Technology
Microsoft SC-200: Sentinel Threat Hunting Without Dashboard Tourism
Threat hunting is not the act of opening dashboards until something looks unusual. Dashboards summarize known signals; hunting starts with uncertainty. The analyst forms a hypothesis about attacker behavior, identifies the data that could prove or disprove it, runs targeted queries, preserves meaningful findings, and decides whether the result should become an incident, a detection, a control improvement, or simply a documented negative result. The October 21, 2026 Microsoft SC-200 English-language objectives explicitly assess threat hunting with Kusto Query Language (KQL) across Microsoft Defender XDR and Sentinel. A useful hunt…
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…
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…
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…
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…
Microsoft SC-401: Information Security Alerts Need Clear Owners
Information-security alerts are valuable only when someone is responsible for turning them into decisions. A policy can detect sensitive data leaving an approved boundary, an insider-risk pattern can surface unusual activity, and an audit system can record a suspicious action, but none of those signals become risk reduction until the organization knows who investigates and what happens next. Home/Microsoft/Microsoft SC-401: Information Security Alerts Need Clear OwnersMicrosoftPublished October 3, 2026On this pageEvery alert should have a purpose before it has a severityPolicy owners and queue owners are different rolesTriage needs a…
Microsoft AZ-900: Cloud Economics: CapEx, OpEx, and the Cost of Commitment
Cloud economics is often summarized as a shift from capital expenditure to operating expenditure, but that shorthand can hide the decisions that actually matter. Moving to cloud services changes when organizations pay, what they pay for, how quickly costs can change, and how much financial commitment they make before demand is known. The cloud-concepts portion of The July 20, 2026 Microsoft AZ-900 objectives includes consumption-based pricing, cloud cost considerations, and the distinction between capital and operating expenditure. Those ideas become practical when finance and engineering compare a predictable baseline workload…
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…
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,…
Microsoft AI-103: Hybrid Search and Reranking
Home/Certifications/Microsoft/Microsoft AI-103: Hybrid Search and Reranking AI & Machine LearningUpdated October 11, 2026 · 9 min read A user can describe a problem without using any of the words stored in the answer. Another user might ask for an exact error code that must not be paraphrased at all. Those two requests should not be forced through one retrieval strategy. Azure AI Search offers lexical, vector and hybrid search, with optional semantic ranking, but the features are useful only when their ranking behavior matches the application’s questions. The engineering challenge…
Microsoft AI-103: Managed Identities for AI Apps
Home/Certifications/Microsoft/Microsoft AI-103: Managed Identities for AI Apps AI & Machine LearningUpdated October 11, 2026 · 9 min read An AI application may access a model endpoint, search index, storage container and internal tool API in one user request. Putting an access key for every dependency into application settings creates a maintenance burden and a serious incident risk when one secret leaks. Managed identities can replace many stored Azure credentials with Microsoft Entra tokens issued to a workload, but they do not make authorization automatic. The hard design work is deciding…
Microsoft AI-103: Multimodal Vision Workflows
Home/Certifications/Microsoft/Microsoft AI-103: Multimodal Vision Workflows AI & Machine LearningUpdated October 11, 2026 · 9 min read A photograph of a damaged shipment may show a cracked housing, a serial-number label and handwritten delivery notes in one frame. A single caption can describe the picture while missing the identifier needed to process a claim. A single OCR pass can capture the label but miss the physical damage. Azure AI teams therefore need to combine visual understanding, text extraction, validation and human judgment around the decision the application must make. Microsoft Foundry…
Microsoft AI-103: Extracting Structure from Complex Documents
Home/Certifications/Microsoft/Microsoft AI-103: Extracting Structure from Complex Documents AI & Machine LearningUpdated October 11, 2026 · 8 min read An invoice can be readable to a person and still be unsuitable for automated processing. A total may sit below several discounts, a signature can cross an annotation, and the same document may contain tables, handwriting, and scanned attachments. Treating all those details as a single text string loses the relationships that make a business decision possible. Azure Content Understanding provides a way to extract structured evidence, but engineers still have to…
Microsoft AI-103: Evaluating Agents Beyond the Final Answer
Home/Certifications/Microsoft/Microsoft AI-103: Evaluating Agents Beyond the Final Answer AI & Machine LearningUpdated October 11, 2026 · 8 min read An agent can produce a convincing final message after taking an unsafe route to get there. It may select the wrong tool, read records outside the user’s authority, quietly retry a non-idempotent action, or use a document instruction that should never have been trusted. A conventional answer-quality score will not reveal those defects. Evaluating agents in Microsoft Foundry therefore means inspecting a sequence of decisions alongside the outcome, with tests for…
Microsoft AI-103: Scaling AI Apps Without Cost Surprises
Home/Certifications/Microsoft/Microsoft AI-103: Scaling AI Apps Without Cost Surprises AI & Machine LearningUpdated October 11, 2026 · 8 min read An AI application may respond quickly for ten test users and collapse under a seemingly ordinary production launch. One chat request can invoke retrieval, several models, tools, retries, and a long generated answer; each part consumes a different resource and may hit a different limit. Azure model deployments also distinguish traffic quotas from the processing capacity an application can reliably use. Sustainable scale therefore begins with a workload model, not an…