How to pass Microsoft Certified: Azure AI Fundamentals (AI-901)
12 min read2 domains coveredFree practice, no sign-up
Microsoft Certified: Azure AI Fundamentals (AI-901) is the current entry-level Azure AI exam. It replaced AI-900, which retired on 30 June 2026, and it is a different exam: where AI-900 spread across five domains of largely conceptual, classic-machine-learning material, AI-901 has just two domains, is noticeably more technical, and is built on the current Microsoft Foundry platform and naming. If you are studying from AI-900 notes or an older course, most of it is now out of date, and that mismatch is the single biggest reason people underestimate this exam.
The exam tests two things in proportion. The smaller half asks you to identify AI concepts and capabilities: the six Microsoft responsible-AI principles, how generative models work and how you pick and configure one, and which AI workload fits a described scenario. The larger half asks you to implement AI solutions with Microsoft Foundry: building generative and agentic apps, working with text and speech, using vision and image generation, and extracting information with Azure Content Understanding. Because it is a Fundamentals exam there is no live coding, but the questions assume you know which Foundry surface does what.
It suits developers, data professionals, analysts, and technical decision-makers who need a current, credible grounding in Azure AI. The material is broad rather than deep, so a focused few weeks closes the gap, provided you study the current outline and not the retired one.
AI-901 is the current Azure AI Fundamentals exam that replaced the retired AI-900. It is only two domains, more technical, and built on Microsoft Foundry, so studying AI-900 material is the main way people go wrong.
Difficulty
Foundational
Best for
Developers, data and analytics professionals, and technical decision-makers who want a current, recognised grounding in Azure AI and the Microsoft Foundry platform.
Prerequisites
None. Some familiarity with programming concepts, REST APIs, and the Azure portal helps because AI-901 is more technical than the retired AI-900, but nothing is formally assumed.
Typically 40 to 60 questions
Questions
45 min
Time allowed
700 / 1000
Pass mark
$99
Exam cost (USD)
300
Practice questions
How this exam thinks
AI-901 rewards two habits, and both come back to currency and single-best judgement.
First, it is built on the current Microsoft Foundry naming, and a retired name is a wrong answer, not a stylistic quibble. The exam expects Microsoft Foundry as the platform, with a clear split between the Foundry portal (a visual surface for deploying and testing) and the Foundry SDK (the code path for building an application). Information extraction is Azure Content Understanding in Foundry Tools; speech is Azure Speech in Foundry Tools. The AI-900-era names, such as Cognitive Services, Computer Vision API, Text Analytics, LUIS, QnA Maker, and Form Recognizer, are now traps. When an option names one of those, or attributes a task to the wrong Foundry surface, it is usually the distractor.
Second, the questions are short scenarios where several options are plausible and only one fits the requirement as written. The reliable discriminations are: which responsible-AI principle a stated concern maps to, especially transparency versus accountability; which model a stated capability constraint calls for; which workload a scenario describes, keeping agentic AI (an agent that plans and takes actions to complete a task) distinct from plain generative output; and which service performs a task, such as choosing Azure Content Understanding over a general vision model for structured extraction. Read the requirement in the last line first, then judge each option against that requirement rather than against general truth.
What each domain tests and how to study it
The AI-901 blueprint is split across 2 domains. Weights are the official share of the exam; see the official exam guide for the authoritative breakdown.
What you must be able to do. Match a stated concern to the correct responsible-AI principle, reason about how generative models work and how you select and configure one, and map a scenario to the right AI workload.
In one sentenceThe conceptual half: the six responsible-AI principles, how generative models work and how you choose and configure them, and matching a scenario to the correct AI workload.
Recall check: answer these from memory first
Name the six Microsoft responsible-AI principles and give the one concern each addresses.
State in one line the difference between transparency and accountability as responsible-AI principles.
Given a scenario, say whether it is generative, agentic, text analysis, speech, computer vision, or information extraction, and why.
What it tests. The six Microsoft responsible-AI principles and the consideration each addresses; how generative models work at a conceptual level, including tokens and next-token prediction, plus selecting a model by capability and the deployment and configuration parameters such as temperature that shape its behaviour; and identifying which AI workload a scenario needs, across generative and agentic AI, text analysis, speech, computer vision, and information extraction, keeping the text-analysis techniques distinct.
