AI-102 Practice Exam 3 — 20 Questions

Question 1

You are designing a knowledge mining solution for a medical research organization. The solution must extract relationships between drugs, diseases, and genes from scientific articles. The data will be stored in a knowledge graph for querying. Which Azure AI service should you use for the extraction?

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

Accepted Answer

Azure AI Language healthcare entity recognition and relation extraction. Azure AI Language's healthcare entity recognition and relation extraction is specifically designed to extract medical entities (drugs, diseases, genes) and their relationships from unstructured text, making it ideal for building a knowledge graph. This pre-built model uses deep learning trained on biomedical literature, directly supporting the required extraction without custom training.

Answer

Azure AI Search with semantic ranking

Answer

Azure AI Translator with dictionary lookup

Answer

Azure AI Document Intelligence custom extraction model

Question 2

You have the above skillset in Azure AI Search. The indexer processes a document with 12,000 characters of content. How many entity recognition skill executions occur?

Accepted Answer

3. The Azure AI Search entity recognition skill has a maximum text length per execution of 5,000 characters. A document with 12,000 characters is split into chunks of up to 5,000 characters, resulting in three chunks (5,000 + 5,000 + 2,000). Each chunk triggers one skill execution, so three executions occur.

Answer

4

Answer

2

Answer

1

Question 3

You plan to use Azure AI Search to index a large number of text documents stored in Azure Blob Storage. The documents are in English. You want to automatically extract key phrases from the content during indexing. What should you add to the skillset?

Accepted Answer

Key Phrase Extraction skill. The Key Phrase Extraction skill is the correct choice because it is specifically designed to identify and extract important phrases from text content, which aligns with the requirement to automatically extract key phrases during indexing. This skill is part of Azure AI Search's cognitive skillset and operates on English text to produce a list of key phrases per document.

Answer

Sentiment skill

Answer

Language Detection skill

Answer

Entity Recognition skill

Question 4

Which THREE considerations are important when designing a custom skill for Azure AI Search that calls an external API for specialized data extraction?

Accepted Answer

The API endpoint must be reachable from the search service. Option A is correct because a custom skill in Azure AI Search is essentially a Web API skill that the indexer invokes over HTTPS, so the external API endpoint must be network-reachable from the search service (including any required private endpoint or firewall rules) or enrichment will fail. Option D is correct because the Web API skill has a documented maximum request payload size of 16 MB; larger payloads will be rejected, so the skill design must keep the serialized input within that limit. Option E is correct because the Web API skill enforces a maximum execution time of 230 seconds per call, after which the request times out, so long-running extraction logic must be optimized or split. Option B is wrong because a custom skill can accept multiple inputs and produce multiple outputs via the inputs and outputs mappings. Option C is wrong because the skill can be implemented in any language or framework (for example C#, Node.js, or Java) as long as it exposes a compatible HTTP endpoint.

Answer

The skill can only accept one input and produce one output

Answer

The skill must be written in Python

Question 5

A financial services firm uses Azure AI Language to analyze earnings call transcripts. They need to extract key phrases and identify sentiment for each speaker's turn. Which approach should they use?

Accepted Answer

Split the transcript by speaker turns and call key phrase extraction and sentiment analysis on each part. The requirement is to extract key phrases and identify sentiment per speaker turn. The Azure AI Language key phrase extraction and sentiment analysis APIs operate on individual text inputs. By splitting the transcript by speaker turns, each segment can be analyzed independently, providing per-speaker insights. Processing the entire transcript as a single document would aggregate sentiment and key phrases, losing per-speaker granularity.

Answer

Call the prebuilt sentiment analysis API on the entire transcript

Answer

Use QnA Maker to extract Q&A pairs per speaker

Answer

Use Text Analytics for health to extract entities and sentiment

Question 6

You are a solution architect at a legal firm. The firm wants to build a copilot using Microsoft Foundry that answers questions about case law documents stored in Azure Blob Storage. The copilot should use the Retrieval Augmented Generation (RAG) pattern with Azure AI Search as the vector store. The documents are in PDF format and include complex tables and footnotes. The solution must ensure that the answers are grounded in the documents and that the copilot can handle follow-up questions. You need to design the ingestion pipeline. Which approach should you take?

Accepted Answer

Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search. It uses Azure AI Document Intelligence to accurately extract content from PDFs (including complex tables and footnotes), then chunks by headings and paragraphs to preserve document structure, generates embeddings via Azure OpenAI for semantic understanding, and indexes in Azure AI Search with vector search to enable RAG-based, grounded answers with follow-up support.

Answer

Use Azure AI Vision OCR to extract text, split by page, and use Azure AI Search keyword search

Answer

Use Azure AI Document Intelligence prebuilt-read model, chunk by character count, and use Azure AI Search with semantic ranking

Answer

Use Azure AI Language to extract key phrases, create a non-vector index, and use simple search

Question 7

You are building a knowledge mining solution for legal documents using Azure AI Search. The solution must extract entities like dates, organizations, and persons from PDF files and index them. Which built-in skill should you add to the skillset to perform this extraction?

