CertiAce

AI-901 Study Guide

Microsoft Certified: Azure AI Fundamentals

 

Before You Start Studying

Before diving into the study sections, review the prerequisites and recommended background knowledge below to understand what will help you succeed.

 

Recommended Exam Path

AI-901 is a fundamentals-level certification, which makes it a great entry point into Microsoft AI certifications. It replaced the retired AI-900 exam on June 30, 2026, and earns the same certification: Microsoft Certified: Azure AI Fundamentals.

Do not let the fundamentals label fool you, though. AI-901 is noticeably more developer-flavored than AI-900 was. Microsoft expects you to have conceptual knowledge of AI solutions in Azure, knowledge of Python coding syntax, and familiarity with Azure resources. More than half of the exam focuses on implementing AI solutions with Microsoft Foundry.

If you are completely new to cloud computing, AZ-900: Microsoft Certified - Azure Fundamentals is a helpful starting point, although it is not required.

AZ-900 helps you build:

  • Foundational understanding of cloud concepts
  • Familiarity with the Azure portal and Azure resources
  • A shared vocabulary used throughout Microsoft tooling

After AI-901, a natural next step is AI-103: Developing AI Apps and Agents on Azure, which goes much deeper into building generative AI applications, agents, and computer vision solutions with Microsoft Foundry.

 

Prerequisites

There are no strict prerequisites to start AI-901 preparation, but the exam assumes some foundational technical skills.

You should be comfortable with:

  • Basic AI and cloud concepts
  • Reading simple Python code
  • Navigating the Azure portal and working with Azure resources
  • A general awareness of REST APIs and SDKs

 

Recommended Background Knowledge

AI-901 is organized around two skill areas. The first is conceptual; the second expects you to recognize how solutions are actually built with Microsoft Foundry.

Identify AI Concepts and Capabilities (40-45% of the exam)

  • The six principles of responsible AI: fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability
  • How generative AI models work, and how to pick an appropriate model based on capabilities
  • Model deployment options and configuration parameters
  • Common AI workloads: generative and agentic AI, text analysis, speech, computer vision, and information extraction
  • Text analysis techniques such as keyword extraction, entity detection, sentiment analysis, and summarization
  • Speech recognition and speech synthesis capabilities
  • Computer vision and image-generation model capabilities
  • Techniques to extract information from text, images, audio, and video

Implement AI Solutions by Using Microsoft Foundry (55-60% of the exam)

  • Writing effective system and user prompts for generative AI models
  • Deploying a model and interacting with it in the Foundry portal
  • Creating a lightweight chat client application with the Foundry SDK
  • Creating and testing a single-agent solution in the Foundry portal
  • Building lightweight applications for text analysis and speech using Azure Speech and Azure Language in Foundry Tools
  • Responding to spoken prompts and interpreting visual input with multimodal models
  • Generating new visual outputs with generative models
  • Extracting information from documents, forms, images, audio, and video using Azure Content Understanding in Foundry Tools

 

Step-by-Step Study Guide

 

Step 1: Review the Official Study Guide

What to do:

  • Open the official AI-901 study guide
  • Read the skills measured sections
  • Note any topics that are new to you
  • Use it as your checklist throughout your prep

Link to The Official Study Guide

 

Step 2: Schedule Your Exam

What to do:

  • Choose a date that gives you enough time for study and practice
  • Schedule the exam through the official Microsoft certification page
  • Put the date on your calendar and plan backwards

Recommended timing:

  • If you already work with Azure AI services or Foundry: 1 to 3 weeks
  • If you know Azure but are new to AI workloads: 3 to 6 weeks
  • If you are new to both Azure and Python: 6 to 8 weeks

Certification and Exam Details Page

 

Step 3: Go Through the Official Learning Paths

AI-901 has two official learning paths, and they map directly to the two modules you will find in CertiAce practice.

What to do:

  • Complete the AI concepts learning path first to build the conceptual foundation
  • Then complete the AI applications and agents learning path for the Foundry-focused skills
  • Take notes on concepts you cannot explain in simple terms
  • Flag areas that require additional hands-on practice

AI Concepts for Developers and Technology Professionals

Get Started with AI Applications and Agents on Azure

 

Step 4: Get Hands-On with Microsoft Foundry

More than half of AI-901 focuses on implementing AI solutions with Microsoft Foundry, so hands-on time in the Foundry portal is the highest-value preparation you can do.

You can create a free Azure account and work through the exercises included in the official learning paths.

You should aim to get experience with:

  • Deploying a model and chatting with it in the Foundry portal
  • Writing and refining system and user prompts
  • Creating and testing a simple agent in the Foundry portal
  • Trying text analysis features such as sentiment analysis and entity detection
  • Converting speech to text and text to speech with Azure Speech
  • Analyzing images with a multimodal model and generating new images
  • Extracting fields from a document with Azure Content Understanding

Create an Azure Free Account

Microsoft Foundry Documentation

 

Step 5: Deep-Dive the Service Documentation

What to do:

  • Skim the documentation for the services the exam names explicitly
  • Focus on what each service does and when you would choose it, not on memorizing syntax
  • Pay special attention to Azure Content Understanding, which is heavily featured in the information extraction objectives

Azure AI Services Documentation

Azure Content Understanding

Azure Speech

Azure Language

 

Step 6: Benchmark Your Knowledge

What to do:

  • Use CertiAce to benchmark your readiness
  • Practice exam-style questions across both skill areas
  • Review explanations carefully, especially for wrong answers
  • Return to Microsoft Learn and hands-on practice for weak topics

Recommended target:

  • Aim for consistent performance, not one lucky high score
  • If a topic is unstable, return to learning + hands-on
  • Pay close attention to questions that distinguish similar workloads, such as image analysis versus image generation, or speech recognition versus speech synthesis

Note that the official Microsoft practice assessment for AI-901 was not yet available when this guide was written. Microsoft usually publishes practice assessments within a couple of months of a new exam becoming generally available, so check the practice assessments page for updates.

CertiAce AI-901 Exam Practice

Microsoft Practice Assessments

 

Step 7: Take the Exam

The day before:

  • Review your weak topics only
  • Revisit the six responsible AI principles and the common AI workload types
  • Refresh what each Foundry capability is used for
  • Avoid learning brand new topics

On exam day:

  • Read questions carefully and identify what they are truly asking
  • Eliminate wrong options first
  • Watch for scenarios that map to a specific workload: creating new content points to generative AI, interpreting existing content points to analysis
  • A score of 700 or greater is required to pass
  • The Azure AI Fundamentals certification does not expire, so there is no renewal to worry about

 

Additional Learning Resources

 

Microsoft Official Resources

 

Microsoft Product Documentation

 

YouTube

 

Community

Ready to test your knowledge?

Practice questions for AI-901
CertiAceAboutTerms of ServicePrivacy PolicySign up
AI-901 Study Guide — Microsoft Azure AI Fundamentals | CertiAce - CertiAce