AI-102 Practice Test 4 — 10 Questions

Question 1

You are building an agent for a legal firm that uses Azure OpenAI to analyze contracts. The agent must extract key clauses, identify risks, and summarize the contract. The agent uses a RAG pattern with Azure Cognitive Search as the vector database. After deployment, the agent sometimes returns irrelevant information or fails to find relevant clauses. You suspect the issue is with the chunking strategy. The contracts are large, typically 50-100 pages. Currently, you are chunking by page (each page is one chunk). You want to improve retrieval accuracy. Which action should you take?

Accepted Answer

Change chunking to use semantic boundaries: split at clause or section headings.. Option D is correct because splitting contracts at semantic boundaries (clause or section headings) preserves the natural meaning and context of each chunk, which is critical for legal document analysis. Page-level chunking often splits a clause across two pages, causing the vector search to retrieve incomplete or irrelevant information. By aligning chunks with the document's logical structure, the RAG pattern retrieves more coherent and relevant passages for the Azure OpenAI agent to process.

Answer

Keep page-level chunking but add 50% overlap between chunks.

Answer

Use a different embedding model, such as text-embedding-3-large.

Answer

Increase the chunk size to 5 pages per chunk and reduce overlap.

Question 2

A company is building an agent that uses Azure OpenAI to answer questions from a large document library. The agent must use a Retrieval Augmented Generation (RAG) pattern. Which TWO actions should the team take to implement RAG effectively?

Accepted Answer

Index the documents into a vector database like Azure Cognitive Search.. Option C is correct because indexing documents into a vector database like Azure Cognitive Search enables efficient similarity search over embeddings, which is the retrieval foundation of RAG. This allows the system to quickly find the most relevant document chunks based on semantic meaning, rather than relying on the model to memorize or be fine-tuned on the entire library.

Answer

Ensure the model is large enough to memorize the entire document library.

Answer

Fine-tune the Azure OpenAI model on the document library.

Answer

Train a custom language model from scratch.

Question 3

An agent uses Azure AI Language to perform sentiment analysis on customer feedback. The team notices that the sentiment scores are sometimes inaccurate for negative feedback. Which TWO improvements should the team consider?

Accepted Answer

Pre-process the text to handle negations and sarcasm.. Option A is correct because Azure AI Language's pre-built sentiment analysis models can struggle with linguistic nuances like negations (e.g., 'not good') and sarcasm (e.g., 'Great, another delay'). Pre-processing the text to explicitly handle these patterns—such as by expanding contractions or using negation detection—can improve the accuracy of the sentiment scores before they are passed to the model.

Answer

Switch to a different language model without fine-tuning.

Answer

Increase the number of decimal places in the sentiment score.

Answer

Increase the confidence threshold for positive sentiment.

Question 4

An e-commerce company wants to build an agent that helps users track orders, initiate returns, and answer FAQs. The agent should be available on the company's website and mobile app. Which Azure service should the team use to deploy the agent?

Accepted Answer

Azure Bot Service. Azure Bot Service is the correct choice because it provides a managed environment for building, deploying, and scaling conversational AI agents that can be integrated with multiple channels, including websites and mobile apps. It supports the Bot Framework SDK, which enables the agent to handle order tracking, returns, and FAQs through natural language understanding (NLU) with LUIS or the newer CLU service.

Answer

Azure Logic Apps

Answer

Azure API Management

Answer

Azure Functions

Question 5

A company is developing an agent that uses Azure AI Language to extract entities and intents from user queries. The agent receives a query: 'Book a flight to Paris on Friday.' The agent should extract the intent as 'BookFlight' and entities as 'Paris' (destination) and 'Friday' (date). The team uses a custom entity extraction model. After testing, the model extracts 'Paris' as location but fails to extract 'Friday' as date. What should the team do to fix this?

Accepted Answer

Train the entity extraction model with more examples of dates.. Option C is correct because the custom entity extraction model in Azure AI Language requires sufficient labeled examples for each custom entity type to learn patterns. Since the model extracts 'Paris' (location) but fails on 'Friday' (date), the issue is specifically with the date entity's training data, not the location. Adding more diverse examples of date expressions (e.g., 'next Monday', 'tomorrow', 'March 5th') will improve the model's ability to recognize 'Friday' as a date entity.