Accepted Answer

Named Entity Recognition skill. The Named Entity Recognition (NER) skill in Azure AI Search is specifically designed to extract entities such as dates, organizations, and persons from text. When added to a skillset, it processes the content extracted from PDF files and outputs structured entity information that can be indexed and queried. This directly matches the requirement to extract and index named entities from legal documents.

Answer

Language Detection skill

Answer

Optical Character Recognition (OCR) skill

Answer

Key Phrase Extraction skill

Question 8

Refer to the exhibit. You have this Azure AI Search indexer configuration. The indexer is failing after processing 6 documents that contain errors. What should you do to ensure the indexer continues processing even if some documents fail?

Accepted Answer

Increase maxFailedItems to a higher value, such as 100. The indexer is failing after processing 6 documents because the `maxFailedItems` threshold has been reached. By increasing `maxFailedItems` to a higher value like 100, the indexer will continue processing even if more documents fail, as long as the total number of failed items stays below the new threshold.

Answer

Decrease the batch size to 5

Answer

Increase batch size to 20

Answer

Remove the schedule to run the indexer on demand

Question 9

A company uses Azure OpenAI to generate product descriptions. They notice that the model occasionally produces descriptions that include false claims about product features. The company needs to reduce the frequency of these inaccuracies without changing the training data. Which parameter adjustment would be most effective?

Accepted Answer

Decrease the temperature parameter. Decreasing the temperature parameter reduces the randomness of the model's output, making it more deterministic and less likely to generate creative but factually incorrect statements. This directly addresses the need to reduce false claims without modifying training data, as lower temperature forces the model to rely on its most probable (and typically more accurate) token predictions.

Answer

Increase the top_p parameter

Answer

Increase the max_tokens parameter

Answer

Increase the frequency_penalty parameter

Question 10

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. A Microsoft Copilot Studio copilot is the core conversational interface that orchestrates the interaction. Without the copilot itself, there is no runtime environment to process user queries, manage conversation state, or invoke configured knowledge sources. It is the mandatory host for all custom copilot functionality.

Answer

A Power Automate flow to trigger the copilot

Answer

An Azure OpenAI Service deployment

Question 11

Drag and drop the steps to create a custom question answering project in Azure Language Service into the correct order.

Accepted Answer

Step 1: Create Azure resource, Step 2: Access Language Studio, Step 3: Create project, Step 4: Add QnA pairs, Step 5: Train and deploy. First, create the Azure resource. Then access Language Studio, create the project, add QnA pairs, and finally train and deploy.

Answer

Step 1: Access Language Studio, Step 2: Create Azure resource, Step 3: Create project, Step 4: Add QnA pairs, Step 5: Train and deploy

Answer

Step 1: Create Azure resource, Step 2: Create project, Step 3: Access Language Studio, Step 4: Add QnA pairs, Step 5: Train and deploy

Answer

Step 1: Add QnA pairs, Step 2: Create project, Step 3: Create Azure resource, Step 4: Access Language Studio, Step 5: Train and deploy

Question 12

Which THREE actions can be performed using the Azure Custom Vision service?

Accepted Answer

Export a trained model to ONNX format for offline inference.. Option B is correct because Azure Custom Vision supports exporting trained models in several formats, including ONNX, TensorFlow, CoreML, and Docker, enabling offline or edge inference. Option C is correct because Custom Vision is designed for image classification, allowing you to train a model that assigns images to labeled classes such as product types. Option D is correct because Custom Vision also supports object detection, which returns bounding boxes and labels for multiple objects within an image. Option A is not correct because extracting text from scanned receipts is an OCR task handled by Azure AI Vision (Computer Vision Read API) or Document Intelligence, not Custom Vision. Option E is not correct because identifying specific individuals via facial recognition is provided by Azure AI Face, not Custom Vision.

Answer

Extract text from scanned receipts.

Answer

Identify specific individuals in a crowd using facial recognition.

Question 13

Which TWO of the following are best practices for securing Azure AI services?

Accepted Answer

Enable diagnostic settings to audit usage and detect anomalies.. Option C is correct because enabling diagnostic settings on Azure AI services streams resource logs and metrics to destinations such as Log Analytics, Azure Storage, or Event Hubs, which supports auditing usage, monitoring for anomalies, and meeting compliance requirements. Option E is correct because managed identities let applications authenticate to Azure AI services via Microsoft Entra ID tokens, eliminating the need to store or rotate API keys in code or configuration. Option A is incorrect since publicly exposing endpoints increases the attack surface; access should be restricted with private endpoints, network ACLs, or Azure Private Link. Option B is incorrect because disabling diagnostic logging removes the audit trail needed to detect misuse and investigate incidents. Option D is incorrect because sharing API keys across applications prevents per-app revocation and least-privilege scoping, so keys should be unique, stored in Key Vault, and rotated regularly.

Answer

Expose endpoints publicly to simplify client access.

Answer

Disable diagnostic logging to reduce data exposure.

