AI-102 Practice Test 7 — 10 Questions

Question 1

A company is building a chatbot using Azure Bot Service and Language Understanding (LUIS). The chatbot needs to handle user intents for booking flights and checking flight status. After testing, the chatbot frequently fails to distinguish between the two intents when users mention flight numbers. Which action should the engineer take to improve intent recognition?

Accepted Answer

Add more utterances that include flight numbers to the training data for both intents.. Option B is correct because adding more utterances that include flight numbers to both intents provides LUIS with more varied examples of how flight numbers appear in natural language, enabling the model to learn distinguishing patterns. Without sufficient training data containing flight numbers, LUIS cannot reliably differentiate between 'BookFlight' and 'CheckFlightStatus' when users mention flight numbers, as the entity alone does not determine intent.

Answer

Increase the number of intents to split the flight-related queries further.

Answer

Reduce the confidence score threshold for intent detection.

Answer

Use the prebuilt domain for flight booking to improve accuracy.

Question 2

A company is building a chatbot using Azure OpenAI Service to answer customer queries. The chatbot must not generate harmful or offensive content. Which Azure AI service should be integrated to filter inappropriate content?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety is the correct service because it provides built-in content moderation APIs that detect and filter harmful or offensive text and images, including hate speech, violence, self-harm, and sexual content. Integrating this service with the Azure OpenAI chatbot ensures that user inputs and model outputs are screened in real time, preventing the generation of inappropriate responses.

Answer

Azure Bot Service

Answer

Azure Cognitive Search

Answer

Azure Form Recognizer

Question 3

A developer is using Azure Cognitive Service for Language to perform sentiment analysis on customer reviews. The service returns sentiment labels (positive, negative, neutral) and confidence scores. For a particular review, the service returns 'positive' with a confidence score of 0.55. The developer wants to ensure that only high-confidence results are used. What should the developer do?

Accepted Answer

Configure a minimum confidence threshold of 0.75 in the application logic.. Option C is correct because the developer must implement a confidence threshold in the application logic to filter out low-confidence results. The Azure Cognitive Service for Language returns confidence scores between 0 and 1 for each sentiment label, and the developer can set a minimum threshold (e.g., 0.75) to ensure only high-confidence predictions are used. This approach does not require retraining the model or modifying the input text, as the threshold is applied post-inference in the client code.

Answer

Use the Text Analytics for Health API instead.

Answer

Retrain the sentiment analysis model with additional labeled data.

Answer

Adjust the input text by removing ambiguous phrases.

Question 4

You are analyzing a document using Azure Cognitive Service for Language named entity recognition. The exhibit shows a partial JSON response for entity extraction. The engineer notices that 'Jane Smith' has a low confidence score of 0.45. Which action should the engineer take to improve the confidence score for similar entities?

Accepted Answer

Provide more context around the entity in the input text, such as titles or roles.. Option B is correct because providing more context around the entity, such as titles or roles (e.g., 'Dr. Jane Smith' or 'CEO Jane Smith'), gives the prebuilt named entity recognition (NER) model additional linguistic cues that improve its confidence in classifying the entity. Azure Cognitive Service for Language's NER uses a pre-trained model that does not support retraining with custom labels; instead, it relies on surrounding context to disambiguate entities. Adding descriptive terms helps the model leverage its training on patterns where such context correlates with higher confidence scores.

Answer

Retrain the entity recognition model with labeled examples of 'Jane Smith'.

Answer

Use a different language detection model to improve entity recognition.

Answer

Decrease the confidence threshold to 0.3 to include 'Jane Smith' as a valid entity.

Question 5

A large retail company deploys a custom text classification model using Azure Cognitive Service for Language to categorize customer support tickets into 'Billing', 'Technical', and 'General' categories. The model is trained on 10,000 labeled tickets from the past year. After deployment, the model performs well on new tickets but shows a significant drop in accuracy for tickets submitted during holiday seasons, where the volume of billing issues spikes. The engineering team suspects concept drift. They need to maintain high accuracy without manual retraining every season. Which action should the engineer take?