How to study it. Learn the six principles as concern-to-principle mappings rather than definitions, and drill the transparency-versus-accountability pair until it is automatic because it is the most-tested confusion. For models, anchor the sampling parameters to outcomes you can reason about: a low temperature gives reproducible, on-message output. For workloads, practise placing a scenario into exactly one category, and be strict that an agent that plans and takes actions is agentic, not generative. Keep keyword extraction, entity detection, sentiment analysis, and summarization separate in your mind.
Easy to confuse
Transparency versus accountability. Transparency is making the system and its decisions understandable to the people affected, including its limits; accountability is people and governance remaining answerable for how the system behaves. If the concern is understanding a decision it is transparency; if it is who is responsible and what oversight exists it is accountability.
Agentic AI versus generative AI. Generative AI produces content such as text or images in response to a prompt; agentic AI plans and takes actions, calling tools or knowledge, to complete a task towards a goal. If the scenario describes taking steps and using tools rather than just producing an answer, it is agentic.
Selecting a model by capability. A language model handles text, a multimodal model accepts images or audio alongside text, an embedding model turns content into vectors for similarity, and an image-generation model creates pictures. The exam states a capability constraint and expects the one model class that meets it, so match the stated need rather than defaulting to a general chat model.
Worked example from the AI-901 bank
lock_openFree sampleIdentify AI concepts and capabilitieseasy
A bank deploys a model that declines some loan applications. The team wants applicants and reviewers to be able to understand which factors drove each decision and how the system reaches its conclusions. Which Microsoft responsible AI principle does this goal address?
ATransparencycheck_circle Correct
BFairness
CAccountability
DReliability and safety
Transparency means making an AI system and the factors behind its decisions understandable to the people it affects. The requirement is that people can understand how the system works and why it produced a particular outcome, which is precisely what the transparency principle is intended to deliver.
Why A is correct: Transparency is the principle of making an AI system understandable, so that people can see how it works and which factors influenced a given decision.
Why B is wrong: Loan decisions are a classic setting for bias concerns, which makes fairness tempting, but fairness is about giving comparable groups comparable treatment, not about making the reasoning behind a decision understandable.
Why C is wrong: Being answerable for decisions sounds close, but accountability is about people and governance remaining responsible for the system, not about the system itself being intelligible to those affected.
Why D is wrong: Reliability and safety covers consistent, safe operation under varied conditions, so it is tempting for a high-stakes banking use, but it does not concern explaining how a decision was reached.
What you must be able to do. Choose the correct Microsoft Foundry surface and capability for a described build, across generative and agentic apps, text and speech, vision and image generation, and information extraction.
In one sentenceThe larger, more technical half: building with Microsoft Foundry across generative and agentic apps, text and speech, vision, and information extraction, using the right surface and capability each time.
Recall check: answer these from memory first
Say when a build needs the Foundry portal and when it needs the Foundry SDK.
Distinguish a multimodal model interpreting an image from a generative image model creating one.
Name the Foundry capability for extracting structured fields from documents, and say why a general vision model is the wrong choice.
What it tests. Implementing AI solutions with Microsoft Foundry: writing prompts and deploying and interacting with a model in the Foundry portal, building with the Foundry SDK, and creating and testing a single-agent solution; text analysis and responding to spoken prompts, plus Azure Speech in Foundry Tools for speech-to-text and text-to-speech; interpreting visual input with a multimodal model versus generating new images; and extracting structured information from documents, images, audio, and video with Azure Content Understanding in Foundry Tools.
How to study it. This domain carries the larger weight, so spend the most time here. Build a mental map of Foundry: the portal for deploying and testing visually, the SDK for building an application in code, and the named capabilities (Azure Speech, Azure Content Understanding) that sit in Foundry Tools. Practise the single-best decisions the exam leans on: portal versus SDK, a multimodal model that interprets an existing image versus a generative model that creates a new one, and Azure Content Understanding versus a general vision model for structured field extraction. Use only current names in your notes so a retired one stands out as wrong.
