Practice Exams:

AI & Machine Learning

Azure AI Engineering

Azure AI engineering has moved beyond the question of whether a model can produce a plausible response. Production systems have to control identity, data access, retrieval, safety, model choice, capacity, deployment, monitoring, and release behavior as one operating system. Microsoft now documents much of this stack under Microsoft Foundry, while many practitioners still encounter Azure AI Foundry terminology in existing projects, architecture discussions, and search results. The practical engineering problem is the same: turn a model capability into a service that can be operated safely and predictably. Home/Microsoft/Azure AI EngineeringMicrosoftPublished…

Read More

Microsoft SC-100: Data Security for Copilots, Agents, and AI Services

Generative AI changes the way employees and applications discover, summarize, transform, and act on enterprise information. It does not remove the older rules of data security. The current SC-100 Microsoft Cybersecurity Architect exam now explicitly includes data and AI security in the cybersecurity architect’s responsibilities, which is appropriate because Copilots, agents, and AI services expose weaknesses in classification, permissions, lifecycle, and monitoring much faster than traditional manual workflows. Home/Microsoft/Microsoft SC-100: Data Security for Copilots, Agents, and AI ServicesMicrosoftPublished October 3, 2026On this pageAI security begins with knowing where sensitive data…

Read More

Microsoft AI-900: The New Azure AI Fundamentals Path

Home/After ai 900 the new azure ai fundamentals pathThe Microsoft AI-900 exam retired on June 30, 2026, but it did not retire the Azure AI Fundamentals certification itself. The credential now uses the Microsoft AI-901 exam, which reflects a broader shift in Microsoft’s AI platform toward Microsoft Foundry, generative AI, agents, and simple implementation tasks.On this pageAI-900 is retired, not bookableThe certification continues under AI-901AI-901 is aimed at technical beginnersMicrosoft Foundry in the current pathwayMachine learning fundamentals still matterGenerative AI and agents are core topicsResponsible AI remains a core foundationOld…

Read More

Microsoft AI-900: What Changes With AI-901

Home/Ai 900 to ai 901 what changed in azure ai fundamentalsThe move from retired Microsoft AI-900 to current Microsoft AI-901 is more than an exam-number change. Both exams connect to the same Microsoft Azure AI Fundamentals certification, but Microsoft changed the audience assumptions, the skills balance, and the platform context to reflect how entry-level AI solution development now works.On this pageAI-901 targets technical beginnersThe exam weight shifted toward implementationMicrosoft Foundry replaces the old service-by-service mental modelClassic machine learning concepts still provide the baseGenerative AI becomes practical implementationAgents are now part…

Read More

Microsoft AI-900: Machine Learning, Generative AI, and Agents

Home/Machine learning generative ai and agents a beginners mental modelAI beginners often encounter machine learning, generative AI, large language models, multimodal models, and agents within the same week. The terms are related, but they do not describe the same layer of a solution. Treating them as interchangeable makes it harder to choose a tool, understand risk, or explain what a system is actually doing.On this pageMachine learning learns from dataGenerative AI produces new outputsLanguage models are not complete applicationsAgents add goals, tools, and action authorityMultimodal AI still needs problem definitionComputer…

Read More

Microsoft AI-901: Computer Vision, Language, and Generative AI

Home/Computer vision language and generative ai start with the problemTeams often choose an AI service before they have defined the problem. A stakeholder asks for “AI,” someone proposes a chatbot, and only later does the group discover that the real task was to extract fields from documents, classify images, detect entities in text, or generate a draft from approved source material. Better AI design starts by framing the information transformation before selecting a model.On this pageStart with input and decision requirementsComputer vision interprets visual informationLanguage workloads range from analysis to…

Read More

Microsoft AI-900: Skills That Still Matter in the Current AI Path

Home/What ai 900 still teaches in microsofts current ai pathMicrosoft AI-900 retired on June 30, 2026, but retirement does not make every concept in the old exam obsolete. Machine learning basics, common AI workloads, responsible AI, computer vision, language processing, and generative AI still provide useful foundations. What changed is the platform context and the level of practical participation expected from a beginner.On this pageCore machine-learning vocabulary still mattersResponsible AI principles transfer almost unchangedComputer vision implementations have evolvedLanguage tasks across model typesGenerative AI becomes a core applicationAgents are new fundamentals…