Answer

Share API keys among multiple applications for simplicity.

Question 14

A company wants to generate product descriptions for thousands of items using an Azure OpenAI GPT-4 model. They need to ensure the descriptions match a consistent brand voice. Which approach is most efficient and cost-effective?

Accepted Answer

Set a system message with brand voice guidelines and use few-shot examples. Setting a system message with brand voice guidelines and providing few-shot examples allows the GPT-4 model to consistently apply the desired tone and style across all product descriptions without retraining. This approach is efficient and cost-effective as it avoids the high compute and data preparation costs of fine-tuning, while still enabling precise control over output through in-context learning.

Answer

Write a separate prompt for each product category

Answer

Use Azure OpenAI on your data with a vector database of brand guidelines

Answer

Fine-tune a base model on existing product descriptions

Question 15

Refer to the exhibit. A developer runs this PowerShell script to call Azure OpenAI. The script fails with an authentication error. What is the most likely cause?

Accepted Answer

The script uses the wrong HTTP header; it should use 'api-key' instead of 'Authorization: Bearer'.. The script uses 'Authorization: Bearer' header, but Azure OpenAI requires the API key to be passed in the 'api-key' header. The 'Authorization: Bearer' header is used for Microsoft Entra ID token-based authentication, not for direct API key authentication. Since the script is using an API key (as indicated by the PowerShell script), the correct header is 'api-key'.

Answer

The script uses the wrong HTTP method; it should use GET.

Answer

The API version is incorrect.

Answer

The endpoint URI is missing the resource name.

Question 16

You need to generate realistic synthetic data using Azure OpenAI Service to train a machine learning model. The data must be diverse and cover edge cases. Which approach should you use?

Accepted Answer

Use prompt engineering with detailed instructions to generate varied examples.. Prompt engineering with detailed instructions allows you to explicitly control the diversity, structure, and edge-case coverage of generated synthetic data without requiring a pre-existing dataset. By crafting system messages and user prompts that specify variations in attributes, formats, and boundary conditions, you can produce a wide range of realistic examples that mimic real-world distributions, which is essential for training robust machine learning models.

Answer

Fine-tune the model on a small dataset of real examples.

Answer

Use Azure OpenAI embeddings to generate similar data points.

Answer

Set a high temperature parameter only.

Question 17

Your company uses Azure AI Content Safety to moderate user-generated content in a chat application. You need to detect and block sexual content in multiple languages. Which pre-built category should you configure?

Accepted Answer

Sexual. Azure AI Content Safety provides pre-built severity-based categories for content moderation. The 'Sexual' category is specifically designed to detect and block explicit sexual content, including text and images, across multiple languages. This makes it the correct choice for your requirement to moderate sexual content in a chat application.

Answer

Self-harm

Answer

Hate

Answer

Violence

Question 18

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. Azure AI Language sentiment analysis is the correct component because it provides pre-built sentiment detection capabilities that analyze text and return sentiment labels (positive, negative, neutral) and confidence scores. This directly meets the requirement to detect negative user sentiment in chatbot conversations, enabling escalation to a human agent when needed.

Answer

Azure Cognitive Search

Answer

Orchestration workflow

Answer

QnA Maker

Question 19

You are a generative AI engineer at a financial services company. The company uses Azure OpenAI Service to generate investment summaries. You have deployed a GPT-4 model with a content filter set to 'Low' for hate speech. The model frequently generates summaries that include biased language against certain demographics. You need to reduce biased outputs while maintaining the ability to generate detailed financial analysis. You cannot afford to retrain the model. You have the following options: A) Change the content filter severity to 'High' for all categories, B) Add a system message instructing the model to avoid bias and provide examples of unbiased summaries in the prompt, C) Use the Azure AI Language service to detect bias in the output and regenerate if bias is found, D) Deploy a different model like GPT-3.5 which has less bias. Which course of action should you take?

Accepted Answer

Add a system message instructing the model to avoid bias and provide examples of unbiased summaries in the prompt.. Adding a system message that explicitly instructs the model to avoid bias and providing few-shot examples of unbiased summaries is the most direct and cost-effective way to steer the model's behavior without retraining. This approach leverages prompt engineering to influence the model's output distribution while preserving the ability to generate detailed financial analysis.

Answer

Use the Azure AI Language service to detect bias in the output and regenerate if bias is found.

Answer

Change the content filter severity to 'High' for all categories.

Answer

Deploy a different model like GPT-3.5 which has less bias.

Question 20

You are implementing a generative AI solution using Azure OpenAI. You need to ensure that the model's outputs do not contain certain inappropriate words or phrases. Which feature should you configure?

Accepted Answer

Content filters. Content filters in Azure OpenAI are specifically designed to detect and block inappropriate words or phrases in both prompts and completions. They operate at the service level, applying configurable severity thresholds for categories like hate, violence, sexual content, and self-harm, ensuring model outputs adhere to policy without requiring prompt engineering or data modifications.

Answer

System message instructions

Answer

Grounding with your data

Answer

Max tokens limit