Practice Exams:

AI & Machine Learning

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…

Read More

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…

Read More

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…

Read More

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…

Read More

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…

Read More

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…

Read More

Microsoft AI-103: Observability for Agentic Applications

Home/Certifications/Microsoft/Microsoft AI-103: Observability for Agentic Applications AI & Machine LearningUpdated October 11, 2026 · 8 min read A generative AI service can return HTTP 200 while giving a user the wrong answer. The model might have relied on an outdated retrieved passage, silently ignored an authorization error, or called a tool with valid syntax and the wrong account identifier. Ordinary web metrics show that the request completed, but not why the outcome was wrong. AI observability has to connect user intent to retrieval, model decisions, tools, and the final result…

Read More

ServiceNow CIS-DF: Build ServiceNow Data Foundations for AI and Automation

AI and automation amplify whatever data foundation they are given. When identity is stable, ownership is clear, relationships are meaningful, and lifecycle state is current, automation can make reliable decisions at scale. When those foundations are weak, the same automation can spread errors faster than a human process ever could. A recommendation engine can route work to the wrong owner, an automated remediation can target the wrong CI, or an AI assistant can summarize a service relationship that the CMDB itself does not represent accurately. Home/ServiceNow/ServiceNow CIS-DF: Build ServiceNow Data…

Read More

Microsoft AB-100: AI Across Dynamics 365, Power Platform, and Foundry

Home/Certifications/Microsoft/Microsoft AB-100: AI Across Dynamics 365, Power Platform, and Foundry AI & Machine LearningReviewed October 11, 2026 · 8 min read Many Microsoft organizations already have business processes spread across Dynamics 365, Dataverse, Power Apps, Power Automate, Microsoft 365, and Azure services before an AI initiative begins. Agentic architecture should not flatten those systems into one new “AI platform.” It should decide how AI participates in an existing application landscape: where the authoritative records remain, where deterministic workflow belongs, where model reasoning adds value, and how actions are governed across…

Read More

Microsoft AB-100: Integration Design for AI-Powered Business Processes

Home/Certifications/Microsoft/Microsoft AB-100: Integration Design for AI-Powered Business Processes AI & Machine LearningReviewed October 11, 2026 · 8 min read An AI-powered business process is rarely one model call. It usually crosses systems that were built for different purposes: CRM, ERP, ticketing, document repositories, messaging, custom APIs, databases, identity services, and workflow engines. The AI layer may interpret a request or choose a next step, but the reliability of the complete solution depends on ordinary integration architecture—contracts, state, identity, retries, idempotency, error handling, and ownership. On this pageStart from the business…

Read More

Databricks Generative AI Engineer Associate: Evaluating RAG Answers

  Retrieval-augmented generation is easy to demo and surprisingly difficult to evaluate. A response can sound fluent while citing weak evidence, retrieve the right passage but answer incompletely, or be factually correct for reasons unrelated to the supplied context. The current Databricks Generative AI Engineer Associate exam and Generative AI Engineer Associate certification treat retrieval evaluation, agent scoring, SME feedback, tracing, and monitoring as core engineering work because “looks good to me” cannot support reliable iteration. Home/Databricks/Databricks Generative AI Engineer Associate: Evaluating RAG AnswersDatabricksPublished October 3, 2026On this pageStart with…

Read More

Databricks Generative AI Engineer Associate: Embedding Choices Matter

  Embedding models are often chosen with a single line of configuration, but that choice shapes what a semantic search system can retrieve. Context length, vector dimension, language coverage, domain fit, normalization, latency, and cost all influence the result. The current Databricks Generative AI Engineer Associate exam and Generative AI Engineer Associate certification explicitly connect embedding-model selection to source documents, expected queries, optimization strategy, vector search, and retrieval evaluation. Home/Databricks/Databricks Generative AI Engineer Associate: Embedding Choices MatterDatabricksPublished October 3, 2026On this pageEmbeddings turn meaning into a geometry that retrieval depends…

Read More

Databricks Generative AI Engineer Associate: Serving Models Reliably

  A foundation model can be impressive in a notebook and still be unsuitable for production traffic. Reliability depends on availability, latency, throughput, quotas, routing, authentication, cost controls, observability, rollback, and behavior under overload. The current Databricks Generative AI Engineer Associate exam and Generative AI Engineer Associate certification connect model selection with Model Serving, Foundation Model APIs, inference logging, monitoring, governance, and cost control for exactly this reason. Home/Databricks/Databricks Generative AI Engineer Associate: Serving Models ReliablyDatabricksPublished October 3, 2026On this pageStart with a service objective, not a model nameLatency is…

Read More

Databricks Generative AI Engineer Associate: Guardrails Beyond Filters

  “Add a content filter” is an appealing answer to generative-AI risk because it is concrete and easy to demonstrate. Enterprise guardrails are broader. A production system must control who can access models, what data can enter prompts, which tools an agent may use, how secrets and personal data are handled, what actions require approval, and what evidence is retained for review. The current Databricks Generative AI Engineer Associate exam and Generative AI Engineer Associate certification make guardrails, malicious-input protection, masking, legal risk, access controls, inference logging, and governance explicit…

Read More

Databricks Generative AI Engineer Associate: Grounding With Delta Tables

  A grounded answer is the visible end of a much longer data path. Source systems must be ingested, cleaned, parsed, chunked, stored, indexed, retrieved, ranked, and supplied to a model with enough provenance to support the response. The current Databricks Generative AI Engineer Associate exam and Generative AI Engineer Associate certification explicitly connect chunked text in Delta Lake tables and Unity Catalog with Vector Search, retrieval evaluation, RAG assembly, governance, and monitoring. Home/Databricks/Databricks Generative AI Engineer Associate: Grounding With Delta TablesDatabricksPublished October 3, 2026On this pageRaw source and searchable…

Read More