Azure AI Fundamentals (AI-901) is a hands-on introductory course that covers the skills measured in the AI-901 exam, from responsible AI, generative AI and model deployment to building simple chat apps, agents, speech, vision and Content Understanding solutions on Microsoft Foundry. It suits newcomers to AI, developers with basic Python and anyone preparing for the AI-901 exam.
AI is now part of almost every team's work, from chatbots that answer customers and document summaries to meeting transcripts and automatic invoice reading. Yet many people are still unsure which kind of AI suits each task, how the models actually work and how to start building real solutions in the cloud without neglecting their responsibility to users. A sound grounding in both the concepts and the practice is therefore the first important step for anyone who will work with AI on Microsoft Azure.
This course covers the skills measured in the AI-901 Microsoft Azure AI Fundamentals exam, following the latest outline on Microsoft Learn. Day one lays the conceptual foundations: responsible AI principles, how generative AI works, choosing and deploying models, and AI workloads for text, speech, computer vision and information extraction. Day two is hands-on in Microsoft Foundry in each learner's own Azure subscription, from writing prompts and building a chat app and an agent with the Foundry SDK to speech and vision apps and extracting information from documents, images, audio and video with Content Understanding. The course helps with exam preparation, but learners book the exam with Microsoft themselves. (2 days, 6 hours per day, 12 hours in total, Beginner level.)
Course Details
This course covers the skills measured in the AI-901 Microsoft Azure AI Fundamentals exam, following the latest outline on Microsoft Learn. It runs for 2 days, 6 hours per day (12 hours in total, 09:00-16:00), as lectures with labs. Beginner level. It builds on Microsoft Azure Fundamentals (AZ-900), which focuses on the cloud in general, and concentrates on AI in Microsoft Foundry. Every lab runs in the learner's own Azure subscription (a free account,
pay-as-you-go or a company sandbox); model calls and Foundry Tools are billed by actual usage at the learner's own cost, and each lab ends with clean-up steps. The course helps with exam preparation but is not official Microsoft courseware; it does not include the exam fee or a voucher, and learners book the exam with Microsoft themselves. Learners take home a lab guide, Python code for every lab and a summary of the skills in the exam outline.
Section 1: Lab: AI on Azure and the AI-901 Outline
Section 2: Workshop: Responsible AI Principles
Section 3: Lab: How Generative AI Works
Section 4: Lab: Deploying Models and Setting Parameters
Section 5: Lab: Text, Speech, Vision and Information Extraction Workloads
Section 6: Lab: Prompts and a Chat App with the Foundry SDK
Section 7: Lab: Building an Agent in Foundry
Section 8: Lab: Text, Speech and Vision Apps
Section 9: Lab: Information Extraction with Content Understanding
Section 10: Workshop: Review and Exam Preparation
No public rounds are open right now. Join the waiting list and we will contact you first when the next round opens, or ask us on LINE. Or call 02-570-8449 or 088-807-9770
Microsoft defines six Responsible AI principles: fairness, so systems treat people equitably; reliability and safety; privacy and security of data; inclusiveness, so everyone can use them; transparency, so users understand how the system works; and accountability, so people remain responsible for its outcomes. These principles can be used in practice to assess an organisation's AI work.
Generative AI such as a large language model is trained on vast amounts of text to predict the next piece of text, building an answer one piece at a time. The units it reads and writes are tokens, which can be words, parts of words or punctuation, and they determine length limits and usage charges. Temperature is a parameter that controls randomness: low values give consistent, focused answers, and high values give more varied, creative ones.
Start by creating a Foundry project in your Azure subscription and choosing a suitable model from the model catalogue. Deploy it, test it in the playground, adjust parameters such as temperature and write a system prompt that sets the assistant's role and limits. Then call the model from Python with the Foundry SDK to build the chat app, and delete the resources when you finish so you are not charged further.
It suits AI newcomers who want a structured understanding of AI on Azure, developers and students who can write Python, IT, data and business analyst teams choosing AI services, and people preparing for AI-901 or who have passed AZ-900. You should read and write basic Python and know Azure basics such as subscriptions and resource groups; no machine learning or advanced maths is required.
You will be able to explain responsible AI and how generative AI works, distinguish AI workload types, deploy models on Microsoft Foundry, build simple chat apps and agents with the Foundry SDK, create apps that analyse text, speech and images, extract data from documents with Content Understanding, and plan your AI-901 exam preparation. Participants receive a Certificate of Completion with its own number that can be verified online, separate from the Microsoft exam.
Bring a laptop with a browser, VS Code and Python, plus your own Azure subscription, such as a free account, pay-as-you-go or an organisational sandbox. Model usage is billed to you at actual consumption, and steps for deleting resources are given after each lab. The course helps you prepare but is not official Microsoft training, does not include an exam voucher, and you register for the exam yourself.
Articles are published in Thai.
Building a chatbot prototype on a language model takes very little time, but taking AI apps and agents into real use across an organisation is another matter. Development teams have to choose the right models and services for each task, bring in…
Microsoft Azure is widely used by Thai organizations, especially those already running Microsoft 365 and Windows. The Microsoft Certified: Azure Fundamentals (AZ-900) credential is the best starting point for anyone who wants to understand the cloud and…
Organisations that move to Microsoft Azure often start by creating machines and services as the need arises. Before long they face permissions that are far too broad, resources nobody can say who owns, costs that climb every month, networks exposed to the…
