AI-102 Implement generative AI solutions — 10 Questions

Question 1

A developer wants to deploy a custom generative AI model using Azure Machine Learning. Which compute target should they choose for low-latency real-time inference?

Accepted Answer

Azure Kubernetes Service (AKS). Azure Kubernetes Service (AKS) is the correct compute target for low-latency real-time inference because it supports horizontal pod autoscaling, GPU acceleration, and can be configured with a low-latency ingress controller (e.g., NGINX or Azure Application Gateway) to route inference requests directly to model containers. AKS also integrates with Azure Machine Learning's real-time inference endpoint, which uses a gRPC or HTTP-based scoring protocol to achieve sub-100ms response times.

Answer

Local deployment

Answer

Azure Batch

Answer

Azure Functions

Question 2

A company uses Azure OpenAI to generate code snippets. They notice that the model sometimes produces code that uses deprecated APIs. They want to minimize this without retraining the model. What should they do?

Accepted Answer

Add a system message instructing the model to use only current, non-deprecated APIs.. Adding a system message in Azure OpenAI allows you to set high-level instructions that guide the model's behavior without retraining. By explicitly instructing the model to use only current, non-deprecated APIs, you leverage the system prompt's ability to influence output style and content, effectively reducing deprecated API usage in generated code snippets.

Answer

Fine-tune the model on a dataset of recent code.

Answer

Set the temperature parameter to 0 to reduce randomness.

Answer

Provide a few-shot example of correct code in the prompt.

Question 3

A research lab wants to use Azure OpenAI to generate synthetic data for training a model. They need to generate a large volume of data quickly and cost-effectively. Which approach should they use?

Accepted Answer

Use the batch API to process requests asynchronously.. The batch API is designed for high-throughput, asynchronous processing of large volumes of requests, making it ideal for generating synthetic data at scale. It allows the lab to submit many prompts in a single batch, which Azure OpenAI processes efficiently, reducing both cost and time compared to real-time processing.

Answer

Fine-tune a model to generate the data locally.

Answer

Use the streaming API with multiple concurrent connections.

Answer

Deploy a model on Azure Functions and call it in parallel.

Question 4

Which TWO Azure services can be used together with Azure OpenAI to implement a Retrieval-Augmented Generation (RAG) solution?

Accepted Answer

Azure Cosmos DB. Azure AI Search (option C) is correct because it provides the vector and hybrid search index that retrieves the most relevant document chunks to ground the Azure OpenAI model's responses in a RAG pattern. Azure Cosmos DB (option B) is correct because it can serve as the data store for the source documents and, with its vector indexing capabilities, can also be queried to supply relevant context to Azure OpenAI. Azure Blob Storage (A) is only a storage layer and lacks native retrieval/ranking, so it cannot by itself fulfill the retrieval role. Azure SQL Database (D) is a relational store without built-in vector search for RAG retrieval. Azure Functions (E) is compute glue for orchestration, not a retrieval or knowledge store service.

Answer

Azure Blob Storage

Answer

Azure SQL Database

Answer

Azure Functions

Question 5

A company is deploying a generative AI solution using Azure OpenAI Service to generate product descriptions. The solution must comply with responsible AI principles, specifically ensuring that generated content does not include harmful or offensive language. Which Azure AI service feature should they implement to automatically filter the output?

Accepted Answer

Enable the default content filtering system in Azure OpenAI Service.. Azure OpenAI Service includes a built-in default content filtering system that automatically screens generated outputs for harmful or offensive language, aligning with responsible AI principles. This system operates at the service level without additional configuration, making it the simplest and most direct way to filter product descriptions for compliance.

Answer

Configure Prompt Shields in Azure AI Content Safety.

Answer

Use Azure AI Content Safety with a custom category severity threshold.

Answer

Use groundedness detection in Azure AI Content Safety.

Question 6

A developer is using Azure OpenAI to generate code snippets. The developer needs to ensure that the generated code does not contain security vulnerabilities. Which TWO actions should the developer take? (Choose two.)

