Exam AI-901: Microsoft Azure AI Fundamentals (Video)

Description

• Copyright 2027
• Edition: 1st

• Online Video
• ISBN-10: 0-13-596092-4
• ISBN-13: 978-0-13-596092-9

Prepare to pass the AI-901 exam and launch your AI career with confidence.

Microsoft Foundry represents the unified platform for building AI applications and agents on Azure. It consolidates what used to be scattered across Azure OpenAI Service, Azure AI Studio, and a sprawl of standalone Azure AI services into a single, coherent development experience.

The AI-901 exam validates that candidates understand not just what AI can do, but how to make it do things--deploying models, crafting effective prompts, building lightweight client applications with the Foundry SDK, and creating single-agent solutions. The technology stack covered spans responsible AI principles, generative and agentic AI patterns, text analysis, speech recognition and synthesis, computer vision, image generation, and information extraction via Azure Content Understanding.

For an entry-level exam, this is remarkably ambitious, and thats exactly why learners need comprehensive, hands-on video training to complement the Microsoft Learn documentation. Each lesson begins with a crisp explanation of the why behind a skill, then drops into the Foundry portal or VS Code for live-coded walkthroughs.

Skill Level:

• Beginner to Intermediate

Learn How To:

• Describe and apply the six principles of responsible AI in real Azure deployments
• Identify the right AI model for a given task: LLMs, small language models, multimodal models, code models, and embedding models
• Deploy models in the Foundry portal and interact with them through effective system and user prompts
• Build a lightweight chat client application using the Foundry SDK
• Create and test single-agent solutions in the Foundry portal, then build client applications for agents
• Implement text analysis, speech recognition, and speech synthesis using Foundry
• Interpret visual input and generate images using deployed multimodal models
• Extract information from documents, images, audio, and video using Azure Content Understanding

Course requirement:

Pre-requisites:

• Basic familiarity with cloud computing concepts (IaaS, PaaS, SaaS)
• Beginner-level Python coding ability (variables, functions, loops)
• Access to an Azure subscription with pay-as-you-go billing enabled (demos use low-cost tiers and pay-per-call model deployments; budget a few dollars total, and run the included cleanup script after each lesson)
• Comfort navigating the Azure portal

Who Should Take This Course:

Job titles:

• Business analysts exploring AI capabilities
• IT professionals pivoting into AI roles
• Junior developers building their first AI applications
• Data analysts expanding into AI/ML
• Students and career-changers entering the Azure ecosystem

About Pearson Video Training:

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Sams, and Que. Topics include IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at  http://www.informit.com/video.

Video Lessons are available for download for offline viewing within the streaming format. Look for the green arrow in each lesson.



Sample Content

Table of Contents

Lesson: Identify AI Workloads and Common Scenarios

    Identify scenarios for common AI workloads, including generative and agentic AI, text analysis, speech, computer vision, and information extraction

    Describe how Microsoft Foundry supports AI workloads in Azure and where each workload type fits in modern cloud architectures

    Differentiate between classic machine learning, generative AI, and agentic AI and map real-world business scenarios to the correct approach

    Demo: Foundry Resource and Project Architecture

    Demo: Identify AI Workloads in the Foundry Portal

Lesson: How Generative AI Models Work and How to Choose Them

    Describe how generative AI models work

    Identify an appropriate AI model, based on capabilities

    Identify appropriate model deployment options and configuration parameters

    Demo: LLM tokenization and Foundry project deployment

    Demo: Tour the Foundry model catalog

    Demo: Reduce hallucination with grounding

Lesson: Responsible AI: Fairness, Reliability and Safety, Privacy and Security

    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

    Demo: Fairness

    Demo: Reliability & Safety

    Demo: Defense in Depth

    Demo: Privacy & Security

Lesson: Responsible AI: Inclusiveness, Transparency, Accountability

    Describe considerations for inclusiveness in an AI solution

    Describe considerations for transparency in an AI solution

    Describe considerations for accountability in an AI solution

    Demo: Inclusiveness

    Demo: Transparency

    Demo: Accountability, Disclosure & Ownership

Lesson: Text Analysis and Speech Concepts

    Describe common text analysis techniques, including keyword extraction, entity detection, sentiment analysis, and summarization

    Identify features and capabilities of speech recognition and speech synthesis

    Describe how natural language processing powers both classic text analysis and modern generative language models

