AI-103 Practice Test 25 — 15 Questions

Question 1

You are creating a Language resource in the Azure portal. Which blade should you navigate to if you need to retrieve your endpoint URL and subscription keys for your application configuration?

Accepted Answer

Keys and Endpoint. The 'Keys and Endpoint' blade in an Azure AI Language resource provides the endpoint URL and the subscription keys (Key1 and Key2) required for authenticating client applications. These credentials are essential for configuring your application to call the Language service APIs. This blade is specifically designed to surface the connection information needed for development and integration.

Answer

Diagnostic settings

Answer

Pricing tier

Answer

Access control (IAM)

Question 2

You are designing an agentic workflow where an agent needs to maintain conversational context and remember user preferences across multiple disparate sessions over several weeks. Which architectural component should you implement?

Accepted Answer

A persistent semantic memory store integrated with the agent's context pipeline.. Maintaining conversational context and user preferences across disparate sessions over weeks requires a persistent memory layer that survives beyond a single session or context window. A persistent semantic memory store integrated with the agent's context pipeline allows the agent to retrieve relevant past interactions and preferences via embeddings, enabling long-term personalization. This is the standard architectural pattern for long-horizon agent memory.

Answer

Increasing the model context window to 1,000,000 tokens for every request.

Answer

Using a stateless function with zero memory persistence.

Answer

Storing the entire conversation history in a local client-side cookie.

Question 3

You are developing a customer support agent using Microsoft Foundry. The agent needs to call a custom weather API tool when a user asks about local conditions. How should you define this capability in the agent configuration?

Accepted Answer

Register a custom function tool by providing an OpenAPI schema definition that describes the weather API endpoints, parameters, and expected responses.. Custom function tools in Microsoft Foundry agents are declared using an OpenAPI schema that describes the endpoint, HTTP methods, parameters, and response shape, allowing the model to invoke the weather API through tool calling. The schema acts as the contract the orchestrator uses to generate valid function calls and parse results back into the conversation. This is the standard, supported mechanism for exposing external REST APIs to an agent.

Answer

Upload the compiled C# library containing the API client code directly into the agent code interpreter workspace.

Answer

Add the weather API endpoint URL as a grounding data source under the vector store settings.

Answer

Configure a managed data connection pointing to the weather API URL within Azure AI Search.

Question 4

Your development team needs to test a new Azure AI Language service feature without incurring ongoing charges when the service is idle. Which billing model is appropriate for initial prototyping?

Accepted Answer

Pay-as-you-go (Consumption-based metering). Pay-as-you-go (consumption-based metering) charges only for the transactions and features actually used, with no upfront commitment or idle cost, making it ideal for prototyping a new Azure AI Language feature. It lets the team experiment freely and stop incurring charges when the service is idle. This is the standard billing model for initial development and testing.

Answer

Dedicated hardware hosting

Answer

Reserved Instance 3-year term

Answer

Commitment tier (Pre-purchased capacity)

Question 5

You need to extract text from a multi-page PDF document using Azure AI Vision Read API. How are pages represented in the JSON response structure?

Accepted Answer

They are organized under a 'readResult.pages' or 'pages' array in the analyze result.. The Read API (and the newer Image Analysis/Read model) returns an analyze result that includes a pages array (or readResult.pages in older SDK shapes), where each page contains lines, words, and their bounding polygons plus angle and dimensions. This page-level structure lets you map extracted text back to specific pages of a multi-page PDF.

Answer

All text from all pages is merged into a single unstructured string without page separation.

Answer

Pages are returned as separate JPEG files in a ZIP archive.

Answer

Each page requires a separate API transaction starting with a new POST request.

Question 6

You are processing customer feedback emails that contain both English and Spanish paragraphs within the same message. You need to perform sentiment analysis on each paragraph separately. What should you do?