Accepted Answer

Enable active learning on the model and set up a human review loop for low-confidence predictions.. Active learning in Azure Cognitive Service for Language automatically identifies low-confidence predictions and sends them for human review, creating a continuous feedback loop that adapts to concept drift without manual retraining. This allows the model to improve its accuracy on seasonal billing spikes by learning from newly labeled examples, while the human review loop ensures quality control.

Answer

Add subcategories to the classification schema to better capture seasonal patterns.

Answer

Increase the number of training examples per category to 15,000 each.

Answer

Schedule monthly retraining using the original 10,000 tickets plus the new tickets.

Question 6

A company uses this skillset in an Azure AI Search enrichment pipeline. They notice that the enrichment pipeline fails when processing a document larger than 5000 characters. What is the most likely cause?

Accepted Answer

The output field mapping is missing or incorrect. The enrichment pipeline fails because the output field mapping is missing or incorrect. When a skillset processes documents, the output of each skill must be explicitly mapped to an index field; if this mapping is absent or misconfigured, the pipeline cannot store the enriched data and fails, especially for larger documents that produce more output data.

Answer

The maximum page length is too small

Answer

The default language code is not supported

Answer

The text split mode should be 'sentences'

Question 7

A healthcare organization uses Azure Document Intelligence to process patient intake forms. They notice that the confidence scores for field extraction are low. What is the most likely cause?

Accepted Answer

The custom model was trained with only 10 labeled forms. Custom models in Azure Document Intelligence require a minimum of five labeled forms for training, but low confidence scores typically indicate insufficient training data. With only 10 labeled forms, the model lacks enough examples to generalize well across variations in handwriting, formatting, and field values, leading to poor extraction confidence.

Answer

The document resolution is too low

Answer

The document layout is not analyzed

Answer

The batch processing size is too large

Question 8

A company uses Azure Document Intelligence to extract data from invoices. They deploy the model to a container for on-premises processing. After deployment, they notice that the container consumes more memory than expected. What should they do to optimize memory usage?

Accepted Answer

Set the 'Memory' environment variable to a lower value in the container configuration. Option A is correct because Azure Document Intelligence containers expose a 'Memory' environment variable that allows you to limit the container's memory allocation. By setting this variable to a lower value, you constrain the container's memory usage, which directly addresses the issue of higher-than-expected consumption. This is the recommended approach for optimizing memory in containerized deployments.

Answer

Use the 'Read' model instead of the 'Layout' model

Answer

Use the cloud API instead of the container

Answer

Reduce the batch size in the client application

Question 9

An organization is deploying a conversational AI solution using Azure OpenAI. They want to ensure the model's responses are grounded in their own knowledge base documents to reduce hallucinations. Which approach should they implement?

Accepted Answer

Integrate Azure Cognitive Search for retrieval-augmented generation (RAG). Option A is correct because Retrieval-Augmented Generation (RAG) with Azure Cognitive Search allows the model to dynamically retrieve relevant chunks from the organization's knowledge base documents at inference time. This grounds responses in authoritative, up-to-date content, directly reducing hallucinations by providing factual context rather than relying solely on the model's parametric memory.

Answer

Fine-tune the model on the knowledge base documents

Answer

Implement Azure AI Content Safety filters

Answer

Use prompt engineering to instruct the model to only use the knowledge base

Question 10

Which TWO actions are required to enable a custom chatbot built with Azure OpenAI to answer questions based on a company's internal PDF documents?

Accepted Answer

Ingest the PDFs into an Azure Cognitive Search index. Option D is correct because Azure Cognitive Search provides the indexing and retrieval capabilities needed to make PDF content searchable. By ingesting PDFs into an Azure Cognitive Search index, the chatbot can perform vector or keyword searches over the extracted text, enabling it to retrieve relevant passages to answer user questions. This is the standard approach for grounding a custom chatbot on proprietary documents without modifying the underlying model.

Answer

Use Azure AI Document Intelligence to extract text from PDFs before indexing

Answer

Deploy Azure AI Content Safety to filter responses

Answer

Fine-tune the GPT model on the PDF content