πŸ”’ Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AI-901 Domain 1
Domain 1 β€” Module 1 of 11 9%
1 of 26 overall

AI-901 Study Guide

Domain 1: AI Concepts and Capabilities

  • What is AI? Your First 10 Minutes Free
  • Responsible AI: The Six Principles Free
  • How Generative AI Actually Works Free
  • Choosing the Right AI Model Free
  • Deploying AI Models: Options & Settings
  • AI Workloads at a Glance
  • Text Analysis: Keywords, Entities & Sentiment
  • Speech: Recognition & Synthesis
  • Computer Vision: Seeing the World
  • Image Generation: Creating with AI
  • Information Extraction: From Chaos to Structure

Domain 2: Implement AI Solutions Using Foundry

  • Prompting Fundamentals: System & User Prompts
  • Microsoft Foundry: Your AI Command Center Free
  • Building a Chat App with the Foundry SDK
  • Agents in Foundry: Create & Test
  • Building an Agent Client App
  • Building a Text Analysis App
  • Multimodal: Responding to Speech
  • Azure Speech in Foundry Tools
  • Visual Prompts: Images as Input
  • Generating Images with AI
  • Building a Vision App
  • Content Understanding: Documents & Forms
  • Multimodal Extraction: Images, Audio & Video
  • Building an Extraction App
  • Exam Prep: Putting It All Together

AI-901 Study Guide

Domain 1: AI Concepts and Capabilities

  • What is AI? Your First 10 Minutes Free
  • Responsible AI: The Six Principles Free
  • How Generative AI Actually Works Free
  • Choosing the Right AI Model Free
  • Deploying AI Models: Options & Settings
  • AI Workloads at a Glance
  • Text Analysis: Keywords, Entities & Sentiment
  • Speech: Recognition & Synthesis
  • Computer Vision: Seeing the World
  • Image Generation: Creating with AI
  • Information Extraction: From Chaos to Structure

Domain 2: Implement AI Solutions Using Foundry

  • Prompting Fundamentals: System & User Prompts
  • Microsoft Foundry: Your AI Command Center Free
  • Building a Chat App with the Foundry SDK
  • Agents in Foundry: Create & Test
  • Building an Agent Client App
  • Building a Text Analysis App
  • Multimodal: Responding to Speech
  • Azure Speech in Foundry Tools
  • Visual Prompts: Images as Input
  • Generating Images with AI
  • Building a Vision App
  • Content Understanding: Documents & Forms
  • Multimodal Extraction: Images, Audio & Video
  • Building an Extraction App
  • Exam Prep: Putting It All Together
Domain 1: AI Concepts and Capabilities Free ⏱ ~10 min read

What is AI? Your First 10 Minutes

Artificial intelligence isn't science fiction β€” it's in your phone, your inbox, and your search bar. Let's start with what AI actually means, how it works at a high level, and why it matters for your career.

What is artificial intelligence?

β˜• Simple explanation

AI is software that learns patterns from data instead of following exact instructions.

Traditional software is like a recipe book β€” you give it step-by-step instructions, and it follows them exactly. AI is more like teaching someone to cook β€” you show them thousands of dishes, and eventually they figure out how to make new ones on their own.

When your email app filters spam, when your phone recognises your face, when a chatbot answers your question β€” that’s AI. It’s not magic. It’s maths, data, and clever engineering.

Artificial intelligence (AI) is a branch of computer science focused on building systems that can perform tasks typically requiring human intelligence. These tasks include understanding language, recognising images, making decisions, and generating content.

Modern AI systems work by training mathematical models on large datasets. During training, the model identifies patterns and relationships in the data. Once trained, the model can make predictions, classifications, or generate new content based on new inputs it hasn’t seen before.

AI is not a single technology β€” it’s an umbrella term covering machine learning, deep learning, natural language processing, computer vision, and generative AI.

AI vs traditional software

Traditional software vs AI software
FeatureTraditional SoftwareAI Software
How it worksFollows explicit rules written by a developerLearns patterns from data during training
Handles new situationsOnly if a rule exists for that caseCan generalise from training to new inputs
Example'If email contains X, move to Spam folder''Based on patterns in 1 million emails, this looks like spam'
Gets better over time?Only if a developer updates the rulesCan improve with more or better training data
Needs data?Only configurationNeeds large amounts of training data

The AI landscape β€” what you’ll learn in this cert

The AI-901 exam covers six types of AI workloads. Think of them as different skills AI can have:

AI WorkloadWhat It DoesReal-World Example
Generative AICreates new content (text, images, code)ChatGPT writing an email draft
Agentic AITakes actions and makes decisions autonomouslyAn AI agent booking a meeting based on your calendar
Text analysisUnderstands and extracts meaning from textDetecting negative sentiment in customer reviews
SpeechConverts speech to text and text to speechMeeting transcription, voice assistants, real-time captions
Computer visionAnalyses images and videoA hospital AI flagging abnormalities in X-rays
Information extractionPulls structured data from documentsReading invoice numbers from scanned PDFs
ℹ️ Where does Microsoft fit in?

Microsoft’s AI platform is called Microsoft Foundry (formerly Azure AI Studio). It’s where you deploy AI models, build AI-powered apps, and create intelligent agents β€” all within Azure.

The AI-901 exam splits into two halves:

  • Domain 1 (40-45%): Understand AI concepts β€” what AI can do, how it works, responsible AI
  • Domain 2 (55-60%): Build AI solutions in Foundry β€” deploy models, write prompts, create apps

This module gets you oriented. The rest of the course goes deep on each area.

Meet the characters

Throughout this course, you’ll follow four organisations using AI:

CharacterWho They AreAI Use Cases
πŸ₯ MediSparkHealthcare startup, 40 staffAI diagnostic assistant, medical image analysis, patient document extraction
πŸŽ“ PriyaComputer science studentLearning Azure AI, first Foundry project, exploring models
🏒 DataFlow CorpEnterprise analytics company, 2000 employeesAI at scale, speech transcription, customer support agents
🌿 GreenLeafSustainable agriculture co-opCrop image analysis, invoice extraction, weather report generation

These scenarios help anchor abstract concepts to real situations β€” exactly how the exam tests you.

🎬 Video walkthrough

🎬 Video coming soon

What is AI? β€” AI-901 Module 1

What is AI? β€” AI-901 Module 1

~10 min

Flashcards

Question

What is artificial intelligence?

Click or press Enter to reveal answer

Answer

Software that learns patterns from data instead of following exact instructions. It can understand language, recognise images, make decisions, and generate content.

Click to flip back

Question

What are the six AI workload types covered in AI-901?

Click or press Enter to reveal answer

Answer

Generative AI, agentic AI, text analysis, speech, computer vision, and information extraction.

Click to flip back

Question

What is Microsoft Foundry?

Click or press Enter to reveal answer

Answer

Microsoft's unified Azure platform for deploying AI models, building AI-powered apps, and creating intelligent agents. Formerly known as Azure AI Studio.

Click to flip back

Knowledge Check

Knowledge Check

MediSpark wants to automatically read patient intake forms (handwritten PDFs) and extract the patient's name, date of birth, and insurance number into their database. Which AI workload type best describes this task?

Knowledge Check

Priya is learning about AI and reads that 'AI learns patterns from data.' What makes this fundamentally different from traditional software?


Next up: Responsible AI β€” the six principles Microsoft uses to keep AI helpful, fair, and safe.

Next β†’

Responsible AI: The Six Principles

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.