Accepted Answer

Include examples of secure coding practices in the prompt.. Option A is correct because including examples of secure coding practices in the prompt (few-shot prompting) conditions the model on desired secure patterns, which measurably reduces the likelihood of generating vulnerable code such as SQL injection or hardcoded secrets. Option D is correct because Azure OpenAI's content filtering feature can be configured with custom blocklists and category filters (e.g., Hate, Violence, Self-Harm, Sexual) to detect and block malicious or harmful code patterns before they reach the developer. Option B is incorrect because max_tokens only controls output length and has no bearing on code security. Option C is incorrect because fine-tuning on insecure code would teach the model to reproduce vulnerabilities, the opposite of the goal. Option E is incorrect because a system message alone is a soft instruction and does not provide the deterministic enforcement that content filtering or concrete secure examples do.

Answer

Set the max_tokens parameter to a high value to allow longer outputs.

Answer

Fine-tune the model on a dataset containing examples of insecure code.

Answer

Add a system message that instructs the model to never generate insecure code.

Question 7

Refer to the exhibit. The developer is using Azure OpenAI with data sources (preview) to ground the model on a custom dataset. The assistant response includes a citation [^1]. However, the developer notices that the citation does not appear in the final output displayed to the user. What is the most likely cause?

Accepted Answer

The 'include_contexts' parameter in the API call is set to false.. The 'include_contexts' parameter controls whether citation metadata from the data sources is included in the final output. When set to false, the API suppresses the citation markers (e.g., [^1]) even though the underlying context was used to generate the response. This is a preview feature of Azure OpenAI with your own data, where the citation rendering is explicitly gated by this parameter.

Answer

The citation format [^1] is not supported in Azure OpenAI with data sources.

Answer

The system message overrides the citation rendering.

Answer

The 'context' object in the assistant response is not being passed back in the prompt for the next turn.

Question 8

Drag and drop the steps to configure a multi-region disaster recovery for Azure Cognitive Services into the correct order.

Accepted Answer

Create resources in both regions, then enable geo-replication, then configure failover routing, then set up monitoring, then test failover. Start by creating resources in both regions, then set up replication, configure failover routing, monitor health, and test.

Answer

Create resources, then configure failover routing, then enable geo-replication, then set up monitoring, then test failover

Answer

Create resources, then enable geo-replication, then set up monitoring, then configure failover routing, then test failover

Answer

Create resources, then enable geo-replication, then configure failover routing, then test failover, then set up monitoring

Question 9

Drag and drop the steps to build and deploy a custom Azure AI Document Intelligence model into the correct order.

Accepted Answer

Step 1: Gather and label documents, Step 2: Create the Azure AI Document Intelligence resource, Step 3: Train the model, Step 4: Test the model, Step 5: Publish the model. First gather and label documents, create the resource, train the model, test, and publish.

Answer

Step 1: Create the Azure AI Document Intelligence resource, Step 2: Gather and label documents, Step 3: Train the model, Step 4: Test the model, Step 5: Publish the model

Answer

Step 1: Gather and label documents, Step 2: Train the model, Step 3: Create the Azure AI Document Intelligence resource, Step 4: Test the model, Step 5: Publish the model

Answer

Step 1: Gather and label documents, Step 2: Create the Azure AI Document Intelligence resource, Step 3: Test the model, Step 4: Train the model, Step 5: Publish the model

Question 10

Match each Azure Bot Service channel to its description.

Accepted Answer

Direct Line: Enables communication between your bot and your own client application.. The correct matches are: Direct Line for custom client communication, Web Chat for embeddable chat, Microsoft Teams for team collaboration, and Facebook Messenger for Messenger integration. Common mistakes include confusing Direct Line and Web Chat definitions.

Answer

Direct Line: Embeds a chat control in a web page.

Answer

Microsoft Teams: Enables communication between your bot and your own client application.