AI-103 Implement Generative AI And Agentic Solutions Practice Test 9 — 15 Questions

Question 1

You need to ensure that your agent's response is formatted as valid JSON. How should you approach this?

Accepted Answer

Define the JSON schema in the system prompt instructions.. Using structured outputs or defining the schema in the system prompt is the standard way to enforce output formats in LLMs.

Answer

Set the temperature to 0.5.

Answer

Use an external library to convert text to JSON.

Answer

Ask the user to request JSON.

Question 2

Your team is implementing 'Human-in-the-loop' (HITL) for an agent that performs account updates. Which mechanism should you use to pause the agent and wait for approval?

Accepted Answer

Use a Prompt Flow 'Pause' node or custom state management logic.. In agentic workflows, an interruption or 'callback' mechanism allows the system to pause execution until human input is received.

Answer

Set a long timeout in the API call.

Answer

Increase the model's 'stop_sequences'.

Answer

Use an infinite loop in Python.

Question 3

You are testing an agent in the Azure AI Foundry playground. You observe that the agent answers questions about its internal prompt. What is the most effective way to prevent this?

Accepted Answer

Update the system prompt to explicitly refuse requests about its instructions.. System prompts should clearly define the agent's identity and boundaries to prevent prompt leakage.

Answer

Delete the search index.

Answer

Use a higher-parameter model.

Answer

Disable the playground.

Question 4

Which role is responsible for ensuring the ethical deployment of an AI agent within an organization?

Accepted Answer

The Azure AI Developer.. Responsible AI practices are a cross-functional responsibility, but the developer must implement the technical guardrails provided by the organization.

Answer

The Data Scientist only.

Answer

The end user.

Answer

The Azure Billing Admin.

Question 5

What is the purpose of 'Batch Inference' in Azure AI Foundry?

Accepted Answer

To run multiple prompts against a large dataset for evaluation.. Batch inference allows you to process large volumes of data offline, which is more cost-effective and efficient than real-time requests.

Answer

To create a backup of the agent.

Answer

To test the agent in real-time.

Answer

To debug individual chat turns.

Question 6

You need to optimize the retrieval performance of your RAG agent. You find that the search engine returns too many irrelevant documents. What should you adjust?

Accepted Answer

Configure Hybrid Search settings in the search index.. Hybrid search (combining vector and keyword search) and adjusting ranking parameters can significantly improve retrieval accuracy.

Answer

Increase the model temperature.

Answer

Change the model to a newer version.

Answer

Reduce the system prompt length.

Question 7

You are experiencing high latency in your RAG agent. You confirm the model response time is fine, but the retrieval step is slow. What should you investigate?

Accepted Answer

The index retrieval configuration and semantic ranker parameters.. Vector search latency is often tied to index configuration, partitioning, or query complexity.

Answer

The system prompt length.

Answer

The content safety threshold.

Answer

The model temperature.

Question 8

You want to add a new tool to an agent. Which step is required to link the tool to the model?

Accepted Answer

Register the tool in the agent configuration within Azure AI Foundry.. The tool must be defined as an 'Available Tool' in the agent's configuration so the model knows it can call it.

Answer

Hardcode the tool logic in the system prompt.

Answer

Add the tool code to the global Python environment.

Answer

Update the content safety policy.

Question 9

Which of the following is a core principle of Responsible AI in Azure AI Foundry?

Accepted Answer

Transparency and explainability.. Transparency is a core principle, often implemented by providing sources and citations in AI responses.

Answer

Bypassing all safety filters.

Answer

Maximizing cost savings at any cost.

Answer

Forcing the model to agree with the user.

Question 10

When evaluating an AI agent, what does the 'Coherence' metric measure?

Accepted Answer

The logical flow and clarity of the generated text.. Coherence measures how well the generated text flows and connects logical ideas together.

Answer

The cost of the API call.

Answer

The number of sources cited.

Answer

The speed of the response.

Question 11

How do you handle sensitive user data when using an Azure AI Agent?

Accepted Answer

Use Data Masking/PII filtering before the data reaches the agent.. Data privacy practices dictate that sensitive data should be anonymized before being sent to the model or excluded from training.

Answer

Send all data to the model; the model will ignore it.

Answer

Increase the model parameter size.

Answer

Store user PII in the vector index.

Question 12

You need to ensure that your agent is compliant with regional data residency requirements. Where should you check this?

Accepted Answer

In the Azure AI Foundry resource's region settings.. Data residency is determined by the Azure region where the service instance is deployed.

Answer

In the Prompt Flow runtime.

Answer

In the Content Safety policy.

Answer

In the model configuration settings.

Question 13

You are using Prompt Flow to iterate on an agent. What is the benefit of using 'Environment Variables' in your flow?

Accepted Answer

To manage configuration settings like API keys and endpoints across environments.. Environment variables allow you to switch between development, test, and production configurations without changing code.

Answer

To reduce the model response time.

Answer

To store large data files.

Answer

To increase the prompt length.

Question 14

An agent is designed to summarize meeting transcripts but keeps including internal meeting notes in the final summary. What is the most effective way to address this?

Accepted Answer

Update the system prompt to clarify which sections of the transcript to include.. Modifying the system prompt to explicitly define the inclusion/exclusion criteria for the summary is the most effective way to control agent output.

Answer

Lower the temperature.

Answer

Switch to a different model.

Answer

Add a 'stop_sequence' to the API call.

Question 15

Which TWO actions should you take to ensure your agentic solution is 'Responsible'?

Accepted Answer

Enable Content Safety filters for all inputs and outputs.. Responsible AI involves both technical guardrails (Content Safety) and transparency (disclosures/citations).

Answer

Disable all logging to protect user privacy.

Answer

Set the model temperature to 1.0 to increase diversity.

Answer

Allow the agent to access the public internet without restrictions.