AI-102 Practice Test 18 — 15 Questions

Question 1

You are using Azure OpenAI Service to generate marketing copy. The marketing team reports that the generated content sometimes contains factual inaccuracies. You need to improve the factual accuracy of the generated content. What should you do?

Accepted Answer

Include relevant context and facts in the prompt. Option B is correct because providing relevant context in the prompt gives the model factual information to base its response on. Option A is wrong because reducing temperature does not improve factual accuracy. Option C is wrong because increasing max_tokens does not improve accuracy. Option D is wrong because disabling content filtering does not address inaccuracies.

Answer

Increase the max_tokens parameter

Answer

Decrease the temperature parameter

Answer

Disable content filtering

Question 2

You are building a generative AI application that uses Azure OpenAI Service. The application must handle sensitive user data and comply with GDPR. You need to ensure that the service does not store or log user prompts and completions. What should you configure?

Accepted Answer

Disable data logging in the Azure OpenAI Service resource. Option C is correct because disabling data logging in the Azure OpenAI Service resource ensures that prompts and completions are not stored. Option A is wrong because the region does not affect logging. Option B is wrong because content filtering does not prevent logging. Option D is wrong because the resource endpoint does not affect logging.

Answer

Deploy the resource in a GDPR-compliant region

Answer

Configure content filtering to block sensitive data

Answer

Use a custom endpoint that anonymizes data

Question 3

Refer to the exhibit.

{
  "content_filters": [
    {
      "type": "hate",
      "action": "block",
      "severity": "high"
    },
    {
      "type": "sexual",
      "action": "block",
      "severity": "medium"
    },
    {
      "type": "self_harm",
      "action": "block",
      "severity": "low"
    }
  ]
}

You deploy an Azure OpenAI model with the above content filter configuration. A user submits a prompt that the system rates as "hate" at severity level "medium". What happens?

Accepted Answer

The prompt is allowed because the severity is below the threshold.. Option C is correct because the filter for hate blocks only at severity 'high', so a 'medium' severity hate message is allowed. Options A and B are wrong because the action is block only for high severity. Option D is wrong because the filter is not skipped entirely.

Answer

The prompt is blocked because hate content is detected.

Answer

The prompt is blocked because the severity is medium.

Answer

The prompt is allowed because the hate filter is not configured for medium.

Question 4

Which THREE factors should you consider when choosing between Azure OpenAI Service and Azure Machine Learning for deploying a generative AI model?

Accepted Answer

Latency requirements: Azure OpenAI may offer lower latency for standard models.. Options A, C, and E are correct. A: Azure OpenAI is fully managed with less operational overhead. C: Azure OpenAI offers pre-trained models, while Azure ML allows custom models. E: Azure OpenAI may have lower latency for similar model sizes. B is wrong because both services support scaling. D is wrong because both services support governance.

Answer

Integration with Microsoft Purview for data governance.

Answer

Ability to scale to thousands of concurrent requests.

Question 5

You are deploying a solution that uses Azure OpenAI Service to generate financial reports. You need to ensure the outputs are accurate and consistent. Which TWO parameters should you adjust? (Choose two.)

Accepted Answer

Set temperature to 0.. A and C are correct. Temperature set to 0 reduces randomness for consistent outputs. Top_p set to 0.1 forces high-probability tokens. B is wrong because presence_penalty encourages topic diversity, not consistency. D is wrong because frequency_penalty reduces repetition, which might be desired but not for consistency. E is wrong because max_tokens controls length, not accuracy or consistency.

Answer

Set presence_penalty to 0.5.

Answer

Set max_tokens to 2000.

Answer

Set frequency_penalty to 0.7.

Question 6

Your company wants to build a custom Copilot for customer support using Microsoft Copilot Studio. The support team needs to query a backend CRM system securely using the Copilot. Which authentication method should you configure for the custom connector to the CRM?

Accepted Answer

Microsoft Entra ID OAuth 2.0. Option C is correct because Microsoft Entra ID OAuth 2.0 is the recommended secure authentication for custom connectors in Copilot Studio, allowing token-based access without exposing credentials. Option A is wrong because API keys are less secure and not recommended for production. Option B is wrong because Basic authentication sends credentials in plain text. Option D is wrong because client certificates are not directly supported by Copilot Studio connectors.

Answer

API key authentication

Answer

Basic authentication

Answer

Client certificate authentication

Question 7

You are designing a generative AI solution that uses Azure OpenAI Service. The solution must not generate responses that include personally identifiable information (PII). Which TWO configurations should you implement? (Choose two.)

Accepted Answer

Use Azure AI Content Safety to filter PII in the output.. A and D are correct. Using system messages to instruct the model to avoid PII is a direct approach. Azure AI Content Safety can detect and filter PII in outputs. B is wrong because fine-tuning on non-PII data does not guarantee avoidance. C is wrong because data retention policies affect storage, not generation. E is wrong because enabling logging does not prevent generation of PII.

Answer

Enable diagnostic logging to audit all generated responses.

Answer

Set data retention policies to delete prompts and completions after 30 days.

Answer

Fine-tune the model on a dataset that excludes PII.

Question 8

You are working for a healthcare organization that uses Azure AI Document Intelligence to process patient intake forms. The forms are scanned and uploaded as multi-page PDFs. The extraction accuracy for the 'diagnosis code' field is poor. You have a labeled dataset of 200 forms. You need to improve the extraction accuracy without writing custom code. The solution must also handle forms with varying layouts. What should you do?

