AI-103 Practice Test 20 — 15 Questions

Question 1

Your enterprise application uses Azure AI Vision. Security policies require that all API keys are rotated every 30 days without causing application downtime. How should you manage the key rotation?

Accepted Answer

Switch client applications to Key 2, regenerate Key 1 in the Azure portal, switch clients to Key 1, and then regenerate Key 2.. Azure AI services (including Azure AI Vision) issue two API keys per resource specifically to enable zero-downtime rotation. The correct pattern is to move all clients to Key 2 while Key 1 is still valid, regenerate Key 1, cut clients back over to the new Key 1, then regenerate Key 2 — so at no point is a client using a key that has just been invalidated. This dual-key design is the documented Microsoft approach for credential rotation without service interruption.

Answer

Restart the Azure App Service hosting the client application.

Answer

Delete the Azure AI service resource and create a new one every 30 days.

Answer

Disable authentication on the resource during the rotation window.

Question 2

You are implementing a RAG solution where documents contain complex hierarchical headings. To ensure search chunks retain sufficient context about which section they belong to, what chunking strategy should you adopt?

Accepted Answer

Hierarchical (parent-child) chunking retaining section headers. Hierarchical (parent-child) chunking retains section headers and structural context, so each child chunk knows which parent section it belongs to. This preserves the document's hierarchy, ensuring that retrieved chunks carry enough context for the LLM to answer accurately. It is the recommended strategy for complex hierarchical documents in RAG.

Answer

Fixed-size character chunking with zero overlap

Answer

Random token sampling without structural awareness

Answer

Single-chunk whole document ingestion

Question 3

You are designing an agentic workflow where an orchestrator agent delegates sub-tasks to specialized worker agents (e.g., a research agent and a coding agent). Which framework or service native to Azure AI supports multi-agent orchestration patterns?

Accepted Answer

Semantic Kernel or Microsoft AutoGen. Semantic Kernel and Microsoft AutoGen are Microsoft's frameworks designed for building AI agents and multi-agent orchestration, including patterns where an orchestrator delegates to specialized worker agents. They provide abstractions for agent roles, conversation routing, and tool use that map directly to the described workflow.

Answer

Azure Data Factory pipeline authoring

Answer

Azure Stream Analytics query editor

Answer

Azure Logic Apps standard workflow designer

Question 4

You are designing an AI application and want to test different foundation models (e.g., GPT-4o vs. Llama 3) side-by-side using the same prompt and test dataset. Which feature in Azure AI Foundry should you use?

Accepted Answer

Side-by-side evaluation in Azure AI Foundry playground. Side-by-side evaluation in the Azure AI Foundry playground lets you run the same prompt and test dataset against multiple foundation models and compare outputs, metrics, and quality. This is the native feature for model comparison during design and selection.

Answer

Azure Monitor workbook performance graphs

Answer

Azure Cosmos DB cross-region replication

Answer

Azure Front Door traffic routing

Question 5

You are orchestrating a multi-agent system in Microsoft Foundry where Agent A generates code and Agent B reviews it. Agent B frequently gets stuck in a loop trying to optimize minor syntax formatting. How should you design the agentic workflow to prevent this infinite refinement loop?

Accepted Answer

Configure a maximum turn counter and state transition condition in the orchestrator workflow to terminate the loop after a set threshold.. Configuring a maximum turn counter and a state transition condition in the orchestrator terminates the loop after a defined threshold, preventing infinite refinement. This is the standard pattern for bounded agentic workflows, ensuring the system exits gracefully when convergence is not reached. It directly addresses the runaway loop without degrading agent capability.

Answer

Disable function calling for Agent B so it can only output text responses.

Answer

Increase the model's presence penalty so Agent B is forced to generate novel review comments.

Answer

Use a smaller model for Agent B to reduce the quality of its reviews.

