Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

AI-901-Microsoft Azure AI Fundamental Certification

Name: AI-901-Microsoft Azure AI Fundamental Certification
Rating: 4.6 (7897 reviews)

Prepare for both AI-900 and the AI-901 exam

Created byAlan Rodrigues

Last updated 7/2026

English

English [Auto],Spanish [Auto],

What you'll learn

Prepare for both the AI-900 exam and the new AI-901 beta exam — covering all official Microsoft exam objectives for both certifications.
Understand core AI concepts including machine learning, deep learning, NLP, computer vision, generative AI, and agentic AI.
Learn the principles of Responsible AI — fairness, transparency, accountability, privacy, inclusiveness, reliability, and safety.
Deploy and interact with AI models using the Microsoft Foundry portal, including generative AI apps and single-agent solutions.
Build lightweight client applications using the Foundry SDK and extract information from documents, images, audio, and video using Azure Content Understanding.

Course content

10 sections • 173 lectures • 11h 13m total length

IMPORTANT - How the course has been structured6:03
Slides download0:08
What This Section Covers — And Why It Matters2:10
Generative AI - The Big Picture2:34
A wide-angle view of what generative AI actually is and why it represents such a significant shift in how software is built.
Inside the LLM - From Prompt to Response7:18
A look under the hood of large language models — what they are, how they're trained, and what actually happens between the moment you send a prompt and the moment you receive a response.
AI Models Landscape Anthropic and OpenAI7:31
Let's have an overview of the various models in the market and focus our attention on the OpenAI models.
The Art of the Prompt Engineering - Better Conversations with AI5:41
A practical guide to communicating with AI models in a way that gets consistently better results.
The Art of the Prompt Engineering - Better Conversations with AI - Resources0:20
Agentic AI - From Answering Questions to Getting Things Done4:22
A conceptual shift from thinking about AI as a question-answering tool to understanding it as an autonomous actor that can plan, use tools, and complete multi-step tasks.
Identifying AI Workloads - Text3:27
A focused look at the wide range of tasks AI models can perform with text
Identifying AI Workloads - Speech1:39
An exploration of where AI adds value in audio and spoken language scenarios.
Identifying AI Workloads - Computer Vision2:14
A survey of AI use cases that involve images and video, including object detection, image classification, optical character recognition, and visual inspection.
Identifying AI Workloads - Information Extraction2:30
A chapter focused on one of the most practically valuable AI applications — pulling structured, usable information out of unstructured content like documents, forms, and reports.
Fairness - Building AI That Treats Everyone Equally6:08
An honest examination of how bias enters AI systems and what it looks like when a model treats different groups of people unequally.
Reliability & Safety - AI That Works When It Matters4:11
A chapter on what it means for an AI system to be reliable — not just accurate on average, but trustworthy across edge cases, unexpected inputs, and high-stakes situations.
Privacy & Security - Protecting People in an AI World4:59
An exploration of the unique privacy and security challenges that come with AI systems
Inclusiveness - Designing AI for Every Human3:45
A look at how AI systems can be designed to work well for people of all backgrounds, abilities, languages, and circumstances.
Transparency - Making AI Understandable5:42
A chapter on the principle that AI systems should be explainable.
Accountability - Keeping Humans in Control5:11
A discussion of who is responsible when an AI system gets something wrong.
From Theory to Practice What We're Going to Build1:26
A bridge chapter that transitions from concepts to code.
Summary11:23
Section Quiz