Accepted Answer

Create a custom neural model and train it with the labeled dataset.. Option C is correct because custom neural models are designed for varied layouts and can be trained with labeled data. Option A is wrong because predefined models are for fixed layouts. Option B is wrong because the form processing feature is for key-value pairs, not free-form fields. Option D is wrong because the general document model is less accurate for specific fields.

Answer

Use the 'Form processing' custom extraction model.

Answer

Use the US Tax W-2 predefined model as a base and customize it.

Answer

Use the General Document model to extract all text and then parse.

Question 9

Your organization is deploying a generative AI solution using Azure AI Foundry. The solution must comply with responsible AI principles, including fairness and transparency. Which combination of tools should you use to assess and mitigate bias in the model?

Accepted Answer

Azure AI Content Safety and Azure Machine Learning fairness assessment. Option B is correct because Azure AI Content Safety provides content filtering, and the fairness assessment in Azure Machine Learning evaluates bias. Option A is wrong because Microsoft Purview is for data governance, not bias detection. Option C is wrong because Microsoft Defender XDR is a security tool. Option D is wrong because Azure AI Language detects PII, not bias.

Answer

Azure AI Language PII detection and Azure AI Search

Answer

Microsoft Defender XDR and Azure AI Language

Answer

Microsoft Purview Data Map and Azure AI Document Intelligence

Question 10

Your company uses Microsoft Copilot for Microsoft 365. You need to ensure that Copilot only accesses data from approved SharePoint sites and does not use any other organizational data. What should you configure?

Accepted Answer

Apply sensitivity labels to the approved SharePoint sites.. Option B is correct because sensitivity labels can restrict Copilot's data access. Option A is wrong as conditional access controls authentication, not data access. Option C is wrong as retention policies manage data lifecycle. Option D is wrong as Purview Data Map catalogs data, not restrict access.

Answer

Configure Conditional Access policies in Microsoft Entra ID.

Answer

Use Microsoft Purview Data Map to catalog the approved sites.

Answer

Set up data retention policies in Microsoft Purview.

Question 11

You are using Azure AI Studio to deploy a fine-tuned model for code generation. After deployment, you notice that the model returns nonsensical code snippets. You need to diagnose the issue. What should you check first?

Accepted Answer

Evaluate the model performance on a held-out test dataset.. Option C is correct because evaluation of the fine-tuned model on a test dataset reveals if it learned correctly. Option A is wrong because training data format issues might cause problems but are not the first diagnostic step after deployment. Option B is wrong because the base model works for many tasks; the fine-tuning likely introduced the issue. Option D is wrong because rate limits affect throughput, not quality.

Answer

Verify that the training data is in JSONL format.

Answer

Test the base model without fine-tuning to compare outputs.

Answer

Check the deployment's rate limits and quotas.

Question 12

You are designing a generative AI solution that uses Azure OpenAI Service. The solution must generate code snippets in Python and JavaScript. You need to ensure the model reliably outputs code in the correct language based on user input. Which approach should you use?

Accepted Answer

Use a system message to specify the desired language.. Option C is correct because the system message can specify the language and instruct the model to output code in that language. Option A is wrong as temperature controls creativity. Option B is wrong as fine-tuning is overkill. Option D is wrong as top_p controls diversity.

Answer

Set the top_p parameter to a low value.

Answer

Fine-tune the model on a dataset of code in both languages.

Answer

Set the temperature to 0 to make the model deterministic.

Question 13

Which TWO Azure AI services can be used to build a conversational chatbot that uses generative AI? (Choose two.)

Accepted Answer

Azure AI Bot Service. Option A is correct because Azure OpenAI Service provides generative models. Option C is correct because Azure AI Bot Service provides the bot framework. Option B is wrong as Azure AI Search is for search, not conversational. Option D is wrong as Azure AI Translator is for translation. Option E is wrong as Azure AI Language provides NLP but not a complete chatbot framework.

Answer

Azure AI Search

Answer

Azure AI Translator

Answer

Azure AI Language

Question 14

You need to deploy a generative AI model that can be used by multiple applications within your organization. The model must support real-time inference with low latency. Which Azure service should you use?

Accepted Answer

Azure OpenAI Service. Option B is correct because Azure OpenAI Service provides managed endpoints with low latency for real-time inference. Option A is wrong because Azure Machine Learning real-time endpoints also work but require more management overhead; Azure OpenAI is more purpose-built for generative AI. Option C is wrong because Azure AI Search is for indexing and search, not inference. Option D is wrong because Azure Functions is a compute service, not designed for hosting large language models.

Answer

Azure AI Search

Answer

Azure Machine Learning real-time endpoint

Answer

Azure Functions

Question 15

Your organization uses Azure OpenAI Service to generate code snippets. You want to log all user prompts and model responses for auditing purposes. What should you configure?

Accepted Answer

Enable diagnostic settings in Azure OpenAI Service to send logs to a Log Analytics workspace.. Option A is correct because Azure OpenAI Service supports content filtering and logging via diagnostic settings; you can send logs to Azure Monitor or storage. Option B is wrong because Azure AI Search is not for logging. Option C is wrong because Azure API Management proxies but does not natively log model responses. Option D is wrong because Azure Key Vault is for secrets management.

Answer

Use Azure API Management to log requests and responses.

Answer

Store logs in Azure Key Vault.

Answer

Use Azure AI Search to index the prompts and responses.