Accepted Answer

Split the email into individual paragraphs and submit them as separate documents in the request payload.. Azure AI Language sentiment analysis processes each document independently and assumes a single language per document. When an email contains mixed languages, submitting the entire email as one document with auto-detect will produce inaccurate results because the service detects one dominant language and applies that language's model to all text. Splitting the email into individual paragraphs and submitting them as separate documents in the request payload allows the service to detect and analyze the language of each paragraph independently, yielding accurate per-paragraph sentiment.

Answer

Use custom text classification instead of sentiment analysis.

Answer

Submit the entire email as a single document with the language set to auto-detect.

Answer

Translate the entire email to French before calling sentiment analysis.

Question 7

You have trained a Custom Vision classification model. You need to export the model to run locally on an edge device using ONNX format. Which project domain must you select when creating the project to support export?

Accepted Answer

General (compact). To export a Custom Vision classification model to ONNX for edge deployment, the project must be created with a compact domain — specifically 'General (compact)' — because only compact domains support model export. The compact domain produces a smaller, optimized model suitable for local/edge inference.

Answer

Retail

Answer

Food (compact) for edge deployment

Answer

General

Question 8

You are deploying an Azure OpenAI resource and want to authenticate client applications using Microsoft Entra ID instead of static API keys. Which role must be assigned to the application's managed identity to permit it to invoke model deployments?

Accepted Answer

Cognitive Services OpenAI User. The Cognitive Services OpenAI User role is the RBAC role specifically scoped to grant data-plane access for invoking Azure OpenAI model deployments (chat completions, embeddings, etc.) without granting management permissions. Assigning it to the application's managed identity lets the app call the inference endpoints using Entra ID tokens instead of API keys. This follows the least-privilege principle for OpenAI resource consumption.

Answer

Storage Blob Data Contributor

Answer

Key Vault Secrets Officer

Answer

Contributor

Question 9

You want to detect whether corporate logos appear in user-submitted images using Azure AI Vision. Which visual feature parameter should you request?

Accepted Answer

features=brands. Azure AI Vision's Analyze Image API supports a 'brands' visual feature that detects corporate logos and brands within an image, returning brand names and confidence scores. Requesting features=brands enables this specific detection capability, which is distinct from general object or tag detection.

Answer

features=domain-specific

Answer

features=objects

Answer

features=tags

Question 10

Your development team needs to deploy an Azure AI Search service and connect it to an Azure SQL Database containing source documents. Security requirements state that credentials must not be stored in application code. Which authentication method should you use between Azure AI Search and Azure SQL Database?

Accepted Answer

Managed Identity. Managed Identity allows Azure AI Search to authenticate to Azure SQL Database without storing credentials in code. The indexer can use the search service's managed identity to access the SQL database, provided the identity has been granted appropriate permissions in SQL.

Answer

Shared Access Signature (SAS) token

Answer

Hardcoded SQL administrator password in indexer configuration

Answer

Anonymous access connection string

Question 11

When designing an Azure AI Foundry project architecture, which TWO resources are typically linked to the Azure AI Hub to enable full model deployment and search capabilities? (Choose TWO)

Accepted Answer

Azure AI Search service. Option A (Azure AI Search service) is correct because an Azure AI Search resource is a standard linked dependency of an Azure AI Hub/project, providing the vector and keyword indexing backend needed for search, retrieval, and RAG-style grounding scenarios. Option C (Azure OpenAI service) is correct because linking an Azure OpenAI resource to the hub supplies the deployed GPT and embedding models that the project uses for model deployment and inference. Option B (Azure SQL Database) is not a typical hub-linked resource; relational data can be connected separately but it is not required for model deployment or search. Option D (Azure Stream Analytics) is a real-time stream processing service unrelated to Foundry hub model/search enablement. Option E (Power BI embedded) is a visualization/analytics service and plays no role in linking model deployment or search capabilities to an AI Hub.