Getting Started with Microsoft Foundry2:17
An introduction to Microsoft Foundry and its role in the AI development ecosystem. This chapter covers what the platform is, why it matters, and what you'll be able to build by the end of this course.
Creating the Azure Free Account4:48
Lab - Creating a Microsoft Foundry Resource7:49
A hands-on lab where you'll provision your first Microsoft Foundry resource inside the Azure portal. You'll walk through resource configuration, subscription setup, and confirm everything is ready for the lessons ahead.
Exploring the Microsoft Foundry Interface6:16
A guided tour of the Microsoft Foundry portal. You'll learn how to navigate the dashboard, locate key sections, and understand how the interface is organized before diving into model work.
Understanding Model Deployment4:12
A conceptual deep-dive into how AI model deployment works within Microsoft Foundry.
Deploying Your First Model7:58
Step-by-step instructions for deploying a model from the Azure AI model catalog. By the end of this chapter, you'll have a live model endpoint ready to accept requests.
Working with the Model Playground8:23
An exploration of the built-in Playground tool in Microsoft Foundry. You'll test prompts, adjust settings, and see model responses in real time — all without writing a single line of code.
Sending images along with your user prompt3:04
A practical look at multimodal prompting. You'll learn how to attach images to your prompts inside the Playground and understand how the model interprets visual input alongside text.
Sending images along with your user prompt - Resources0:06
Using a model to generate images5:31
An introduction to image generation within Microsoft Foundry. You'll explore how to craft effective prompts for image models and review the output options available on the platform.
Using a model to generate images - Resources0:16
Prepare your development environment1:29
A setup chapter covering everything you need before writing code
Setting Up Your Environment: Installing Python on Windows1:54
Setting Up Your Editor: Installing VS Code and the Python Extension2:45
Your First AI-Powered Program14:58
You'll write your first application that calls a deployed AI model via the API. This chapter bridges the gap between the portal and real-world development using a simple but complete working example.
Your First AI-Powered Program - Resources0:10
Sending Images to Your AI Model9:23
A code-level walkthrough of multimodal API calls. You'll learn how to format and send image data programmatically, and handle the model's response in your application.
Sending Images to Your AI Model - Resources0:26
Controlling Model Behavior with Parameters5:46
A practical guide to parameters like temperature and max tokens.
Controlling Model Behavior with Parameters - Resources0:24
Evaluating AI Output Quality with General Purpose Evaluators10:34
An introduction to evaluation frameworks in Microsoft Foundry. You'll learn how to measure response quality systematically using built-in evaluators to ensure your AI outputs meet the bar you need.
Fine-Tuning Models in Microsoft Foundry6:37
A walkthrough of the fine-tuning workflow
Building AI Agents in Microsoft Foundry7:41
An introduction to agentic AI design. You'll learn what agents are, how they differ from simple chat completions, and how to build your first agent using the tools available in Microsoft Foundry.
Building AI Agents in Microsoft Foundry - Resources0:11
Agent Tool Best Practices0:58
A focused look at the do's and don'ts of tool use in AI agents. Topics include tool design, error handling, safety considerations, and patterns that make agents more reliable in production.
Summary5:56
A closing chapter that recaps everything covered throughout the course, highlights key takeaways, and points you toward next steps for continuing your journey with Microsoft Foundry and AI development.
Section Quiz

Azure AI Services2:10
A high-level introduction to the Azure AI Services ecosystem — what it is, how it fits into the broader Azure platform, and why it's become a go-to toolkit for developers building intelligent applications.
Azure AI Language2:34
A conceptual overview of Azure AI Language and its natural language processing capabilities
Lab - Azure AI Language7:23
A hands-on lab where you'll put Azure AI Language to work directly.
Lab - Azure AI Language - Resources0:33
Lab - Azure Translator1:56
A practical lab focused on Azure's neural machine translation service.
Azure AI Speech service4:48
An overview of the Azure AI Speech service and its core capabilities, including speech-to-text, text-to-speech, and speaker recognition.
Lab - Azure Speech - Python - Speech to Text4:43
A coding lab where you'll use Python to transcribe spoken audio into text using the Azure Speech SDK.
Lab - Azure Speech - Python - Speech to Text - Resources0:16
Lab - Azure Speech - Python - Text to Speech2:20
The companion lab to the previous chapter, this time going in the opposite direction — converting written text into natural-sounding speech using Python.
Lab - Azure Speech - Python - Text to Speech - Resources0:13
Real-World Use Case Transcribing Audio at Scale with Azure Blob Storage2:25
A practical, scenario-driven chapter that shows how to build a scalable audio transcription pipeline.
Azure AI Vision Service3:24
An introduction to Azure AI Vision and its image analysis capabilities, including object detection, OCR, image tagging, and facial analysis.
Azure Content Understanding2:14
A conceptual chapter introducing Azure Content Understanding
Lab - Azure Content Understanding - Extract Information from Documents4:02
A hands-on lab where you'll use Azure Content Understanding to pull structured data out of real documents.
Azure Content Understanding - Document Analyzer - Lab Overview2:25
A preparatory chapter that walks you through the multi-part Document Analyzer lab series before you dive in. You'll get a clear picture of the architecture you'll be building, the components involved, and what each upcoming lab contributes to the finished solution.
Lab - Azure Content Understanding - Document Analyzer - Storage Account setup5:45
The first hands-on lab in the Document Analyzer series. You'll provision and configure an Azure Storage Account to serve as the document intake layer
Lab - Azure Content Understanding - Document Analyzer - Model setup2:11
Continuing the Document Analyzer build, this lab focuses on configuring the Content Understanding model.
Lab - Azure Content Understanding - Document Analyzer - Code Execution7:05
The final lab in the Document Analyzer series, where everything comes together.
Lab - Azure Content Understanding - Document Analyzer - Code Execution-Resource0:28
Analyzing Audio & Video with Azure Content Understanding2:14
A closing chapter that extends your Content Understanding knowledge beyond documents into multimedia.
Summary4:48
Section Quiz

