AI-103 Implement Generative AI And Agentic Solutions Practice Test 8 — 15 Questions

Question 1

You are developing an agent using Azure AI Agent Service and notice that the model consistently refuses to answer queries about company-internal technical specifications despite the documentation being uploaded to the vector index. Which action should you prioritize?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Verify the 'Grounding' settings in the Azure AI Foundry portal to ensure the search index is correctly linked.. Grounding ensures the model queries the provided data before generating a response. If it refuses to answer, the grounding configuration is likely failing or missing the retrieval step.

Answer

Enable 'Content Safety' to bypass filtering.

Answer

Increase the system prompt length in the model configuration.

Answer

Switch the model to a higher parameter count version.

Question 2

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. Responsible AI involves monitoring, filtering, and transparency, including content filtering and human-in-the-loop validation.

Answer

Store all user PII in plain text logs

Answer

Increase the temperature of the model to 1.0

Question 3

An agent is prone to 'hallucinations' when responding to specific niche queries. What is the most effective way to reduce these hallucinations using RAG?

Accepted Answer

Set the grounding threshold to a higher value in the agent configuration.. Increasing the 'top_k' or relevance threshold ensures the retrieved data is highly specific to the query, reducing ambiguity.

Answer

Retrain the base LLM on the niche dataset.

Answer

Increase the system prompt length.

Answer

Lower the temperature setting to 0.0.

Question 4

You are building an agentic workflow in Azure AI Foundry. You need the agent to perform a multi-step task: search a database, summarize results, and then send an email. Which component is best suited to manage this orchestration?

Accepted Answer

Azure AI Agent Service.. The Agent Service provides the orchestration framework for agents to manage state, tools, and multi-step reasoning.

Answer

Azure OpenAI fine-tuning service.

Answer

Azure AI Search indexer.

Answer

Azure AI Content Safety API.

Question 5

You are configuring an agent that must call a REST API to get current stock prices. Where must you define this integration to ensure the agent can reliably call the tool?

Accepted Answer

In the Agent Tool Definition.. Tool definitions are required for models to understand how to interact with external functions.

Answer

In the Azure OpenAI deployment configuration.

Answer

In the Search index field mapping.

Answer

In the System Prompt.

Question 6

You need to evaluate the performance of your prompt engineering for a summarization task. Which tool in Azure AI Foundry allows you to run multiple prompt variants against a dataset to compare outputs?

Accepted Answer

Azure AI Prompt Flow.. Prompt flow evaluation allows for comparing prompt versions against specific datasets systematically.

Answer

Azure OpenAI studio Playground.

Answer

Azure AI Content Safety.

Answer

Azure AI Search.

Question 7

You want to monitor the cost and latency of your agentic application in production. Which service should you integrate with your Azure AI Foundry project?

Accepted Answer

Azure Application Insights.. Azure Monitor combined with Application Insights is the standard for tracking telemetry in Azure AI services.

Answer

Azure OpenAI Studio.

Answer

Azure AI Search.

Answer

Azure AI Content Safety.

Question 8

A user asks a question that triggers a 'Blocked' response from Azure AI Content Safety, even though the query seems harmless. What is the best step to investigate this?

Accepted Answer

Check the Content Safety logs in the Azure AI Foundry portal.. Viewing the logs in the Content Safety dashboard identifies which specific policy was triggered.

Answer

Change the system prompt to ignore safety.

Answer

Increase the model temperature.

Answer

Disable Content Safety for the deployment.

Question 9

What is the primary purpose of a 'Vector Store' in a RAG-based agentic application?

Accepted Answer

To store embeddings for efficient semantic similarity search.. Vector stores allow for semantic search, which finds content based on meaning rather than exact keyword matching.

Answer

To generate text responses.

Answer

To log user conversations for analytics.

Answer

To fine-tune the LLM.

Question 10

An agent is performing poorly on multi-hop reasoning tasks. What architectural pattern should you implement to improve performance?

Accepted Answer

Use a Chain-of-Thought prompting strategy in the agent's system prompt.. Chain-of-thought prompting forces the model to break down complex queries into intermediate logical steps.

Answer

Increase the temperature to 1.0.

Answer

Switch to a smaller model to increase speed.

Answer

Decrease the max_tokens parameter.

Question 11

You are designing an agent that needs to access user-specific data from OneDrive. How should you handle the authentication for this tool call?

Accepted Answer

Use a Managed Identity for the agent.. Managed Identities provide the secure, token-based authentication required for services to communicate without storing credentials.

Answer

Disable authentication for the API.

Answer

Hardcode the OAuth tokens in the tool definition.

Answer

Request the user to provide credentials via the chat interface.

Question 12

You are configuring a Prompt Flow to use a custom Python tool. Which configuration is required to ensure the environment has the necessary libraries?

Accepted Answer

Include them in a 'requirements.txt' file in the flow directory.. Dependencies for custom tools must be defined in the 'requirements.txt' file within the flow folder.

Answer

Install them manually on the host machine.

Answer

Add them to the System Prompt.

Answer

Add them to the deployment manifest.

Question 13

When using Prompt Flow, you notice that your flow is failing at the 'aggregate' node. What is the most likely cause?

Accepted Answer

The input data from the previous node does not match the expected schema of the aggregate node.. The aggregate node expects a specific schema and iteration results from the previous node; if these are missing or mismatched, the flow fails.

Answer

The system prompt is too long.

Answer

The search index is empty.

Answer

The model is too busy.

Question 14

You are using Azure AI Foundry to deploy an agent. You want to ensure that the agent only uses approved data sources. Which feature should you configure?

Accepted Answer

Grounding data configuration in the Agent settings.. Grounding with specific data sources restricts the agent to provided data, preventing the use of external knowledge.

Answer

Prompt engineering for 'Do not use external info'.

Answer

Model temperature control.

Answer

Content Safety policy filters.

Question 15

Which Azure AI Foundry feature allows you to visualize the execution path of an agentic workflow?

Accepted Answer

Prompt Flow visual designer.. The Prompt Flow canvas provides a visual representation of the nodes and connections in your workflow.

Answer

Azure OpenAI Playground.

Answer

Azure AI Search dashboard.

Answer

Model catalog view.