Read More

Microsoft AB-900: Conditional Access in an AI-Enabled Workplace

Generative AI changes how people find and use organizational information, but it does not remove the basic identity question that has always mattered: who is requesting access, under what conditions, and how much trust should the organization place in that session? Microsoft 365 Copilot and agents make this question more visible because they can help users move across mail, files, meetings, chats, and other work context with much less friction than traditional manual search. Home/Microsoft/Microsoft AB-900: Conditional Access in an AI-Enabled WorkplaceMicrosoftPublished October 3, 2026On this pageAI makes an authenticated…

Read More

Microsoft AB-900: The Microsoft 365 Admin Role Now Includes AI

The Microsoft 365 administrator has always worked across boundaries. A licensing problem can look like an application problem. A Teams issue can actually be an identity or policy issue. A SharePoint permission mistake can become a security incident. Microsoft 365 Copilot and agents add another layer to that interconnected environment, which means AI administration is becoming part of the normal tenant operating model rather than a completely separate specialty. Home/Microsoft/Microsoft AB-900: The Microsoft 365 Admin Role Now Includes AIMicrosoftPublished October 3, 2026On this pageAI administration starts with tenant fundamentalsLicense management…

Read More

Amazon AWS AIF-C01: GenAI Security Starts With Data, Identity, and Access

Generative AI introduces new attack surfaces, but many of the most damaging failures still begin with familiar security problems: data was accessible to the wrong identity, credentials were over-privileged, secrets were embedded in prompts, logs exposed sensitive content, or an application allowed a model to call a tool without independent authorization. Treating GenAI security as a completely new discipline can distract teams from the controls they already know how to apply. Home/Amazon/Amazon AWS AIF-C01: GenAI Security Starts With Data, Identity, and AccessAmazonPublished October 3, 2026On this pageClassify the data before…

Read More

Amazon AWS AIF-C01: Evaluating AI Outputs Beyond a Single Accuracy Score

Generative AI evaluation becomes misleading when every problem is reduced to one “accuracy” number. A model can be factually correct but irrelevant, helpful but unsafe, well grounded but too slow, concise but incomplete, or excellent on common prompts while failing badly on an important minority of cases. Product quality is multidimensional, so evaluation has to reflect the real task. Home/Amazon/Amazon AWS AIF-C01: Evaluating AI Outputs Beyond a Single Accuracy ScoreAmazonPublished October 3, 2026On this pageStart with a task-specific definition of successReference-based metrics work only when a meaningful reference existsHuman evaluation…

Read More

Amazon AWS AIF-C01: Choose AWS AI Services by Use Case, Not Hype

AWS offers a wide AI and machine learning portfolio, which makes service selection easy to overcomplicate. The simplest decision rule is to start with the business task and choose the highest-level managed service that meets the requirement. Use a specialized AI API when the job is well defined, Amazon Bedrock when the application needs foundation models and generative AI capabilities, and Amazon SageMaker AI when the organization needs deeper control over building, training, customizing, or operating machine learning models. Home/Amazon/Amazon AWS AIF-C01: Choose AWS AI Services by Use Case, Not…

Read More

Microsoft SC-401: Protecting AI Data Beyond Traditional DLP

Generative AI changes the path that sensitive information can take. A user no longer has to attach a document to an email or upload it to a file-sharing site to expose data. They can paste text into a prompt, ask an assistant to summarize a confidential document, connect an agent to a repository, or allow an AI workflow to retrieve information automatically. Traditional DLP remains important, but it is no longer the whole data-protection story. Home/Microsoft/Microsoft SC-401: Protecting AI Data Beyond Traditional DLPMicrosoftPublished October 3, 2026On this pageAI expands the…

Read More

Microsoft AI-103: Building Reliable RAG Retrieval

Home/Certifications/Microsoft/Microsoft AI-103: Building Reliable RAG Retrieval AI & Machine LearningUpdated October 11, 2026 · 9 min read Retrieval-augmented generation fails quietly when a fluent answer rests on the wrong document. An employee may ask whether an expense is reimbursable, receive a persuasive response, and only later discover that the retrieved policy was superseded months ago. Better prompting cannot repair a missing or unauthorized source. Building RAG on Azure therefore starts with an evidence contract: which documents may answer which questions, how fresh they must be, and what the application should…

Read More

Microsoft AI-103: Safe Tool-Using Agents

Home/Certifications/Microsoft/Microsoft AI-103: Safe Tool-Using Agents AI & Machine LearningUpdated October 11, 2026 · 9 min read A conversational assistant becomes an operational agent when it can do more than describe a task. It might look up an order, create a support ticket, or request a change to a customer record. The design risk changes at that boundary: a plausible sentence is one kind of mistake, but an unintended action can alter a business system. Microsoft Foundry provides agent runtimes and tools, yet the application still owns authorization, validation, side effects,…

Read More