Important Course instructions - Important0:28
This chapter focuses on the important course instructions
PDF Download0:04
Introduction to Azure2:02
This chapter focuses on the introduction to Azure
The Azure Free Account4:11
This chapter focuses on the Azure Free account
Creating an Azure Free Account4:48
Learn to create an Azure free account using Gmail or GitHub, verify email and phone, create a Microsoft account, enable multi-factor authentication, and note the $200 credit for new customers.
Tour around the Azure portal3:00
This chapter focuses on the quick view of the Azure Portal
Lab - An example of creating a resource in Azure12:23
This chapter focuses on an example on the creation of a resource in Azure

Machine Learning and Artificial Intelligence4:52
This chapter focuses on Machine Learning and Artificial Intelligence
Why consider Machine Learning5:28
This chapter focuses on prediction and forecasting
Anomaly Detection Workloads4:51
This chapter focuses on anomaly detection workloads
Natural Language Processing Workloads4:30
This chapter focuses on natural language processing workloads
Computer Vision Workloads4:23
This chapter focuses on computer vision workloads
Conversational AI Workloads4:17
This chapter focuses on conversational AI workloads
Generative AI4:39
Microsoft Guiding principles for response AI - Accountability3:37
This chapter focuses on Microsoft guiding principles for Response AI - Accountability
Microsoft Guiding principles for response AI - Reliability and Safety3:33
Explore the reliability and safety principle of Microsoft's responsible AI. Test AI under diverse real-world conditions, from autonomous driving to medical diagnostics.
Microsoft Guiding principles for response AI - Privacy and Security3:12
This chapter focuses on Microsoft guiding principles for Response AI - Privacy and Security
Microsoft Guiding principles for response AI - Transparency3:06
This chapter focuses on Microsoft guiding principles for Response AI - Transparency
Microsoft Guiding principles for response AI - Inclusiveness2:41
This chapter focuses on Microsoft guiding principles for Response AI - Inclusiveness
Microsoft Guiding principles for response AI - Fairness4:10
This chapter focuses on Microsoft guiding principles for Response AI - Fairness
Short Quiz

