer:
Explanation:
The correct answers are Yes, Yes, and Yes.
According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn content in the section "Describe features of conversational AI workloads on Azure", bots created using Azure Bot Service can interact with users across multiple channels. The AI-900 syllabus explains that Azure Bot Service integrates with various communication platforms, allowing developers to build a single bot that can be deployed in many contexts without rewriting the logic.
* "You can communicate with a bot by using Cortana." - Yes.The AI-900 learning materials explain that Cortana, Microsoft's intelligent personal assistant, can serve as a channel for bots built with the Azure Bot Service. Through the Bot Framework, bots can be connected to Cortana to allow users to interact via voice or text. Although Cortana is less prominent now, it remains conceptually included in the AI-
900 coverage as an example of a voice-based conversational AI channel.
* "You can communicate with a bot by using Microsoft Teams." - Yes.This statement is true and directly referenced in the AI-900 syllabus. Microsoft Teams is a fully supported communication channel for Azure Bot Service. Bots in Teams can handle chat messages, commands, and interactions in team or personal contexts. The Microsoft Learn materials specify Teams as one of the native connectors where enterprise users can interact with organizational bots.
* "You can communicate with a bot by using a webchat interface." - Yes.This is also true. The Web Chat channel is one of the most common ways to deploy bots publicly. Azure Bot Service provides a Web Chat control that can be embedded directly into a webpage or web application. This allows users to interact with the bot using a chat window, just like on customer service websites.
Therefore, all three interfaces-Cortana (voice-based), Microsoft Teams (enterprise chat), and Web Chat (browser-based)-are valid and officially supported communication channels for Azure bots.
What is an example of the Microsoft responsible Al principle of transparency?
Correct Answer: C
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
You deploy the Azure OpenAI service to generate images.
You need to ensure that the service provides the highest level of protection against harmful content.
What should you do?
You need to ensure that the service provides the highest level of protection against harmful content.
What should you do?
Correct Answer: C
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
NOTE: Each correct selection is worth one point.
Correct Answer:
Explanation:
< A webchat bot can interact with users visiting a website # Yes
Automatically generating captions for pre-recorded videos is an example of conversational AI # No A smart device in the home that responds to questions such as "What will the weather be like today?" is an example of conversational AI # Yes
\ These answers are based on the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore conversational AI in Microsoft Azure."
1. A webchat bot can interact with users visiting a website # Yes
This statement is true. A webchat bot is a key example of conversational AI, which allows users to communicate with an intelligent system through natural language. The Azure Bot Service supports a webchat channel, enabling website visitors to ask questions or get assistance directly through a chat interface embedded on a webpage. This allows businesses to provide 24/7 automated support and interactive engagement without human intervention.
2. Automatically generating captions for pre-recorded videos is an example of conversational AI # No This is incorrect because automatically generating captions involves speech-to-text transcription, which falls under speech recognition and not conversational AI. While it uses AI to convert audio into text, it does not involve interactive communication or natural language dialogue. This task would be handled by Azure AI's Speech service, not the conversational AI framework.
3. A smart device in the home that responds to questions such as "What will the weather be like today?" is an example of conversational AI # Yes This is true. Smart assistants like those found in home devices (e.g., voice-activated systems) use conversational AI technologies to process spoken language (using natural language processing and speech recognition) and generate appropriate responses. This interaction represents a classic example of conversational AI, as it allows human-like dialogue between a user and an AI system.
# Final Answers:
* Webchat bot interacting with users # Yes
* Auto-captioning videos # No
* Smart home device answering questions # Yes
Select the answer that correctly completes the sentence.
Correct Answer:
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore fundamental principles of machine learning," regression is a type of supervised machine learning used to predict continuous numeric values.
In this question, the goal is to predict how many vehicles will travel across a bridge on a given day. The predicted output (the number of vehicles) is a continuous value-meaning it can take on any numerical value depending on various factors like time, weather, or day of the week. This makes it a regression problem, as the model learns from historical numeric data to estimate a continuous outcome.
How Regression Works:
Regression models find patterns between input features (such as temperature, weekday/weekend, traffic trends) and a numerical output (number of vehicles). Common regression algorithms include linear regression, decision trees for regression, and neural network regression. In Azure Machine Learning, regression tasks are used for business scenarios such as:
* Predicting sales revenue for a future month.
* Estimating house prices based on property characteristics.
* Forecasting energy consumption or traffic flow, as in this case.
Why not the other options?
* Classification: Used for predicting discrete categories (e.g., "spam" vs. "not spam"). It does not handle continuous numeric values.
* Clustering: An unsupervised learning technique used to group data points based on similarity without predefined labels (e.g., segmenting customers into groups).
Therefore, the task of predicting the number of vehicles-a numeric, continuous value-is a regression problem.
Select the answer that correctly completes the sentence.
Correct Answer:
Explanation:
According to the Microsoft Azure AI Fundamentals (AI-900) Official Study Guide and the Microsoft Learn module "Explore fundamental principles of machine learning," regression is a supervised machine learning technique used to predict continuous numeric values based on input data.
