Skip to content
checksum
Tracks
In preparation

AI-901

Exam AI-901: Microsoft Azure AI Fundamentals

Outline from the official exam guide (opens in a new tab), as of April 15, 2026.

Add to my tracks: AI-901

Study the official path too

Microsoft Learn has two learning paths for AI-901. Use them alongside Checksum.

In preparation. Lessons and questions appear once approved.

Outline

Word for word from the official exam guide.

Domain 1 · Weight 40-45%Not started0%

Identify AI concepts and capabilities

  1. Task 1.1Not started

    Describe principles of responsible AI

    Lessons appear once approved.

    Skills measured (6)
    • 1.1.1Describe considerations for fairness in an AI solution
    • 1.1.2Describe considerations for reliability and safety in an AI solution
    • 1.1.3Describe considerations for privacy and security in an AI solution
    • 1.1.4Describe considerations for inclusiveness in an AI solution
    • 1.1.5Describe considerations for transparency in an AI solution
    • 1.1.6Describe considerations for accountability in an AI solution
  2. Task 1.2Not started

    Identify AI model components and configurations

    Lessons appear once approved.

    Skills measured (3)
    • 1.2.1Describe how generative AI models work
    • 1.2.2Identify an appropriate AI model, based on capabilities
    • 1.2.3Identify appropriate model deployment options and configuration parameters
  3. Task 1.3Not started

    Identify AI workloads

    Lessons appear once approved.

    Skills measured (5)
    • 1.3.1Identify scenarios for common AI workloads, including generative and agentic AI, text analysis, speech, computer vision, and information extraction
    • 1.3.2Describe common text analysis techniques, including keyword extraction, entity detection, sentiment analysis, and summarization
    • 1.3.3Identify features and capabilities of speech recognition and speech synthesis
    • 1.3.4Identify features and capabilities of computer vision and image-generation models
    • 1.3.5Identify techniques to extract information from text, images, audio, and videos

Domain 2 · Weight 55-60%Not started0%

Implement AI solutions by using Microsoft Foundry

  1. Task 2.1Not started

    Implement generative AI apps and agents by using Foundry

    Lessons appear once approved.

    Skills measured (5)
    • 2.1.1Create effective system and user prompts for generative AI models
    • 2.1.2Deploy a model and interact with it in the Foundry portal
    • 2.1.3Create a lightweight chat client application by using the Foundry SDK
    • 2.1.4Create and test a single-agent solution in the Foundry portal
    • 2.1.5Create a lightweight client application for an agent
  2. Task 2.2Not started

    Implement AI solutions for text and speech by using Foundry

    Lessons appear once approved.

    Skills measured (3)
    • 2.2.1Build a lightweight application that includes text analysis
    • 2.2.2Respond to spoken prompts by using a deployed multimodal model
    • 2.2.3Build a lightweight application by using Azure Speech in Foundry Tools
  3. Task 2.3Not started

    Implement AI solutions with computer vision and image-generation capabilities by using Foundry

    Lessons appear once approved.

    Skills measured (3)
    • 2.3.1Interpret visual input in prompts by using a deployed multimodal model
    • 2.3.2Create new visual outputs by using generative models
    • 2.3.3Build a lightweight application that includes vision capabilities
  4. Task 2.4Not started

    Implement AI solutions for information extraction by using Foundry

    Lessons appear once approved.

    Skills measured (4)
    • 2.4.1Extract information from documents and forms by using Azure Content Understanding in Foundry Tools
    • 2.4.2Extract information from images by using Content Understanding
    • 2.4.3Extract information from audio and video by using Content Understanding
    • 2.4.4Build a lightweight application with information extraction capabilities by using Content Understanding

About the exam

From the vendor’s own pages.

  • A score of 700 or greater is required to pass.

  • Scores are reported on a scale of 1 to 1,000, and because the score is scaled, a passing score of 700 may not equal 70% of the points.

    Microsoft states this for technical exams in general, not for AI-901 specifically.

  • Fundamentals exams: 45 minutes of exam time and 65 minutes of seat time.

    Microsoft gives this for Fundamentals exams in general, not for AI-901 specifically.

  • Most Microsoft Certification exams typically contain between 40-60 questions; however, the number can vary depending on the exam.

    This is general, and the AI-901 count is not published.

  • Microsoft does not identify specific exam formats or question types before the exam.

  • Microsoft Learn is not available during Fundamentals exams.

  • Fundamentals certifications do not expire.

Free forever. Support Checksum

Checksum is an independent study platform, not affiliated with or endorsed by Amazon Web Services, Microsoft or LeetCode. AWS and AWS Certified are trademarks of Amazon.com, Inc. or its affiliates. Microsoft and Azure are trademarks of the Microsoft group of companies. Other trademarks belong to their owners.