    Demo: Touring the Azure AI Language service

    Demo: Touring the Azure AI Speech service

    Demo: Classic vs. Generative Language and Speech processing

    Demo: Azure AI Language Python SDK example

Lesson: Computer Vision and Image-Generation Concepts

    Identify features and capabilities of computer vision and image-generation models

    Describe core computer vision tasks, including image classification, object detection, OCR, and facial analysis

    Describe how multimodal and image-generation models interpret visual input and produce visual outputs from natural-language prompts

    Demo: Touring the Computer Vision API and Tool

    Demo: Azure AI Vision Python SDK example

    Demo: Multimodal Image Generation with GPT in Foundry

Lesson: Information Extraction Concepts

    Identify techniques to extract information from text, images, audio, and videos

    Describe how multimodal models and Azure Content Understanding convert unstructured content into structured, grounded representations

    Compare rule-based, machine learning, and multimodal approaches to information extraction and when each is appropriate

    Demo: One Analyzer, Four Modalities

    Demo: Azure AI Content Understanding Python SDK example

Lesson: Tour Microsoft Foundry and Deploy Your First Model

    Deploy a model and interact with it in the Foundry portal

    Navigate the Microsoft Foundry portal and identify its primary workspaces, projects, model catalog, and playground surfaces

    Select a model from the Foundry model catalog based on task requirements, context length, and cost footprint

    Demo: Foundry Hub, Project, and Catalog Tour

    Demo: Filter the Catalog and Pick a Model

    Demo: Deploy and Exercise in the Playground

Lesson: Craft Effective System and User Prompts

    Create effective system and user prompts for generative AI models

    Distinguish between system messages and user messages and describe how each shapes model behavior and response quality

    Apply prompt engineering techniques including role instructions, few-shot examples, and structured output formatting

    Demo: Few-Shot Ticket Triage in the Playground

    Demo: Structured Outputs with JSON Schema

    Demo: Azure OpenAI Prompt Patterns Python SDK example

Lesson: Build a Lightweight Chat Client Application with the Foundry SDK

    Create a lightweight chat client application by using the Foundry SDK

    Authenticate a Foundry SDK client application by using Microsoft Entra identity and keyless credentials

    Send chat completions to a deployed Foundry model from a Python client application and handle the response

    Demo: Bootstrap and Keyless Auth

    Demo: Chat Completion and Read-Send-Print Loop

Lesson: Create and Test a Single-Agent Solution in the Foundry Portal

    Create and test a single-agent solution in the Foundry portal

    Describe the components of a Microsoft Foundry agent, including role, instructions, tools, and knowledge sources

    Test an agent in the Foundry portal playground and review the conversation trace to troubleshoot behavior

    Demo: Create the Agent in the Portal

    Demo: Attach Instructions and Knowledge

    Demo: Add a Tool and Read the Trace

Build a Lightweight Client Application for an Agent

    Create a lightweight client application for an agent

    Connect a client application to a Foundry agent endpoint by using the Foundry SDK

    Send user messages to an agent and handle multi-turn conversation state from the client application

    Demo: SDK Bootstrap and Connect to the Agent

    Demo: Thread plus Message plus Run

Build a Text Analysis Application with Foundry

    Build a lightweight application that includes text analysis

    Call Azure AI Language capabilities from a client application by using the Foundry SDK

    Extract entities, key phrases, sentiment, and summaries from unstructured text and display the results in a client UI

    Demo: Entities, Key Phrases, Sentiment, and Opinion Mining

    Demo: Extractive vs. Abstractive Summarization & PII Detection

Build a Speech-Enabled Application with Azure Speech in Foundry Tools

    Respond to spoken prompts by using a deployed multimodal model

    Build a lightweight application by using Azure Speech in Foundry Tools

    Configure speech-to-text and text-to-speech in a client application and wire it to a Foundry model for conversational interaction

    Demo: Bootstrap and Speech-to-Text from the Microphone

    Demo: Pipeline Code Walkthrough

Build a Computer Vision and Image-Generation Application

    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

    Demo: Vision Understanding in the Chat Playground

    Demo: Vision Input from Code

Extract Information from Documents, Images, Audio, and Video with Content Understanding

    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

    Demo: Testing Prebuilt Analyzers

    Demo: Lightweight Extraction App (Python SDK)



Updates

Submit Errata

