top of page

AI-901 practice exam and study guide

Microsoft Azure AI Fundamentals

Timed practice exams for AI-901, with 50 questions in 45 minutes in each full exam. That is the site's practice setting: Microsoft publishes no question count, time or exam format for AI-901. Every question is original and every option is explained. Your score is broken down by the sections Microsoft publishes, so you see what to study next. The question bank holds hundreds of practice questions.

Exam facts

  • Passing score: 700 on a scale of 1 to 1,000 [1]
  • Exam languages (real exam): English, Arabic (Saudi Arabia), Chinese (Simplified), Chinese (Traditional), French, German, Indonesian (Indonesia), Italian, Japanese, Korean, Portuguese (Brazil), Russian, Spanish [1]

Tokens: 1 for $4.99, 5 for $14.99, 10 for $24.99 or 25 for $49.99. One token runs a full timed AI-901 practice exam, and every shorter session on that exam is then free. The Unlimited pass is $149.99 for a year of every practice session on every exam.

Get tokens

Exam sections and weights

Microsoft publishes these sections and objectives for AI-901, quoted here as Microsoft words them. [2]

Section 1: Identify AI concepts and capabilities, 40 to 45% of the exam

  • "Describe considerations for fairness in an AI solution"
  • "Describe considerations for reliability and safety in an AI solution"
  • "Describe considerations for privacy and security in an AI solution"
  • "Describe considerations for inclusiveness in an AI solution"
  • "Describe considerations for transparency in an AI solution"
  • "Describe considerations for accountability in an AI solution"
  • "Describe how generative AI models work"
  • "Identify an appropriate AI model, based on capabilities"
  • "Identify appropriate model deployment options and configuration parameters"
  • "Identify scenarios for common AI workloads, including generative and agentic AI, text analysis, speech, computer vision, and information extraction"
  • "Describe common text analysis techniques, including keyword extraction, entity detection, sentiment analysis, and summarization"
  • "Identify features and capabilities of speech recognition and speech synthesis"
  • "Identify features and capabilities of computer vision and image-generation models"
  • "Identify techniques to extract information from text, images, audio, and videos"

Section 2: Implement AI solutions by using Microsoft Foundry, 55 to 60% of the exam

  • "Create effective system and user prompts for generative AI models"
  • "Deploy a model and interact with it in the Foundry portal"
  • "Create a lightweight chat client application by using the Foundry SDK"
  • "Create and test a single-agent solution in the Foundry portal"
  • "Create a lightweight client application for an agent"
  • "Build a lightweight application that includes text analysis"
  • "Respond to spoken prompts by using a deployed multimodal model"
  • "Build a lightweight application by using Azure Speech in Foundry Tools"
  • "Interpret visual input in prompts by using a deployed multimodal model"
  • "Create new visual outputs by using generative models"
  • "Build a lightweight application that includes vision capabilities"
  • "Extract information from documents and forms by using Azure Content Understanding in Foundry Tools"
  • "Extract information from images by using Content Understanding"
  • "Extract information from audio and video by using Content Understanding"
  • "Build a lightweight application with information extraction capabilities by using Content Understanding"

Sample questions

Three questions from the AI-901 practice bank, with the answer and why each option is right or wrong.

Question 1

Your team is building a voice assistant. The team asks people of different ages, languages and abilities to review early designs, then reworks the product around what they say. Which inclusive design principle is the team applying?

  • A. Learn from diversity
  • B. Solve for one, extend to many
  • C. Design for the average user
  • D. Recognize exclusion

Answer: A. Microsoft names three inclusive design principles: recognize exclusion, solve for one and extend to many, and learn from diversity. Bringing different perspectives into the design is the third. [3]

  • A. Right. Learn from diversity means engaging with different perspectives to build better solutions, and the team is building those reviewers' views into the assistant.
  • B. Wrong. Solve for one, extend to many is a different principle. Bringing the views of varied reviewers into the design is learning from diversity.
  • C. Wrong. Designing for an average user isn't one of Microsoft's inclusive design principles, which exist to keep people from being left out.
  • D. Wrong. Recognize exclusion is a different principle. Reworking a design around what varied reviewers say is learning from diversity.

Question 2

You have a model that answers questions with help from a search tool. You need the model to issue search calls, stop generation, and then receive the search results pasted back into the prompt, so it doesn't rely on its own parameters for answers. Which prompt technique should you use?

  • A. Zero-shot learning
  • B. Use of affordances
  • C. A lower temperature
  • D. Being descriptive

Answer: B. With affordances, generation stops once the model writes its search calls, the results go back into the prompt, and the model answers from them. [4]

  • A. Wrong. Zero-shot learning means a prompt with no examples. It adds no search results or other outside data.
  • B. Right. An affordance such as search lets the model draw on outside results, which helps mitigate fabricated answers and brings in up-to-date information.
  • C. Wrong. A lower temperature makes output more focused and concrete. It doesn't give the model any new data.
  • D. Wrong. Being descriptive means using analogies in the prompt. It doesn't bring search results into the prompt.

Practice for AI-901 on ExamSens.ai

ExamSens.ai is not authorized, endorsed or sponsored by Microsoft.

References

[1] https://learn.microsoft.com/en-us/credentials/certifications/exams/ai-901/

[2] https://learn.microsoft.com/en-us/credentials/certifications/resources/study-guides/ai-901

[3] https://learn.microsoft.com/en-us/training/modules/embrace-responsible-ai-principles-practices/3-identify-guiding-principles-responsible-ai

[4] https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering

bottom of page