The World of Machine Learning - Why It Matters5:11
From Idea to Model - The ML Workflow6:30
Your Data - Features, Labels & Splits10:31
Identify data sources, consolidate a usable data set, and define features and labels to train a machine learning model. Clean data and manage missing values and outliers.
Learning Styles - Supervised, Unsupervised & Beyond5:34
This chapter focuses on machine learning algorithms
Getting Started with Azure Machine Learning2:20
A note on the costs3:01
Learn Azure machine learning pricing based on compute for pipelines and Kubernetes endpoints, with note that costs run around 1.5 USD, and set budgets and alerts to control spending.
Lab - Building Your ML Home - Creating a Workspace5:26
This chapter focuses on creating a workspace
Touring the ML Studio - Where the Magic Happens3:53
Explore the Azure machine learning studio, a low-code platform to build, train, and deploy models. Use the designer for drag-and-drop workflows with datasets or notebooks for Python and automated ML.
Mission Brief - Building a Binary Classification Model3:58
Lab - Binary Classification Model - Understanding Our Data6:39
This chapter focuses on building a classification machine learning pipeline with splitting data
Lab - Binary Classification Model - Cleaning for Better Accuracy6:55
Lab - Binary Classification Model - Setting Up Your Compute Instance7:25
Design a binary classification model to predict income up to 50k versus above 50k using a low-code pipeline in Azure Machine Learning Studio, then provision a compute instance to train.
Lab - Binary Classification Model - Running the pipeline6:18
Lab - Binary Classification Model - Splitting the Dataset5:30
Lab - Binary Classification Model - Building Your ML Pipeline6:07
This chapter focuses on the completion of the classification machine learning pipeline
Lab - Binary Classification Model - Evaluating the Model’s Performance12:07
This chapter focuses on the resources for classification machine learning pipeline
Lab - Binary Classification Model - Creating a Kubernetes Cluster4:11
Deploy the trained binary classification model to a production environment using a Kubernetes cluster on Azure Kubernetes Service, enabling 24/7 hosting with compute resources.
Lab - Binary Classification Model - Deploying Your Model5:54
This chapter focuses on deployment of a model
Lab - Binary Classification Model - Trying Out Your Model7:00
This chapter focuses on testing a pipeline
Lab - Binary Classification Model - Trying Out Your Model - Resources0:26
This chapter focuses on the resources for testing a pipeline
Lab - End-to-End Adventure - Building a Regression Model11:11
This chapter focuses on building a regression machine learning pipeline with sample data
Lab Automated ML – Preparing the Dataset4:33
Create and upload a tabular data set for automated machine learning, converting a local house price csv into a data asset in an Azure ML workspace for model training.
Lab Using Automated ML in Azure3:25
This chapter focuses on automated machine learning
Cleaning Up Azure Resources2:17
Section Summary & Key Takeaways5:04
Summarizes machine learning types—classification (binary and multi-class), regression, and clustering—under supervised and unsupervised learning, with features, labels, feature engineering, and evaluation metrics and deployment workflows.
Short Quiz

Getting Started with Azure AI Services3:30
This chapter focuses on an introduction to the Computer Vision service
Lab - Setting up a Microsoft Foundry Hub resource5:08
Set up a Microsoft Foundry Hub resource to explore the Azure AI Vision Service and create an AI Hub with a Central US resource group for Azure AI services.
Lab - Image Insights - Detect Common Objects7:47
Lab - Telling the Story - Image Captions in Action2:05
Lab - Spot the Details - Extract Common Tags1:30
Lab - Reading Text from Images - OCR in Azure2:00
Explore how OCR detects text in images, converts it to machine-readable text, and digitizes documents and receipts with Azure vision, including bounding boxes and text data.
Behind the Scenes - How Azure AI Vision Works3:27
Lab - Calling the Computer Vision API7:16
Lab - Calling the Computer Vision API - Resources0:19
Custom Vision - Tailoring AI for Your Needs1:59
Lab - Working with the Custom Vision service9:27
Lab - Recognizing Faces with Azure Vision Studio2:42
Lab - Recognizing Faces with the Face API1:58
Lab - Recognizing Faces with the Face API - Resources0:15
Lab - From Scans to Insights - Azure AI Document Intelligence4:39
This chapter focuses on the Form Recognizer API
Section Summary & Key Takeaways2:58
Short Quiz