Answer

Azure SQL Database relational server

Answer

Azure Stream Analytics job cluster

Answer

Power BI embedded analytics workspace

Question 12

When configuring role-based access control (RBAC) for an Azure AI Services account, which TWO built-in roles are appropriate for assigning to users who only need to invoke AI models without managing the underlying resource infrastructure? Each correct answer presents part of the solution.

Accepted Answer

Cognitive Services OpenAI User. Option B, Cognitive Services OpenAI User, is correct because it grants the ability to call Azure OpenAI model inference endpoints (such as chat completions and embeddings) without granting permissions to manage the account, keys, or deployments. Option D, Cognitive Services User, is correct because it allows invoking the broader set of Azure AI Services (Cognitive Services) endpoints for inference while excluding resource-management actions. Both roles satisfy the least-privilege requirement of invoking AI models without managing underlying infrastructure. Option A, Owner, is incorrect because it grants full control including managing resources and assigning roles, far exceeding inference-only needs. Option C, Contributor, is incorrect because it allows creating and managing resources (though not role assignment), which is more than invoking models requires. Option E, Storage Blob Data Reader, is incorrect because it only permits reading blob data and has no relevance to invoking AI model endpoints.

Answer

Owner

Answer

Contributor

Answer

Storage Blob Data Reader

Question 13

You are building a generative AI application that summarizes long legal documents. Users complain that summaries omit important clauses located in the middle of the document due to the model's attention limitations over extremely long texts. What phenomenon does this represent, and how can you mitigate it?

Accepted Answer

Lost in the middle phenomenon; mitigate using map-reduce or recursive summarization patterns. The 'lost in the middle' phenomenon describes how transformer models attend more reliably to information at the beginning and end of long contexts, degrading recall for content in the middle. Map-reduce or recursive summarization mitigates this by chunking the document, summarizing each chunk independently, then combining the summaries — ensuring middle content is processed with full attention.

Answer

Token overflow error; mitigate by increasing Azure AI Search semantic ranker depth

Answer

Embedding drift; mitigate by retraining the text-embedding-ada-002 model

Answer

Prompt injection; mitigate by enabling Azure AI Content Safety prompt shields

Question 14

You are troubleshooting a RAG application in Azure AI Foundry where retrieved search results are irrelevant to user queries. Which THREE actions should you take to diagnose and improve retrieval quality? (Choose THREE)

Accepted Answer

Evaluate whether document chunk sizes and overlaps align with query granularity. Option A is correct because chunk size and overlap directly control retrieval granularity: if chunks are too large they dilute the embedding with irrelevant content, and if too small they lose context, so aligning them with typical query granularity improves relevance. Option B is correct because inspecting embedding vector distances and similarity scores (e.g., cosine similarity in Azure AI Search) reveals whether the query embedding is actually close to the retrieved documents or whether the embedding model, index, or query vectorization is mismatched. Option E is correct because enabling semantic ranking in Azure AI Search applies a deep language model re-ranker on top of the initial BM25/vector results, promoting semantically relevant documents and typically raising retrieval precision. Option C is not appropriate because temperature controls generative randomness, not retrieval quality, and 1.5 is outside the supported range for most Azure OpenAI models. Option D is not relevant because Key Vault access policies govern secret management, not the relevance of search results.

Answer

Increase the Azure OpenAI model temperature parameter to 1.5

Answer

Configure Azure Key Vault access policies for the search service

Question 15

You need to export logs from your Azure AI service to an external SIEM (Security Information and Event Management) system. What is the best way to achieve this?

Accepted Answer

Configure a diagnostic setting to stream logs to an Event Hub.. Configuring a diagnostic setting to stream logs to an Event Hub is the standard, scalable way to export Azure AI service logs to an external SIEM. Event Hubs acts as a high-throughput ingestion buffer that the SIEM (e.g., Splunk, Sentinel) consumes via its connector. This is the recommended integration pattern for near-real-time security monitoring.

Answer

Copy the files manually from Blob Storage.

Answer

Use an Azure Logic App to poll the REST API.

Answer

Enable public access on the log file store.