| Exam Code | AI-900 |
| Exam Name | Microsoft Azure AI Fundamentals |
| Questions | 241 Questions Answers With Explanation |
| Update Date | July 07,2025 |
| Price |
Was : |
Struggling to find the right resources to prepare for the Microsoft Azure AI Fundamentals certification? Your search ends here. At Certionary, we offer real exam-based dumps and expertly crafted study guides that mirror the actual exam format — giving you everything you need to pass with confidence.
What’s Inside?
Our dumps are trusted by thousands of IT professionals around the world. You study less, learn more, and pass faster. Why take risks with outdated material or generic practice questions? With Certionary, you get precisely what you need to pass — no guesswork, no stress.
What are three stages in a transformer model? Each correct answer presents a complete solution. NOTE: Each correct answer is worth one point.
A. object detection
B. embedding calculation
C. tokenization
D. next token prediction
E. anonymization
You need to create a customer support solution to help customers access information. The solution must support email, phone, and live chat channels. Which type of Al solution should you use?
A. natural language processing (NLP)
B. computer vision
C. machine learning
D. chatbot
You are building a chatbot that will use natural language processing (NLP) to perform thefollowing actions based on the text input of a user:• Accept customer orders.• Retrieve support documents.• Retrieve order status updates.Which type of NLP should you use?
A. sentiment analysis
B. translation
C. language modeling
D. named entity recognition
You need to build an app that will identify celebrities in images. Which service should you use?
A. Azure OpenAI Service
B. Azure Machine Learning
C. conversational language understanding (CLU)
D. Azure Al Vision
Which two scenarios are examples of a natural language processing workload? Eachcorrect answer presents a complete solution.NOTE; Each correct selection is worth one point.
A. assembly line machinery that autonomously inserts headlamps into cars
B. a smart device in the home that responds to questions such as, "What will the weather
be like today?
C. monitoring the temperature of machinery to turn on a fan when the temperature reaches
a specific threshold
D. a website that uses a knowledge base to interactively respond to users' questions
What can be used to complete a paragraph based on a sentence provided by a user?
A. Azure Al Language
B. Azure OpenAI
C. Azure Machine Learning
D. Azure Al Vision
You need to convert receipts into transactions in a spreadsheet. The spreadsheet mustinclude the date of the transaction, the merchant the total spent and any taxes paid.Which Azure Al service should you use?
A. Face
B. Azure Al Language
C. Azure Al Document Intelligence
D. Azure Al Custom Vision
Which parameter should you configure to produce more verbose responses from a chat solution that uses the Azure OpenAI GPT-3.5 model?
A. Presence penalty
B. Temperature
C. Stop sequence
D. Max response
You have an Internet of Things (loT) device that monitors engine temperature.The device generates an alert if the engine temperature deviates from expected norms.Which type of Al workload does the device represent?
A. natural language processing (NLP)
B. computer vision
C. anomaly detection
D. knowledge mining
You need to predict the animal population of an area.Which Azure Machine Learning type should you use?
A. clustering
B. classification
C. regression
You need to identify street names based on street signs in photographs.Which type of computer vision should you use?
A. object detection
B. optical character recognition (OCR)
C. image classification
D. facial recognition
A smart device that responds to the question. "What is the stock price of Contoso, Ltd.?" is an example of which Al workload?
A. computer vision
B. anomaly detection
C. knowledge mining
D. natural language processing
You have a chatbot that answers technical questions by using the Azure OpenAI GPT-3.5large language model (LLM). Which two statements accurately describe the chatbot? Eachcorrect answer presents a complete solution.NOTE: Each correct answer is worth one point.
A. Grounding data can be used to constrain the output of the chatbot.
B. The chatbot will always provide accurate data.
C. The chatbot might respond with inaccurate data.
D. The chatbot is suitable for performing medical diagnosis.
You need to create a model that labels a collection of your personal digital photographs.Which Azure Al service should you use?
A. Azure Al Language
B. Azure Al Computer Vision
C. Azure Al Document Intelligence
D. Azure Al Custom Vision
You need to implement a pre-built solution that will identify well-known brands in digital photographs. Which Azure Al sen/tee should you use?
A. Face
B. Custom Vision
C. Computer Vision
D. Form Recognizer
Which type of natural language processing (NLP) entity is used to identify a phone number?
A. regular expression
B. machine-learned
C. list
D. Pattern-any
Which Azure Cognitive Services service can be used to identify documents that contain sensitive information?
A. Custom Vision
B. Conversational Language Understanding
C. Form Recognizer
You plan to build a conversational Al solution that can be surfaced in Microsoft Teams. Microsoft Cortana, and Amazon Alexa. Which service should you use?
A. Azure Bot Service
B. Azure Cognitive Search
C. Language service
D. Speech
Which two languages can you use to write custom code for Azure Machine Learningdesigner? Each correct answer presents a complete solution.NOTE; Each correct selection is worth one point.
A. C#
B. Scala
C. Python
D. R
Your company manufactures widgets.You have 1.000 digital photos of the widgets.You need to identify the location of the widgets within the photos.What should you use?
A. Computer Vision Spatial Analysis
B. Custom Vision object detection
C. Custom Vision classification
D. Computer Vision Image Analysis
Which three actions improve the quality of responses returned by a generative Al solutionthat uses GPT-3.5? Each correct answer presents a complete solution.NOTE: Each correct answer is worth one point.
A. Add grounding data to prompts.
B. Provide additional examples to prompts.
C. Modify tokenization.
D. Add training data to prompts.
E. Modify system messages.
During the process of Machine Learning, when should you review evaluation metrics?
A. After you clean the data.
B. Before you train a model.
C. Before you choose the type of model.
D. After you test a model on the validation data.
You have a custom question answering solution.You create a bot that uses the knowledge base to respond to customer requests. You needto identify what the bot can perform without adding additional skills. What should youidentify?
A. Register customer complaints.
B. Answer questions from multiple users simultaneously.
C. Register customer purchases.
D. Provide customers with return materials authorization (RMA) numbers.
You have a natural language processing (NIP) model that was created by using dataobtained without permission.Which Microsoft principle for responsible Al does this breach?
A. privacy and security
B. inclusiveness
C. transparency
D. reliability and safety