Answer

Increase the training data for location entities.

Answer

Add a prebuilt entity component for date.

Answer

Use a different intent classification model.

Question 6

A company is deploying an Azure AI solution that uses Azure Cognitive Services. The solution must comply with data residency requirements that mandate all customer data be stored within a specific geographic region. Which action should the company take when creating the Cognitive Services resource?

Accepted Answer

Select the appropriate region during resource creation.. Data residency requirements are satisfied by physically storing customer data within a specific geographic boundary. When creating an Azure Cognitive Services resource, selecting the appropriate region (e.g., 'West Europe' or 'East US') during the provisioning process ensures that all data processed and stored by that service instance remains within that Azure datacenter region. This is the fundamental and only guaranteed method to enforce data residency at the resource level.

Answer

Apply a resource tag that specifies the region.

Answer

Configure the endpoint URL to point to a regional endpoint.

Answer

Set the SKU to a tier that supports regional restrictions.

Question 7

A developer is building a chatbot using Azure Bot Service and Language Understanding (LUIS). The bot needs to handle multiple intents, including 'BookFlight', 'CancelFlight', and 'CheckWeather'. During testing, the bot frequently confuses 'BookFlight' and 'CancelFlight' intents. What is the most effective way to improve intent classification accuracy?

Accepted Answer

Add more varied training utterances for 'BookFlight' and 'CancelFlight' intents.. Adding more varied training utterances for the 'BookFlight' and 'CancelFlight' intents directly addresses the root cause of confusion: insufficient or overlapping training data. LUIS relies on diverse utterance patterns to distinguish between semantically similar intents; increasing the quantity and variety of labeled examples improves the model's ability to learn discriminative features, thereby boosting classification accuracy.

Answer

Reduce the number of intents by merging similar ones.

Answer

Increase the confidence threshold for intent predictions.

Answer

Add more entities to the utterances.

Question 8

A company is using Azure Form Recognizer to extract data from invoices. The prebuilt model does not correctly extract a custom field that is specific to the company's invoices. What is the most appropriate action to improve extraction accuracy for this field?

Accepted Answer

Train a custom model using labeled invoices that include the custom field.. The prebuilt Form Recognizer model is designed for common invoice layouts and may not recognize company-specific fields. Training a custom model with labeled invoices that include the custom field allows the model to learn the field's location and semantics, significantly improving extraction accuracy for that specific field.

Answer

Use the prebuilt model with a custom field mapping.

Answer

Adjust the confidence threshold for the prebuilt model.

Answer

Retrain the prebuilt model with additional invoices.

Question 9

A company plans to use Azure Cognitive Search to index a large number of PDF documents stored in Azure Blob Storage. The documents contain sensitive personally identifiable information (PII). The search results should only be accessible to authorized users based on their Azure Active Directory (Azure AD) group membership. Which combination of features should the company implement?

Accepted Answer

Index the documents and use security filters with Azure AD group-based access control.. Option B is correct because Azure Cognitive Search supports security trimming via OAuth 2.0 and Azure AD group-based access control. By storing group identifiers in a search index field and using a security filter, only users whose Azure AD group membership matches the stored group IDs can see the corresponding search results. This ensures that sensitive PII in PDF documents is only returned to authorized users without exposing the documents themselves.

Answer

Generate shared access signatures (SAS) for each document and include them in the search index.

Answer

Use Azure RBAC to assign permissions to users for the search service and configure field-level security.

Answer

Store Azure AD group membership in a field in the search index and configure an indexer to map the field.

Question 10

A company uses Azure Content Moderator to review user-generated images in a social media app. Recently, the team noticed that images containing subtle adult content are not being flagged. What should they do to improve detection without increasing false positives?

Accepted Answer

Configure a human review team using the Review tool to manually inspect flagged content.. Option C is correct because Azure Content Moderator is designed to work with human review teams via the Review tool to handle edge cases where automated detection fails. By configuring a human review team, flagged images can be manually inspected to catch subtle adult content that the machine learning model misses, without lowering thresholds that would increase false positives. This approach leverages human judgment to improve detection accuracy while maintaining the existing automated moderation settings.

Answer

Increase the moderation thresholds for adult content.

Answer

Disable the adult classification tier to allow all images to pass through.

Answer

Retrain the Content Moderator model with additional labeled images of adult content.