Easy to confuse
Foundry portal versus Foundry SDK. The portal is the visual surface for deploying a model, testing prompts, and creating and testing an agent; the SDK is the code path for building a lightweight client application. If the scenario is building an app in code it is the SDK; if it is deploying or testing visually it is the portal.
Azure Content Understanding versus a general vision model. Azure Content Understanding in Foundry Tools is purpose-built to extract consistent structured fields from documents, images, audio, and video; a general multimodal vision model can read an image but is not built for repeatable structured output. A requirement to pull the same named fields from many documents points to Content Understanding.
A multimodal model accepting speech versus Azure Speech. A deployed multimodal model can take a spoken prompt directly as input; Azure Speech in Foundry Tools is the dedicated capability for speech-to-text and text-to-speech. If the task is a standalone recognition or synthesis feature it is Azure Speech; if it is feeding spoken input into a multimodal model it is the model itself.
Worked example from the AI-901 bank
lock_openFree sampleImplement AI solutions by using Microsoft Foundryhard
A developer has finished prototyping a chat experience in the Microsoft Foundry portal and now needs to embed the same deployed model inside a C# web service so that inference requests are issued programmatically at runtime. Which Foundry surface is designed for this?
AThe Foundry SDK, which exposes client libraries so an application can authenticate to and call the deployed model from its own code.check_circle Correct
BThe Foundry portal, which is a browser-based workspace for building and testing projects interactively rather than for embedding calls in application code.
CAzure Content Understanding, which extracts fields from documents and media rather than providing programmatic access to a deployed chat model.
DThe model catalogue, which lists available models to browse and deploy but does not itself issue runtime inference requests from application code.
The Foundry SDK is the surface an application uses to call a deployed model programmatically, whereas the portal is for interactive work. Embedding a deployed model in application code requires client libraries that handle authentication and inference calls at runtime; the Foundry SDK provides exactly these, while the portal is an interactive design and testing environment.
Why A is correct: The Foundry SDK provides client libraries for languages such as C# and Python, letting application code authenticate and send inference requests to a deployed model at runtime, which is exactly what embedding the model in a web service requires.
Why B is wrong: The portal is tempting because that is where the prototyping happened, but it is an interactive browser workspace for building and testing, not a mechanism for issuing calls from within a compiled application.
Why C is wrong: Azure Content Understanding is an information-extraction capability for documents, images, audio, and video, so it does not give an application programmatic access to a deployed conversational model.
Why D is wrong: The model catalogue helps you find and deploy a model, but it is a discovery surface, not the runtime client an application uses to call the model once deployed.
A study plan that works
Confirm you are studying AI-901, not AI-900
Day 1
Read the current Microsoft AI-901 study guide and note the skills-measured date. AI-900 retired on 30 June 2026, so discard AI-900 notes and courses. Book a provisional exam date now: a fixed date turns open-ended study into a plan.
Lock the responsible-AI principles and core concepts
Week 1
Learn the six responsible-AI principles as concern-to-principle mappings, drilling transparency versus accountability. Get the generative-model basics solid: tokens, next-token prediction, model selection by capability, and the effect of parameters such as temperature.
Master the AI workloads
Week 1
Practise placing scenarios into exactly one workload: generative, agentic, text analysis, speech, computer vision, or information extraction. Keep the text-analysis techniques distinct and treat agentic AI as separate from generative.
Go deep on Microsoft Foundry (the larger domain)
Weeks 2-3
Spend the most time here. Learn the Foundry portal versus SDK split, single-agent solutions, text and speech with Azure Speech, vision versus image generation, and information extraction with Azure Content Understanding. Use current names only.
Practise on scenarios with every option explained
Week 3
Move to full practice sets and read the explanation for every question, including the ones you got right. The exam tests single-best judgement between plausible options, so understanding why each distractor is wrong is where the marks are.
Find and close your weak areas
Week 4
Use your per-domain accuracy to drill whichever domain is dragging you down rather than re-reading what you already know. Repeat until both domains clear the pass line with margin on unseen questions.
Sit a timed mock and review it
Week 4
Take at least one full timed mock to rehearse pacing and flag-and-return. Treat the score as a per-domain readiness signal, then review every missed question before booking or sitting.
