AI-901 Practice Questions: 10 Sample Questions with Explanations
Ten free AI-901 practice questions with answers and explanations, covering AI concepts, responsible AI and building with Microsoft Foundry.
The best way to gauge your AI-901 readiness is to answer questions in the exam's style. Below are 10 sample AI-901 practice questions with answers and short explanations, spanning both domains — AI concepts, responsible AI, and building with Microsoft Foundry. Try to answer before reading the explanation.
Question 1. A company wants to automatically write product descriptions from a few keywords. Which type of AI workload is this?
- A) Computer vision
- B) Generative AI
- C) Anomaly detection
- D) Speech recognition
Answer: B. Generative AI creates new content (here, text) from input — exactly what a descriptions-from-keywords task needs.
Question 2. A recruiting model consistently favors one group because of biased training data. Which responsible AI principle is most directly violated?
- A) Transparency
- B) Fairness
- C) Reliability and safety
- D) Privacy and security
Answer: B. Fairness is about treating people equitably and avoiding bias.
Question 3. You need to extract printed and handwritten text from scanned images. Which capability do you use?
- A) OCR (optical character recognition)
- B) Sentiment analysis
- C) Speech synthesis
- D) Key phrase extraction
Answer: A. OCR reads text from images and is part of Azure AI Vision.
Question 4. You must pull the invoice number, date and total from thousands of invoices into structured fields. Best fit?
- A) Azure AI Vision
- B) Azure AI Language
- C) Azure AI Document Intelligence
- D) Azure AI Speech
Answer: C. Document Intelligence returns structured data (fields, key-value pairs, tables) from forms and documents — more than plain OCR.
Question 5. Increasing a generative model's temperature setting will generally make its output…
- A) More deterministic and repetitive
- B) More creative and varied
- C) Faster to generate
- D) Cheaper per request
Answer: B. Higher temperature increases randomness, so responses become more creative and varied.
Question 6. Your chatbot must answer using your company's internal documents, not just the model's training data. Which approach?
- A) Increase the temperature
- B) Retrieval-Augmented Generation (grounding)
- C) Change the tokenizer
- D) Add text-to-speech
Answer: B. Grounding via RAG connects the model to your own data so answers are accurate and current.
Question 7. What best distinguishes an AI agent from a simple chatbot?
- A) It always uses a larger model
- B) It can take actions and use tools to complete a goal
- C) It only works in English
- D) It cannot use generative models
Answer: B. Agents act — they use tools and take multi-step actions toward a goal, rather than only replying with text.
Question 8. A bank must explain to customers which factors led to an automated loan decision. Which principle is this about?
- A) Inclusiveness
- B) Transparency
- C) Reliability and safety
- D) Accountability
Answer: B. Transparency means people can understand how and why a decision was made. (If the question stressed who is responsible and the governance around it, the answer would be accountability.)
Question 9. Which statement about AI, machine learning and deep learning is correct?
- A) They are three unrelated fields
- B) Deep learning is a subset of machine learning, which is a subset of AI
- C) Machine learning is a subset of deep learning
- D) AI is a subset of deep learning
Answer: B. The terms nest: deep learning ⊂ machine learning ⊂ artificial intelligence.
Question 10. You want to determine whether customer reviews are positive or negative. Which capability fits best?
- A) Sentiment analysis (Azure AI Language)
- B) Object detection
- C) Speech translation
- D) Image generation
Answer: A. Sentiment analysis, part of Azure AI Language, classifies text as positive, negative or neutral.
How did you do?
Roughly: 8+ correct means you're close to ready; 5–7 means focus on your weak domain; under 5 means start with the fundamentals and build up. Either way, ten questions isn't enough to be confident — you want dozens across every objective.
Start practicing AI-901 questions for free
Reading explains the ideas; answering questions is what makes them stick. Get a question wrong, read why, try again — that loop is what moves your score on exam day.
Ten questions is a taste; a full bank is how you actually pass. On ExamStudyApp you can run a free AI-901 practice session right now — no account and no credit card required. Every Microsoft Azure AI Fundamentals question comes with a full explanation, so each one doubles as a mini lesson.
When you're ready for more, the Microsoft Azure AI Fundamentals (AI-901) practice tests add unlimited adaptive practice and timed, full-length mock exams with a per-objective score breakdown — so you know exactly what to review before you book.
▶ Try free AI-901 practice questions →
