AI-901 exam guide: format, domains, preparation

Who the AI-901 exam is for

AI-901 is the exam for the Microsoft Certified: Azure AI Fundamentals certification. The study guide describes the candidate as someone at the beginning of their career in AI solution development, with conceptual knowledge of AI solutions in Azure and the foundational technical skills to work with them.

The exam is not purely conceptual. The study guide also asks for knowledge of Python coding syntax and programming techniques, familiarity with Azure resources, and familiarity with REST APIs, SDKs and CLIs. Several objectives ask you to build a lightweight application, so expect questions about how a small client calls a model, an agent or a Foundry tool.

Exam format

Conditions worth knowing

• Seat time is the time to allocate for the whole session; exam duration is the time you have to answer.
• No access to Microsoft Learn during the exam: Learn access is not available on fundamentals exams.
• Localized versions are updated approximately eight weeks after the English version. If the exam is not available in your preferred language, you can request an additional 30 minutes.
• Preview features: most questions cover generally available (GA) features, but the exam may contain questions on preview features if those features are commonly used.

Skill areas and weights

The study guide defines two skill areas, each split into groups of objectives.

What each area covers

• Responsible AI: considerations for fairness, reliability and safety, privacy and security, inclusiveness, transparency and accountability.
• Models: how generative AI models work, choosing a model based on its capabilities, deployment options and configuration parameters.
• Workloads: generative and agentic AI, text analysis (keyword extraction, entity detection, sentiment analysis, summarization), speech recognition and synthesis, computer vision and image generation, and information extraction from text, images, audio and video.
• Agents and apps: system and user prompts, deploying a model in the Foundry portal, a chat client with the Foundry SDK, a single-agent solution and a client application for an agent.
• Text, speech, vision and extraction: spoken and visual prompts to a deployed multimodal model, Azure Speech in Foundry Tools, new visual outputs from generative models, and Azure Content Understanding in Foundry Tools for documents, forms, images, audio and video.

The implementation area weighs more than the concepts area, and every objective in it names Foundry. Hands-on time in the Foundry portal and SDK is therefore part of the preparation, not an extra.

AI-900, renamed services and retired services

The AI-900 exam page states that AI-900 was retired on June 30, 2026, and has been replaced by AI-901. Study material written for AI-900 may use older product names. The Microsoft Foundry documentation maps them: Azure AI Studio / Azure AI Foundry became Microsoft Foundry, and Azure AI services became Foundry Tools.

The "find documentation" list at the end of the study guide still links to some services that are being withdrawn:

• Language Understanding (LUIS): its documentation states that LUIS will be fully retired on March 31, 2026, and that LUIS resource creation isn't available.
• Anomaly Detector: its documentation announces its retirement on 1 October 2026 and states that new Anomaly Detector resources can't be created since 20 September 2023.

Do not build your revision around these two services. Follow the objectives of the study guide, which point to Foundry, Foundry Tools and Content Understanding.

How to prepare

1. Read the AI-901 exam page on Microsoft Learn for registration, languages and current conditions.
2. Read the AI-901 study guide and copy every objective into a checklist. Describe the exam from this list, not from older summaries.
3. Follow the two free learning paths: AI concepts for developers and technology professionals, then Get started with AI applications and agents on Azure. Each has 7 modules.
4. Refresh basic Python and the idea of calling a service through a REST API or an SDK, since the study guide lists both.
5. In the Foundry portal, deploy a model, test system prompts, then create and test a single agent. Repeat the same steps from a small Python client.
6. For each Foundry tool named in the objectives (Speech, Content Understanding), note what input it takes and what output it returns.
7. Practise with our AI-901 practice exam under timed conditions, then review each missed question in the free study mode.
8. Shortly before the exam, re-check the date of the skills measured on the study guide in case the objectives have changed.