Know when you're ready
Readiness for AI-901 is a score on questions you have not seen before, not a feeling that the material is familiar. Those are different things, and the gap between them is where people fail. Re-reading notes builds fluency, and fluency feels like knowledge, so confidence rises while real recall does not. The fix is to test yourself: if you can answer fresh scenario questions and explain why the wrong options are wrong, you know it; if you can only nod along to an explanation, you do not yet.
Be especially careful with anything you carried over from AI-900. That exam retired on 30 June 2026, and material written against it will feel confident and be wrong here, because the naming and the platform have moved to Microsoft Foundry. Trust your measured per-domain accuracy on current AI-901 questions over your gut, and make sure the Foundry-heavy second domain, which carries the larger weight, clears the pass line comfortably rather than scraping it.
This guide gives you the map. The practice bank is where you find out whether you can navigate it, with an explanation of why the right answer is right and every wrong one is wrong on every question. Readiness scoring tells you when you are there. Not before.
Ready to put this into practice?
Free AI-901 questions, every answer explained. No sign-up.
Read the last line of the question first. It tells you what is actually being asked, so you can read the scenario looking for the answer rather than memorising detail.
Treat a retired name as a wrong answer. Cognitive Services, Computer Vision API, Text Analytics, LUIS, QnA Maker, and Form Recognizer are AI-900-era names; the current platform is Microsoft Foundry.
For responsible-AI questions, decide between transparency and accountability first. Understanding a decision is transparency; being answerable for the system is accountability.
When a build is described, ask whether it needs the Foundry portal or the SDK. Deploying and testing visually is the portal; building an app in code is the SDK.
For structured extraction from documents, reach for Azure Content Understanding, not a general vision model. Repeatable named-field extraction is what Content Understanding is built for.
Eliminate two options fast. Most questions have two clearly weaker choices; removing them turns a guess into a coin flip at worst.
Flag and move on. Do not lose time on one hard item when easier marks are waiting; the timer rewards covering every question first.
Frequently asked questions
Is AI-901 the same as AI-900?
No. AI-900 retired on 30 June 2026 and AI-901 is its replacement. AI-901 has two domains instead of five, is more technical, and is built on the current Microsoft Foundry platform, so older AI-900 study material is largely out of date.
Is AI-901 hard?
It is a Fundamentals exam, so it is broad rather than deep and there is no live coding. The difficulty is in single-best judgement between plausible options and in using current Foundry naming, which is why scenario practice that explains every option matters more than memorising definitions.
How long should I study for AI-901?
Most candidates with some technical background are ready in three to four weeks of focused study. Spend the most time on the Microsoft Foundry domain, which carries the larger weight, and make sure you are studying the current outline rather than AI-900 material.
Do I need coding experience to pass AI-901?
No. The exam is conceptual and there is no live coding. It is more technical than the retired AI-900, so familiarity with programming ideas, REST APIs, and which Foundry surface does what helps, but you are not asked to write code under exam conditions.
What is the pass mark for AI-901?
Microsoft scores on a scaled range and the published pass mark is shown in the facts panel above. Scoring is scaled, so your raw percentage and the scaled score are not the same thing; aim to clear both domains comfortably in practice rather than scraping a target.
Which domain should I focus on?
Implementing AI solutions with Microsoft Foundry is the larger domain, so it deserves the most time. Identifying AI concepts and capabilities is the smaller, more conceptual domain covering responsible AI, model selection, and workloads.
What is Microsoft Foundry and why does it matter for this exam?
Microsoft Foundry is the platform AI-901 is built around, with a visual portal for deploying and testing and an SDK for building applications. Named capabilities such as Azure Speech and Azure Content Understanding sit in Foundry Tools. Knowing which surface and capability does what is central to the larger domain.
Is the Azure AI Fundamentals certification worth it?
It is a practical, current credential for developers, data professionals, and technical decision-makers who need a recognised grounding in Azure AI. Because it tracks the current Microsoft Foundry naming, it is a more useful first rung than the retired AI-900 before the associate-level Azure AI credentials.
Examworthy is not affiliated with or endorsed by Microsoft. This guide is original study material based on the public exam blueprint. We never reproduce live exam items. AI-901 and related marks belong to their respective owners.
