AI-102 Practice Test 17 — 15 Questions

Question 1

You deploy a chat application using Azure OpenAI Service. Users report that the model sometimes generates inappropriate content. You need to implement a safety system that can be customized for your organization's policies. What should you use?

Accepted Answer

Use Azure AI Content Safety with custom categories and severity thresholds. Option D is correct because Azure AI Content Safety provides customizable content filters that can be tailored to organizational policies. Option A is wrong because Azure AD provides authentication, not content filtering. Option B is wrong because while it has some safety, it is not as customizable as Content Safety. Option C is wrong because responsible AI templates are guidelines, not a deployable filter.

Answer

Use the content filter system in Azure OpenAI Studio

Answer

Apply responsible AI templates from Azure AI Studio

Answer

Configure Microsoft Entra ID Conditional Access policies

Question 2

Which TWO statements about Azure OpenAI Service content filters are true?

Accepted Answer

They can be configured with severity levels (low, medium, high). Option A is correct because Azure OpenAI Service content filters can be configured with severity levels (low, medium, high) to control the strictness of filtering for each content category. This allows administrators to fine-tune the filter sensitivity based on their application's risk tolerance and compliance requirements.

Answer

They only filter the output of the model

Answer

They cannot be customized for specific use cases

Answer

They are bypassed when using PTU deployments

Question 3

You are using Azure OpenAI Service to generate text. You need to reduce the likelihood of the model generating repetitive sequences. Which TWO parameters should you adjust?

Accepted Answer

frequency_penalty. Frequency penalty reduces the likelihood of the model repeating the same tokens or phrases by subtracting a fixed penalty from the log-probability of tokens that have already appeared in the generated text. This directly discourages repetitive sequences, making it one of the two correct parameters to adjust.

Answer

max_tokens

Answer

top_p

Answer

temperature

Question 4

You run the above PowerShell command to check the responsible AI policy applied to an Azure OpenAI Service deployment. The output shows 'MyPolicy'. You need to verify that the policy blocks hate speech. What should you do?

Accepted Answer

Navigate to Azure AI Content Safety and view the policy 'MyPolicy'.. Option B is correct because Azure AI Content Safety is the dedicated service for managing and viewing the details of content filtering policies, including custom policies like 'MyPolicy'. The PowerShell command only confirms the policy name is applied to the deployment; to verify that the policy blocks hate speech, you must inspect the policy's configuration (e.g., severity thresholds for hate categories) within the Azure AI Content Safety portal. The Azure Portal deployment properties only show the policy name, not its rules.

Answer

Use the Azure Portal to review the deployment's properties.

Answer

Run Get-AzCognitiveServicesAccountDeployment with -ExpandProperties.

Answer

Use Azure Monitor to check the deployment's logs.

Question 5

Your company wants to build a custom generative AI model that generates architectural designs. The model should be trained on the company's proprietary dataset of floor plans and designs. Which Azure service should you use?

Accepted Answer

Azure Machine Learning. Option A is correct because Azure Machine Learning provides a platform for training custom models, including generative models. Option B is wrong because Azure OpenAI Service offers pre-trained models, not custom training. Option C is wrong because Azure AI Document Intelligence is for extracting information from documents. Option D is wrong because Azure AI Vision is for image analysis, not generative design.

Answer

Azure OpenAI Service

Answer

Azure AI Vision

Answer

Azure AI Document Intelligence

Question 6

You are developing a custom chatbot using Azure AI Bot Service and Language Understanding (CLU). The chatbot needs to escalate to a human agent when the user's sentiment is negative. Which component should you use to detect sentiment?

Accepted Answer

Azure AI Language sentiment analysis. Option B is correct because the Azure AI Language sentiment analysis is a prebuilt feature that can be integrated into the bot. Option A is wrong because Orchestration workflow routes intents, not sentiment. Option C is wrong because QnA Maker is for FAQs. Option D is wrong because Azure Cognitive Search is for indexing.

Answer

Azure Cognitive Search

Answer

Orchestration workflow

Answer

QnA Maker

Question 7

Your organization is building a chatbot using Azure OpenAI Service. The chatbot must provide citations from a set of internal documents stored in Azure Blob Storage. You need to configure the solution to minimize token usage while ensuring citations are accurate. Which approach should you use?

Accepted Answer

Use Azure OpenAI on your data with Azure Cognitive Search for hybrid retrieval. Option B is correct because Azure OpenAI on your data with Azure Cognitive Search uses a hybrid retrieval approach (vector + keyword), which is more token-efficient than embedding all content into the prompt. Option A is wrong because embedding entire documents wastes tokens. Option C is wrong because it lacks retrieval. Option D is wrong because fine-tuning does not support dynamic document citation.

Answer

Embed all document content into the system prompt

Answer

Fine-tune a model on the documents so it can recall them from memory

Answer

Use a large context window model (e.g., 32K) and include all documents in the prompt

Question 8

You are building a generative AI solution using Azure Machine Learning prompt flow. The solution must allow business analysts without coding experience to modify prompts and evaluate different model versions. What should you do?

Accepted Answer

Use Azure Machine Learning prompt flow with the visual designer and variant management. Option C is correct because prompt flow in Azure ML provides a visual designer and evaluation tools suitable for non-coders. Option A is wrong because direct API calls require coding. Option B is wrong because it's a different service. Option D is wrong because it's not a visual tool.