Question 6

You are auditing a generative AI application for responsible AI compliance. Which THREE practices should you implement to mitigate risks? (Choose 3)

Accepted Answer

Configure system messages to explicitly define boundaries. Option C is correct because configuring system messages to explicitly define boundaries constrains the model's behavior, scope, and tone, helping prevent prompt injection, off-topic responses, and harmful or non-compliant outputs. Option D is correct because enabling Azure AI Content Safety filtering applies classifiers for hate, violence, sexual, and self-harm content (plus prompt shields and groundedness detection), directly reducing the risk of harmful or unsafe generated content. Option E is correct because implementing manual review cycles for high-impact outputs adds human oversight, which is a core responsible AI requirement for consequential decisions where automated errors could cause real harm. Option A is not appropriate because storing user PII in plain text logs violates privacy and data-protection principles and increases breach exposure rather than mitigating risk. Option B is not appropriate because raising the temperature to 1.0 increases randomness and creativity, which raises the likelihood of hallucinated, inconsistent, or unsafe outputs instead of reducing risk.

Answer

Store all user PII in plain text logs

Answer

Increase the temperature of the model to 1.0

Question 7

When designing prompt engineering strategies for complex reasoning tasks in Azure OpenAI, which TWO techniques help reduce hallucinations and improve output reliability? (Choose TWO)

Accepted Answer

Few-shot prompting providing high-quality input-output demonstration examples. Few-shot prompting (A) is correct because supplying several high-quality input-output demonstration examples in the prompt conditions the model on the desired format, tone, and reasoning pattern, which measurably reduces hallucination and improves consistency on complex reasoning tasks. Chain-of-thought prompting (B) is correct because explicitly instructing the model to reason step by step decomposes a hard problem into intermediate steps, improving accuracy on multi-step reasoning and making errors easier to detect. The unmarked options do not belong: removing system prompts (C) strips grounding and behavioral constraints, which increases hallucination risk; setting top_p to 0.0 with temperature 2.0 (D) is a contradictory, degenerate sampling configuration that does not improve reliability; and hex-encoding prompt variables (E) only obscures text and adds no reasoning benefit.

Answer

Disabling system prompts entirely to maximize model freedom

Answer

Setting the top_p parameter to 0.0 while setting temperature to 2.0

Answer

Encoding all prompt variables in hexadecimal format

Question 8

You are evaluating generative AI model outputs in Azure AI Foundry. Which TWO automated evaluation metrics assess the quality and correctness of RAG responses against source data? (Choose TWO)

Accepted Answer

Groundedness (measuring adherence to source context). Option A, Groundedness, is correct because it is a built-in Azure AI Foundry evaluation metric that measures how well a generative AI response is supported by and adheres to the retrieved source context, which is exactly what is needed to verify RAG responses against source data and detect ungrounded or hallucinated content. Option E, Relevance, is correct because it is another built-in Foundry evaluation metric that assesses how well the model's response addresses the user's query, complementing groundedness by judging answer quality and correctness relative to the question. The remaining options are infrastructure and platform telemetry rather than AI quality metrics: B (virtual network gateway throughput) measures network bandwidth, C (storage account transaction count per hour) measures storage operations, and D (CPU utilization percentage of the Azure App Service plan) measures compute load, none of which evaluate the semantic quality or correctness of RAG responses.

Answer

Virtual network gateway throughput

Answer

Storage account transaction count per hour

Answer

CPU utilization percentage of the Azure App Service plan

Question 9

You are designing a secure RAG retrieval pipeline in Azure AI Search. Which THREE indexing or search configurations are essential when handling confidential documents? (Choose THREE)

Accepted Answer

Encryption at rest using Customer-Managed Keys (CMK). Option A is correct because Azure AI Search supports encryption at rest with Customer-Managed Keys (CMK) via Azure Key Vault, which lets you control the key lifecycle and revoke access to confidential index data, a requirement for sensitive workloads. Option B is correct because Private Endpoint connections (via Azure Private Link) give the search service a private IP inside your VNet, so indexing and query traffic never traverses the public internet, isolating confidential retrieval traffic. Option D is correct because document-level security trimming with OData filters (e.g., filtering on a groups or ACL field using search.in or eq) ensures each user only retrieves documents they are authorized to see, preventing leakage of confidential content in RAG responses. Option C is wrong because disabling authentication would expose the index to anonymous guest queries, directly violating confidentiality. Option E is wrong because storing unencrypted indexes in public blob containers removes both encryption and network isolation, which is unacceptable for confidential documents.

