Microsoft AI-200 Practice Exam Questions & Answers

After creating the basic Service Bus instance with name, pricing tier, subscription, resource group, and location through the Azure Portal or initial setup, the next step to complete configuration is to create a namespace using 'az servicebus namespace create' (or the equivalent PowerShell command 'New-AzServiceBusNamespace'). The Service Bus instance requires a namespace, which is the container for all messaging entities like queues and topics. The 'az servicebus namespace create' command allows you to programmatically create the namespace with the necessary parameters (name, resource group, location, pricing tier/SKU), completing the configuration needed for the smart refrigerators to send temperature messages to the Service Bus.

Use the Azure App Configuration provider's caching and dynamic refresh mechanism with a configured refresh interval. The application loads configuration into a local cache and periodically checks App Configuration for changes. When a registered key changes, the provider refreshes the cached configuration without requiring an application restart. Microsoft documents SetRefreshInterval and equivalent provider settings as the mechanism for controlling the minimum time between configuration-refresh checks.

This approach satisfies both requirements. The configuration is dynamic because updated values can be detected and reloaded at runtime, while request latency remains low because normal application requests read configuration from the local cached copy instead of making a remote App Configuration request every time. For request-driven refresh, Microsoft notes that refresh occurs asynchronously and does not block the incoming request. Before the configured refresh interval expires, additional refresh calls effectively perform no remote operation.

Microsoft also recommends caching App Configuration values instead of loading them whenever they are used, both to reduce latency and to avoid excessive service requests, throttling, and unnecessary charges.

Environment variables remain static unless the application is restarted or redeployed. Retrieving configuration on every request increases latency and service load. Key Vault is primarily intended for secrets, not general dynamic application configuration.

Study Guide references: Azure App Configuration; dynamic configuration refresh; provider caching; refresh intervals; request-driven refresh; configuration resiliency.

Detailed The API should use a system-assigned managed identity so no application credential is stored or rotated by the development team. That identity should receive only the permission needed to read secret values: Key Vault Secrets User at the vault scope is materially narrower than Key Vault Administrator at subscription scope. Storing a secret value in App Configuration would violate the requirement to protect secrets and increases exposure. The corrected pair therefore implements both credential-free authentication and least-privilege authorization with a limited blast radius.

Study Guide Alignment: Security and operations: Key Vault, App Configuration, managed identity, OpenTelemetry, Azure Monitor, and KQL-based troubleshooting.

Official Microsoft Learn Reference: AI-200 Study Guide | Azure Key Vault RBAC guide | Managed identities for Azure resources

Detailed GitHub Actions is the correct orchestration mechanism among the options because the case requires an automated, version-controlled pipeline and Bicep-based declarative deployment. Microsoft documents GitHub Actions as a supported way to deploy Bicep and automate Azure resource deployment. Local Git, Azure Functions Core Tools, and Azure CLI can participate in development or scripted deployment, but they do not by themselves satisfy the stated requirement for a repository-driven, repeatable CI/CD pipeline.

Study Guide Alignment: Security and operations: Key Vault, App Configuration, managed identity, OpenTelemetry, Azure Monitor, and KQL-based troubleshooting.

Official Microsoft Learn Reference: AI-200 Study Guide | Deploy Bicep with GitHub Actions | Automate Function app resource deployment

A retrieval-augmented generation (RAG) architecture is the correct mechanism when generated answers must be traceable to specific source documents. RAG first retrieves relevant document chunks from a search index or other knowledge source, supplies those chunks to the language model as grounding context, and then generates an answer based on that retrieved information. Microsoft specifically documents that RAG enables responses containing citations back to source content.

For reliable citation generation, each retrieved chunk should carry identifying metadata such as a source identifier, document title, section, page, or URL. Microsoft's Azure RAG guidance recommends labeling retrieved chunks and including source metadata with them, then explicitly instructing the model to cite the corresponding sources in its response. This allows users to verify individual claims against the underlying documents.

Modern Azure AI Search agentic retrieval can also return structured references and grounding metadata, specifically designed for citation linking.

Increasing top_p only alters token sampling. Content filtering addresses safety, not provenance. Using a base model without retrieval provides no authoritative document linkage.

Study Guide references: RAG architecture; grounding data; retrieval metadata; Azure AI Search references; prompt engineering for citations.

Detailed A semantic-search schema should use the pgvector vector type for embeddings so PostgreSQL can apply vector distance operators and vector indexes. The creation timestamp should use an actual timestamp data type so comparisons, range predicates, ordering, and indexes use date semantics rather than string ordering. Storing vectors or dates as free-form character data would sacrifice type validation and make similarity or date filtering less efficient and less reliable.

Study Guide Alignment: AI data-management workloads: Cosmos DB, PostgreSQL, caching, vector storage, vector retrieval, consistency, and connection optimization.

Official Microsoft Learn Reference: AI-200 Study Guide | Vector similarity search with Azure PostgreSQL

To ensure the application can view writes across all regions within a predictable time window, you can use two consistency levels:

1. Bounded staleness consistency: Guarantees that reads lag behind writes by a bounded amount (either by time interval or number of operations). You specify the maximum staleness window (e.g., 5 seconds or 100 operations), ensuring all regions converge within that predictable window.

2. Strong consistency: Provides the strictest consistency guarantee where all replicas across all regions are synchronized before acknowledging writes. Reads always see the most recent write, with a predictable (instantaneous) view across regions.

Both provide predictable time windows for viewing writes across regions. Eventual consistency would not meet the requirement as it provides no predictable bounds. Session and prefix consistency are weaker options that don't guarantee global consistency within a predictable window.