Answer

Provide the analysts with a Jupyter notebook using the OpenAI Python SDK

Answer

Deploy a chatbot in Microsoft Copilot Studio and let analysts configure it

Answer

Implement a custom web UI using Azure Static Web Apps and Azure Functions

Question 9

Which THREE components are required to build a custom copilot using Microsoft Copilot Studio that can answer questions from a SharePoint document library?

Accepted Answer

A Microsoft Copilot Studio copilot. Options A, C, and E are correct. A copilot is needed as the interface. SharePoint must be configured as a data source. A knowledge source (cognitive search) enables indexing and retrieval. Option B is wrong because Azure OpenAI is not required; Copilot Studio uses its own AI. Option D is wrong because Power Automate is not required for basic Q&A.

Answer

A Power Automate flow to trigger the copilot

Answer

An Azure OpenAI Service deployment

Question 10

You are using Azure OpenAI Service to generate code snippets for a development team. You notice that the generated code sometimes contains security vulnerabilities. You need to minimize the risk of generating insecure code while maintaining productivity. What should you do?

Accepted Answer

Use system messages to instruct the model to prioritize security. Option D is correct because system messages set the behavior of the model, instructing it to prioritize security. Option A is wrong because disabling content filtering would not address security vulnerabilities. Option B is wrong because fine-tuning requires labeled data and may not be practical. Option C is wrong because temperature affects creativity, not security.

Answer

Fine-tune the model on a dataset of secure code

Answer

Set the temperature parameter to 0

Answer

Disable content filtering to allow more flexibility

Question 11

You are developing a generative AI solution that uses Azure OpenAI Service. You need to control the creativity of the generated responses. Which parameter should you adjust?

Accepted Answer

temperature. Option B is correct because the temperature parameter controls the randomness of the output. Option A is wrong because max_tokens controls output length. Option C is wrong because top_p is another randomness parameter, but temperature is more direct. Option D is wrong because frequency_penalty reduces repetition.

Answer

top_p

Answer

max_tokens

Answer

frequency_penalty

Question 12

Refer to the exhibit. You have deployed a GPT-3.5 Turbo model in Azure OpenAI Service with the shown configuration. Users report that the model generates responses that are too repetitive. You need to reduce repetition. Which parameter should you modify?

Accepted Answer

Increase presencePenalty to 0.5. Option D is correct because presence_penalty reduces the likelihood of repeating tokens that have already appeared. Option A is wrong because temperature controls creativity. Option B is wrong because topP controls nucleus sampling. Option C is wrong because frequency_penalty is set to 0 and could be increased, but presence_penalty is more effective for repetition of topics. However, both can reduce repetition; but presence_penalty is often preferred for reducing repetition of content. Based on typical usage, presence_penalty is the better choice.

Answer

Increase frequencyPenalty to 0.5

Answer

Increase temperature to 1.0

Answer

Decrease topP to 0.5

Question 13

You are deploying a generative AI application that uses Azure OpenAI Service. You need to ensure that the application can handle sudden spikes in traffic without exceeding your quota. Which scaling strategy should you implement?

Accepted Answer

Configure a provisioned throughput deployment with auto-scaling.. Option D is correct because a provisioned throughput deployment with auto-scaling allows you to handle spikes while staying within quota. Option A is wrong as Pay-as-you-go has limited throughput. Option B is wrong as manual scaling is not automatic. Option C is wrong as multiple instances don't help if quota is fixed.

Answer

Use a Pay-as-you-go deployment and rely on Azure's automatic scaling.

Answer

Create a deployment with a high base TPM and manually adjust during peak times.

Answer

Deploy multiple instances of the model in different regions.

Question 14

You need to provide a generative AI solution that can answer questions based on a large set of PDF documents stored in Azure Blob Storage. The solution must support natural language queries and return citations from the documents. Which Azure service combination should you use?

Accepted Answer

Azure Cognitive Search and Azure OpenAI Service with 'on your data'. Option C is correct because Azure Cognitive Search indexes the PDFs and Azure OpenAI on your data uses that index to answer with citations. Option A is wrong because Form Recognizer is for extraction, not Q&A. Option B is wrong because Azure ML is for training, not search. Option D is wrong because Azure AI Bot Service alone doesn't index documents.

Answer

Azure Machine Learning and Azure Kubernetes Service

Answer

Azure AI Bot Service and Azure Functions

Answer

Azure AI Document Intelligence and Azure AI Translator

Question 15

You are deploying a generative AI solution using Azure OpenAI Service. The solution must comply with data residency requirements that mandate all data processing and storage remain within a specific geographic region. You need to configure the service to meet these requirements. What should you do?

Accepted Answer

Deploy the Azure OpenAI Service resource in the required region. Option B is correct because deploying the Azure OpenAI Service resource in the required region ensures data processing and storage stay within that region. Option A is wrong because data residency is determined by the region of the resource, not the model. Option C is wrong because data residency is not related to the content filtering configuration. Option D is wrong because the resource endpoint is region-specific but does not affect data residency.

Answer

Use a custom endpoint that routes traffic to the required region

Answer

Select a model that is only available in the required region

Answer

Configure content filtering to block data leaving the region