Answer

Disabling all authentication to allow open guest queries

Answer

Storing unencrypted search indexes in public Azure blob containers

Question 10

You are evaluating a generative AI application in Azure AI Foundry using automated metrics. You need to measure how well the generated answers are supported by the retrieved source documents. Which evaluation metric should you use?

Accepted Answer

Groundedness. Groundedness measures how well a model's generated response is supported by the retrieved source documents, which is exactly the requirement in a RAG-style generative AI application. Azure AI Foundry's evaluation SDK provides a groundedness metric that uses an LLM judge to check whether claims in the answer are entailed by the provided context.

Answer

Word Error Rate (WER)

Answer

BLEU score

Answer

Perplexity

Question 11

You are building an agent in Azure AI Foundry that needs to retrieve information from a company SharePoint site. Which component should you implement to ground the agent?

Accepted Answer

Azure AI Search with a SharePoint connector. Azure AI Search with a SharePoint connector (via the SharePoint indexer or the newer SharePoint ingestion pipeline) is the supported, first-party way to ground an Azure AI Foundry agent on SharePoint content. The connector crawls SharePoint sites, extracts documents, chunks and indexes them, and exposes them through a retriever that the agent can call as a knowledge tool. This gives the agent permission-aware, up-to-date retrieval without custom code.

Answer

Blob Storage integration

Answer

Direct REST API call to SharePoint

Answer

Microsoft Graph Data Connect directly to the model

Question 12

You are building an agentic application that uses function calling. The model frequently hallucinates arguments for complex tool schemas. Which technique should you apply to improve function calling reliability?

Accepted Answer

Enhance the JSON schema with detailed parameter descriptions, enum constraints, and strict schema validation settings.. Detailed parameter descriptions, enum constraints, and strict schema validation give the model explicit guidance on expected argument formats and allowed values, reducing ambiguity that leads to hallucinated arguments. Strict schema validation (e.g., JSON Schema strict mode) rejects malformed outputs and forces the model to conform. This is the most direct and effective technique for improving function-calling reliability.

Answer

Convert all tool arguments into unstructured natural language text.

Answer

Remove all parameter descriptions from the tool schema to reduce prompt token count.

Answer

Set the model frequency penalty to high values.

Question 13

You need to extract text lines, words, bounding polygons, and selection marks (such as radio buttons and checkboxes) from arbitrary documents without training. Which prebuilt model should you invoke?

Accepted Answer

Prebuilt Layout model. The prebuilt Layout model in Azure AI Document Intelligence extracts text lines, words, bounding polygons, and selection marks (checkboxes, radio buttons) from documents without any training. It is designed for general document structure extraction and is the correct choice when you need layout-level elements and selection marks from arbitrary documents. It requires no custom training and works out of the box.

Answer

Prebuilt Business Card model

Answer

Prebuilt ID Document model

Answer

Custom Neural model

Question 14

You are automating document processing. You want to trigger a workflow only after a Document Intelligence operation finishes. What is the standard way to implement this?

Accepted Answer

Poll the 'operation-location' URL. The Document Intelligence analyze operation is asynchronous: it returns a 202 Accepted response with an 'Operation-Location' header containing a URL. The standard way to detect completion is to poll that URL until the status field returns 'succeeded' or 'failed'. This is the documented pattern for all long-running Document Intelligence operations.

Answer

Use a fixed-delay thread sleep

Answer

Use a WebSocket

Answer

Wait for a push notification

Question 15

Your development team needs to monitor the latency and total call volume of an Azure AI Document Intelligence resource in near real-time. Where can you view these pre-aggregated metrics without writing custom log queries?

Accepted Answer

The Metrics blade of the Azure AI Document Intelligence resource in the Azure portal. The Metrics blade of an Azure AI Document Intelligence resource provides pre-aggregated, near-real-time platform metrics such as latency, call volume, and error rates without requiring any KQL queries. These metrics are emitted automatically by the Azure Monitor platform and are viewable directly in the portal.

Answer

The Cost Management + Billing cost analysis dashboard

Answer

The Log Analytics workspace query editor using KQL

Answer

The Azure Advisor recommendations blade