6 real AI-901 sample questions, each with an explanation of why every option is right or wrong. No account, no card. This is the reasoning the AI-901 tests: knowing why the tempting answer is wrong, not just spotting the right one.
The real AI-901 is Typically 40 to 60 questions questions in 45 minutes, pass mark 700 / 1000. For a domain-by-domain breakdown and a study plan, read the AI-901 study guide. The full bank has 300 questions.
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.
lock_openFree sampleImplement AI solutions by using Microsoft Foundryhard
A team wants a solution that, given the goal "reconcile this invoice", will decide which steps to take, call a lookup tool to fetch purchase-order data, and then update a record, all without a person choosing each step. Which type of AI workload does this describe?
- AGenerative AI, which produces new content such as text or images in response to a prompt but does not plan or invoke tools to act on a goal.
- BAgentic AI, in which an agent plans a sequence of steps and takes actions such as calling tools or knowledge sources to complete a task.check_circle Correct
- CText analysis, which extracts information such as sentiment or key phrases from existing text rather than taking actions to complete a task.
- DComputer vision, which interprets images and video rather than orchestrating steps and tool calls towards a goal.
Agentic AI is distinguished from generative AI by planning steps and taking actions with tools to complete a goal. An agent goes beyond producing content: it reasons about a goal, plans a sequence of steps, and takes actions such as calling tools or knowledge sources, which is what separates the agentic workload from plain generation.
Why A is wrong: Generative AI is a close trap because agents are built on generative models, but generation alone only returns content for a prompt; it does not plan a sequence of steps or call tools to change external state.
Why B is correct: The defining trait of agentic AI is that the system plans steps and takes actions towards a goal, including invoking tools and knowledge sources, which matches deciding steps, calling a lookup tool, and updating a record autonomously.
Why C is wrong: Text analysis reads and characterises existing text, so it could describe the invoice but cannot plan steps, call a lookup tool, or update a record to complete the goal.
Why D is wrong: Computer vision interprets visual input; it does not plan multi-step actions or invoke tools, so it does not fit a task defined by autonomous reconciliation of data.
lock_openFree sampleImplement AI solutions by using Microsoft Foundryhard
In a chat application built on a deployed Foundry model, a developer wants to set the assistant's persistent role and behaviour rules, such as "you are a legal assistant that answers only in British English", so that they apply to every turn regardless of what the end user types. Where should this instruction be placed?
- AIn the user prompt, since that field carries the end user's per-turn input rather than the assistant's standing role.
- BIn an embedding vector, since embeddings represent the meaning of text numerically and cannot hold behavioural rules.
- CIn the system prompt, which establishes the model's role and standing behaviour for the whole conversation.check_circle Correct
- DIn the model deployment name, since that value only identifies which deployed model is called and cannot carry behavioural rules.
The system prompt sets a model's persistent role and behaviour, whereas the user prompt carries each turn of end-user input. Persistent role and behaviour rules must live in the system prompt because it is applied across every turn of the conversation, unlike the user prompt which represents the changing per-turn input from the end user.
Why A is wrong: The user prompt does carry text to the model, which makes it tempting, but it represents each turn of end-user input and is not the place to fix behaviour that must persist across the whole conversation.
Why B is wrong: Embeddings numerically represent the meaning of text for search and comparison; they are not a channel for instructing a model how to behave, so they cannot carry persistent role rules.
Why C is correct: The system prompt sets the assistant's role and standing rules for the entire conversation, so persistent behaviour such as acting as a legal assistant answering only in British English belongs there.
Why D is wrong: The deployment name simply identifies which deployed model an application calls; it is an identifier, not an instruction channel, so it cannot hold behavioural guidance.
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.
lock_openFree sampleIdentify AI concepts and capabilitieseasy
An organisation defines a governance framework that names which staff are responsible for an AI system's outcomes, mandates human oversight of its use, and requires the ability to override or shut down the system. Which Microsoft responsible AI principle does this reflect?
- ATransparency
- BAccountabilitycheck_circle Correct
- CPrivacy and security
- DInclusiveness
Accountability means people stay answerable for an AI system through governance, human oversight, and the power to intervene. Naming responsible people, requiring oversight, and keeping the power to override are the governance controls that make humans answerable for the system, which is the accountability principle.
Why A is wrong: A governance framework can involve disclosure, which makes transparency tempting, but transparency is about making the system understandable, not about naming who is answerable for its outcomes.
Why B is correct: Accountability is the principle that people remain answerable for how an AI system behaves, supported by governance structures, human oversight, and the ability to intervene.
Why C is wrong: Oversight can feel like a control measure, but privacy and security is specifically about protecting data and defending the system against misuse, not about assigning human responsibility.
Why D is wrong: Inclusiveness sounds relevant to how an organisation treats people, but it concerns empowering and reaching everyone, not establishing who is responsible and oversees the system.
lock_openFree sampleIdentify AI concepts and capabilitieseasy
A recruitment screening model is evaluated to confirm that it does not systematically disadvantage applicants of a particular gender or ethnic background, and that comparable candidates receive comparable outcomes. Which Microsoft responsible AI principle guides this evaluation?
- AReliability and safety
- BInclusiveness
- CFairnesscheck_circle Correct
- DTransparency
Fairness means an AI system treats people equitably and avoids systematically disadvantaging particular groups. Checking that comparable candidates receive comparable outcomes regardless of gender or ethnicity is a direct application of the fairness principle, which targets equitable treatment across groups.
Why A is wrong: The word evaluation suggests testing that the model works, which makes reliability and safety tempting, but that principle is about consistent and safe operation, not about equitable treatment across groups.
Why B is wrong: Inclusiveness also concerns different groups of people, so it is a plausible trap, but it is about empowering and being accessible to everyone, whereas the concern here is unequal outcomes between groups.
Why C is correct: Fairness is the principle that an AI system should treat all people equitably and avoid systematically advantaging or disadvantaging particular groups.
Why D is wrong: Transparency would help explain a decision, which sounds useful in hiring, but this scenario is about the outcomes being equitable, not about the reasoning being understandable.
Examworthy is not affiliated with or endorsed by Microsoft. All questions are original, blueprint-aligned practice material. We never reproduce live exam items. AI-901 and related marks belong to their respective owners.