Getting Started with Azure AI Language Service3:18
Lab - Key Phrase Extraction in Language Service2:38
This chapter focuses on a lab on Text Analytics for Key Phrases
Lab - Key Phrase Extraction via API Call7:20
Explore key phrase extraction with Azure language service via REST API, creating a multi-services account and posting a JSON payload to endpoint to return phrases like rooftop pool and hotel.
Lab - Key Phrase Extraction via API Call - Resources0:20
This chapter focuses on a lab on the resources for Text Analytics for Key Phrases
Lab - Language Detection with Azure AI Language3:28
This chapter focuses on a lab on Text Analytics for Language Detection
Lab - Language Detection with Azure AI Language - Resources0:24
Lab - Sentiment Analysis with Azure AI Language3:31
This chapter focuses on a lab on Text Analytics for Sentiment Analysis
Lab - Sentiment Analysis with Azure AI Language - Resources0:25
Lab - Named Entity Recognition with Azure AI Language3:03
This chapter focuses on a lab on Text Analytics for Entity Recognition
Lab - Named Entity Recognition with Azure AI Language - Resources0:21
This chapter focuses on a lab on resources for Text Analytics for Entity Recognition
Lab - Introduction to Azure AI Translator Service2:32
This chapter focuses on a lab on the Translator service
Lab - Introduction to Azure AI Translator Service - Resources0:08
Overview of Azure Speech Service1:49
Lab - Speech to Text with Azure Speech Service2:13
This chapter focuses on a lab on for Speech to Text
Lab - Text to Speech with Azure Speech Service1:49
This chapter focuses on a lab on for Text to Speech
Lab - Azure Speech - Text to Speech - Resources0:25
This chapter focuses on resources for Text to Speech
Question and Answering in Azure AI Language3:52
Lab - Creating a Knowledge Base3:57
Connect and configure Azure AI search with Microsoft Foundry, fine-tune for custom question answering, and build a knowledge base by adding Q&A pairs from URLs or files.
Lab - Creating a Knowledge Base - Resources1:08
Lab - Testing the Knowledge Base2:49
Short Quiz

Introduction to Generative AI3:09
Understanding Large Language Models5:11
Getting Started with ChatGPT5:33
Exploring More Features in ChatGPT5:09
Responsible AI - Using AI Ethically3:40
AI-Powered Code Generation4:01
Explore how AI-powered tools generate code from prompts across models like OpenAI, GitHub Copilot, Google Gemini, and Claude. Build a simple AI-900 quiz app with HTML, CSS, and JavaScript.
AI-Powered Code Generation - Resources0:27
Introduction to the OpenAI Platform4:41
Signing Up for the OpenAI Platform6:17
Using the Playground in OpenAI3:24
Using the Playground in OpenAI - Resources0:24
Working with System Messages3:16
Working with System Messages - Resources0:36
Working with GPT Models - Key Insights2:31
Lab - Creating a Microsoft Foundry resource2:21
Lab - Microsoft Foundry - Deploying a Model6:22
Lab - Microsoft Foundry - Using the playground4:05
Learn to interact with a model in Microsoft Foundry's playground, configure system instructions and parameters like max completion tokens and reasoning effort, and observe the model's planning and chain-of-thought reasoning.
Microsoft Foundry - Using an image generation model3:18
Learn to generate code with a Python script for Azure OpenAI, and explore image generation prompts in Microsoft Foundry using the gpt-image model.
Example of Python code interacting with OpenAI - Overview1:53
Demonstrates a simple Python program to interact with a GPT-3 model deployed on Azure AI foundry via REST API calls, with quick steps to install Python and Visual Studio Code.
Example of Python code interacting with OpenAI - Installing Python1:06
Install Python on Windows by downloading the latest version, running the installer with admin permissions, adding python.exe to the path, optionally customizing the install, and verifying the version.
Example of Python code interacting with OpenAI - Installing Visual Studio0:58
Example of Python code interacting with OpenAI - Implementation8:04
Set up a Python program in VS Code to send a prompt to a Microsoft Foundry deployment via the OpenAI library, using the completions and responses APIs.
Example of Python code interacting with OpenAI - Implementation - Resources0:14

Requirements

Azure AI services are cloud-based — some familiarity with Microsoft Azure or basic cloud concepts will be beneficial but is not required.
No prior development experience is needed for the AI-900 content. For AI-901 sections, basic Python coding syntax knowledge is recommended.
A basic understanding of data concepts such as structured/unstructured data and databases is useful when exploring AI models and services.

