Microsoft Azure AI Fundamentals (AI-901) Exam Prep

What's inside

1. Level 1: Exam Orientation; Fairness, Reliability, PrivacyFree
   [Identify AI concepts and capabilities: Describe principles of responsible AI] You learn the exam basics: the AI-901 study guide is Microsoft's own document, free on Microsoft Learn and not copied here; Microsoft's AI-901 exam page states the duration; you need 700 to pass; and this course is independent of Microsoft and promises no pass. Then you cover the considerations for fairness, reliability and safety, and privacy and security in an AI solution through scenario questions.
2. Level 2: Inclusiveness, Transparency and AccountabilityFree
   [Identify AI concepts and capabilities: Describe principles of responsible AI] You cover the considerations for inclusiveness, transparency and accountability in an AI solution, and practise telling all six responsible AI principles apart in 'which principle applies' scenario questions.
3. Level 3: How Generative AI Models Work
   [Identify AI concepts and capabilities: Identify AI model components and configurations] You learn how generative AI models work: tokens, embeddings, the transformer that predicts the next token, the context window, and why models can produce confident but wrong output.
4. Level 4: Choosing, Deploying and Configuring Models
   [Identify AI concepts and capabilities: Identify AI model components and configurations] You learn to identify an appropriate AI model based on capabilities (chat, reasoning, multimodal, embedding, image generation, speech) from the Foundry model catalog, and to identify appropriate model deployment options and configuration parameters such as temperature, top_p and max tokens.
5. Level 5: AI Workloads and Text Analysis Techniques
   [Identify AI concepts and capabilities: Identify AI workloads] You learn to identify scenarios for the common AI workloads (generative AI, agentic AI, text analysis, speech, computer vision and information extraction) and to describe the common text analysis techniques: keyword extraction, entity detection, sentiment analysis and summarization.
6. Level 6: Speech, Computer Vision and Image Generation
   [Identify AI concepts and capabilities: Identify AI workloads] You learn to identify the features and capabilities of speech recognition (speech to text) and speech synthesis (text to speech), and of computer vision and image-generation models, including image classification, object detection, OCR, captioning and creating images from text.
7. Level 7: Information Extraction Techniques
   [Identify AI concepts and capabilities: Identify AI workloads] You learn to identify techniques to extract information from text, images, audio and videos, such as entity and field extraction, OCR and document layout analysis, transcription, and pulling structured fields out of unstructured content.
8. Level 8: Writing Effective System and User Prompts
   [Implement AI solutions by using Microsoft Foundry: Implement generative AI apps and agents by using Foundry] You learn to create effective system and user prompts for generative AI models: setting the role, rules and output format in the system message, giving clear instructions and examples in the user message, and grounding answers in supplied data.
9. Level 9: Deploy and Chat with a Model in Foundry Portal
   [Implement AI solutions by using Microsoft Foundry: Implement generative AI apps and agents by using Foundry] You learn to deploy a model and interact with it in the Foundry portal: create a Foundry project, deploy a model from the model catalog, and test system prompts and parameters in the chat playground.
10. Level 10: Build a Chat Client with the Foundry SDK
    [Implement AI solutions by using Microsoft Foundry: Implement generative AI apps and agents by using Foundry] You learn to create a lightweight chat client application in Python with the Foundry SDK, connecting to your project, sending system and user messages to a deployed model, and keeping the conversation history.
11. Level 11: Create and Test a Single Agent in Foundry
    [Implement AI solutions by using Microsoft Foundry: Implement generative AI apps and agents by using Foundry] You learn to create and test a single-agent solution in the Foundry portal: choose a model, write the agent's instructions, add tools or knowledge, and test it in the agent playground.
12. Level 12: Build a Client App for an Agent
    [Implement AI solutions by using Microsoft Foundry: Implement generative AI apps and agents by using Foundry] You learn to create a lightweight Python client application for an agent, connecting to the Foundry project, starting a conversation with the agent, sending user messages and reading its responses.
13. Level 13: Build a Text Analysis App
    [Implement AI solutions by using Microsoft Foundry: Implement AI solutions for text and speech by using Foundry] You learn to build a lightweight Python application that includes text analysis, using Azure Language in Foundry Tools or a prompted model to detect sentiment, extract key phrases and entities, and summarize text.
14. Level 14: Spoken Prompts and Azure Speech Apps
    [Implement AI solutions by using Microsoft Foundry: Implement AI solutions for text and speech by using Foundry] You learn to respond to spoken prompts by using a deployed multimodal model that accepts audio input, and to build a lightweight application that uses Azure Speech in Foundry Tools for speech to text and text to speech.
15. Level 15: Vision Apps and Image Generation
    [Implement AI solutions by using Microsoft Foundry: Implement AI solutions with computer vision and image-generation capabilities by using Foundry] You learn to interpret visual input in prompts by using a deployed multimodal model, to build a lightweight application that includes vision capabilities, and to create new visual outputs by using an image-generation model.
16. Level 16: Content Understanding: Documents, Forms, Images
    [Implement AI solutions by using Microsoft Foundry: Implement AI solutions for information extraction by using Foundry] You learn to extract information from documents and forms by using Azure Content Understanding in Foundry Tools, and to extract information from images, with prebuilt and custom analyzers and field schemas.
17. Level 17: Content Understanding: Audio, Video and Apps
    [Implement AI solutions by using Microsoft Foundry: Implement AI solutions for information extraction by using Foundry] You learn to extract information from audio and video by using Content Understanding, and to build a lightweight Python application with information extraction capabilities that submits content to an analyzer and uses the structured results.
18. Level 18: Timed Mock Exam (50 Questions, 45 Minutes) Timed mock
    A timed mock exam of 50 original scenario questions in 45 minutes, drawn from every level and weighted like the study guide (40–45% AI concepts and capabilities, 55–60% implementing with Microsoft Foundry), with every distractor explained and a pass mark of 70%.

Access

The first 2 levels are free with a free account. Every level, the podcast edition and the AI tutor come with All Access at £4.99/month or any Creator plan — see pricing.

Start free →