In this scenario, the goal is to predict how many hours of overtime a delivery person will work depending on the number of orders received. The output - the number of overtime hours - is a continuous variable (for example, 1.5 hours, 3.2 hours, etc.), not a category. This makes it a regression problem, where the model learns patterns from historical data and uses those patterns to estimate a continuous numeric outcome.
Why Regression Applies Here:
Regression models work by finding the mathematical relationship between input features (independent variables) and output values (dependent variables). In this case:
* Input (feature): Number of orders received
* Output (label): Predicted overtime hours
Azure Machine Learning supports several regression algorithms, including Linear Regression, Decision Tree Regression, and Neural Network Regression, all of which can handle scenarios where a numeric prediction is required.
Why Not the Other Options:
* Classification: Used for predicting discrete categories or labels (e.g., "on-time" vs. "late"). It does not output continuous numbers.
* Clustering: An unsupervised learning technique used to group data points with similar characteristics, not to make numeric predictions.
Thus, when the output variable is a numeric prediction (such as hours, prices, quantities, or time), the correct machine learning task is Regression.
You are authoring a Language Understanding (LUIS) application to support a music festival.
You want users to be able to ask questions about scheduled shows, such as: "Which act is playing on the main stage?" The question "Which act is playing on the main stage?" is an example of which type of element?
You want users to be able to ask questions about scheduled shows, such as: "Which act is playing on the main stage?" The question "Which act is playing on the main stage?" is an example of which type of element?
Correct Answer: D
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
You need to use Azure Machine Learning designer to build a model that will predict automobile prices.
Which type of modules should you use to complete the model? To answer, drag the appropriate modules to the correct locations. Each module 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.
Which type of modules should you use to complete the model? To answer, drag the appropriate modules to the correct locations. Each module 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.
Correct Answer:
Explanation:
Box 1: Select Columns in Dataset
For Columns to be cleaned, choose the columns that contain the missing values you want to change. You can choose multiple columns, but you must use the same replacement method in all selected columns.
Example:
The task is to build a machine learning model in Azure Machine Learning designer to predict automobile prices, which is a regression problem since the output (price) is a continuous numeric value. The pipeline must follow the logical data preparation, training, and evaluation flow as outlined in the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn module "Create a machine learning model with Azure Machine Learning designer." Here's the correct sequence and reasoning:
* Select Columns in Dataset:The first step after loading the raw automobile dataset is to choose the relevant columns that will be used as features (inputs) and the label (output). This module ensures that only necessary fields (for example, horsepower, engine size, mileage, etc.) are used to train the model while excluding irrelevant columns like vehicle ID or serial number.
* Split Data:Next, the cleaned and filtered dataset must be split into two subsets: training data and testing data (often 70/30 or 80/20). This allows the model to be trained on one portion and evaluated on the other to measure predictive accuracy.
* Linear Regression:Since automobile price prediction is a numeric prediction task, the appropriate learning algorithm is Linear Regression. This supervised algorithm learns relationships between numeric features and the target (price).
Finally, the workflow connects the training data and Linear Regression module to the Train Model module, which outputs a trained regression model. The trained model is then linked to the Score Model module to compare predicted vs. actual prices.
This pipeline fully aligns with Microsoft's recommended process for regression in Azure ML Designer.
You are building a tool that will process images from retail stores and identify the products of competitors.
The solution will use a custom model.
Which Azure Cognitive Services service should you use?
The solution will use a custom model.
Which Azure Cognitive Services service should you use?
Correct Answer: C
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
Which natural language processing feature can be used to identify the main talking points in customer feedback surveys?
Correct Answer: B
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
You need to identify groups of rows with similar numeric values in a dataset. Which type of machine learning should you use?
Correct Answer: C
Vote an answer
Explanation: Only visible for ExamDiscuss members. You can sign-up / login (it's free).
Select the answer that correctly completes the sentence.
Correct Answer:
Explanation:
The correct answer is "An embedding."
In the context of large language models (LLMs) such as GPT-3, GPT-3.5, or GPT-4, an embedding refers to a multi-dimensional numeric vector representation assigned to each word, token, or phrase. According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn documentation for Azure OpenAI embeddings, embeddings are used to represent textual or semantic meaning in a numerical form that a machine learning model can process mathematically.
Each embedding captures the semantic relationships between words. Words or tokens with similar meanings (for example, "car" and "automobile") are represented by vectors that are close together in the multi- dimensional space, while unrelated words (like "tree" and "laptop") are farther apart. This vector representation enables the model to understand context, similarity, and relationships between different pieces of text.
Embeddings are fundamental in tasks such as:
* Semantic search: Finding documents or sentences with similar meaning.
* Clustering: Grouping related concepts together.
* Recommendation systems: Suggesting similar content based on text meaning.
* Contextual understanding: Helping generative models produce coherent and context-aware text.
Option review:
* Attention: A mechanism used within transformers to focus on relevant parts of input sequences but not a representation of words.
* A completion: Refers to the generated text output from a model, not the internal representation.
* A transformer: The architecture that powers models like GPT, not the vector representation of tokens.
Therefore, the correct term for a multi-dimensional vector assigned to each word or token in a large language model (LLM) is An embedding, which represents how meaning is numerically encoded and compared within language models.
0
0
0
10