Description

Release v5.0 – May 2026 (AI-901 Beta Content Added)

The AI-900 exam will retire on June 30, 2026, and is being replaced by AI-901: Azure AI Fundamentals (Refreshed). Since AI-901 is currently in beta, this course now covers both exams so you can prepare for either path with confidence.

What's new in AI-901?

AI-901 is a substantial redesign that pivots from individual Azure AI services to the unified Microsoft Foundry platform. The new exam emphasises implementing generative AI apps and agents, deploying models in the Foundry portal, building lightweight client applications with the Foundry SDK, and extracting information using Azure Content Understanding. Examinotion

The exam is structured around two core skill areas:

Identify AI Concepts and Responsibilities (40–45%) — covering responsible AI principles, AI model components and configurations, and AI workloads including generative and agentic AI, text analysis, speech, computer vision, and information extraction Microsoft Learn
Implement AI Solutions using Microsoft Foundry (55–60%) — covering generative AI apps and agents, text and speech solutions, computer vision and image generation, and information extraction using Azure Content Understanding in Foundry Tools

Release v4.0 - August2025

Artificial Intelligence is no longer the future—it’s the present, reshaping how industries operate and how we work, live, and interact. With tools like ChatGPT and Azure AI becoming part of everyday workflows, staying current with AI fundamentals is not just useful—it’s essential.

The entire course has been updated and refreshed. All chapters have been re-recorded. This has been done to ensure that all contents now reflect the most recent changes to the services on the Azure platform.

All course contents have also been aligned as per any changes to the course objectives.

Release v3.0 - January 2025

All course contents have also been aligned as per any changes to the course objectives.

Additional questions also added to the Practice Tests available at the end of the course.

Release v2.0 - July 2023

All course contents have also been aligned as per any changes to the course objectives.

Quiz questions have also been added to the end of each section.

This course is a preparation course for students who want to attempt the Exam AI-900: Microsoft Azure AI Fundamentals

This course has contents for the Exam AI-900

The objectives covered in this course are

Describe AI workloads and considerations (15-20%) - Here we will discuss the the basics on AI-based workloads.
Describe fundamental principles of machine learning on Azure (30-35%) - Here we will understand what is Machine Learning. We will also look at labs on how to work with the Machine Learning service.
Describe features of computer vision workloads on Azure (15-20%) - Here we will look at the different features of the Computer Vision service. We will also look at the Custom Vision service, the Face service and the Form Recognizer service.
Describe features of Natural Language Processing (NLP) workloads on Azure (15-20%) - Here we will look at services such the Text Analytics service, the Language Understanding Intelligence Service , the Speech service.
Describe features of conversational AI workloads on Azure (15-20%) - Here we will see the basics on the QnA Maker service and the Bot Framework.

There is also a number of labs available in this course. These labs focus on the different services available in Azure when it comes to Machine Learning and Artificial Intelligence.

Who this course is for:

Beginners with no AI or Azure background who want to earn the Microsoft Azure AI Fundamentals certification via the AI-900 or the new AI-901 exam.
IT professionals and cloud practitioners looking to add AI skills to their existing Azure or cloud computing experience.
Aspiring AI developers who want a foundational understanding of Microsoft Foundry, generative AI apps, and AI agents before moving on to the AI Engineer or Data Scientist certifications.

AI-901-Microsoft Azure AI Fundamental Certification

What you'll learn

Explore related topics

Course content

AI-901 - Identify AI concepts and capabilities21 lectures • 1hr 29min

AI-901 - Implement AI solutions - Microsoft Foundry26 lectures • 2hr

AI-901 - Implement AI solutions - Azure AI Services21 lectures • 1hr 4min

AI-900 - Introduction and basics on Azure7 lectures • 27min

AI-900 - Describe AI workloads and considerations13 lectures • 53min

AI-900 - Describe fundamental principles of machine learning on Azure25 lectures • 2hr 21min

AI-900 - Describe features of computer vision workloads on Azure16 lectures • 57min

AI-900 - Describe features of Natural Language Processing and Conversational AI20 lectures • 46min

AI-900 - Describe features of generative AI workloads on Azure23 lectures • 1hr 17min

Practice Section1 lecture • 1min

Requirements

Description

Who this course is for: