AI-102 Practice Exam 51 — 20 Questions

Question 1

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?

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

Accepted Answer

Provide more context around the entity in the input text, such as titles or roles.. 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 2

A healthcare organization is building a clinical decision support system that must extract medical entities (e.g., symptoms, diagnoses, medications) from unstructured clinical notes. The solution must be able to detect relationships between entities, such as 'medication X treats symptom Y'. Which Azure AI service should be used?

Accepted Answer

Azure AI Language - Custom NER with entity linking. Azure AI Language's Custom Named Entity Recognition (NER) with entity linking allows training a model to extract domain-specific medical entities such as symptoms, diagnoses, and medications from unstructured clinical notes. Entity linking connects these entities to a knowledge base (e.g., UMLS), which contains structured relationships between medical concepts, enabling the inference of relationships like 'medication X treats symptom Y'. Thus, Custom NER with entity linking is the appropriate service for both entity extraction and relationship detection.

Answer

Azure AI Translator

Answer

Azure AI Speech-to-Text

Answer

Azure AI Document Intelligence (formerly Form Recognizer)

Question 3

You are building a solution to extract key information from invoices using Azure AI Document Intelligence. The invoices contain fields such as invoice number, date, total amount, and line items. However, the model is not correctly extracting the line items. Which prebuilt model should you use?

Accepted Answer

Prebuilt-invoice model. The prebuilt-invoice model is specifically trained to extract key fields from invoices, including invoice number, date, total amount, and line items. Unlike other prebuilt models, it has dedicated field extraction for line item details such as description, quantity, unit price, and total, making it the correct choice for this scenario.

Answer

Prebuilt-receipt model

Answer

Prebuilt-idDocument model

Answer

Prebuilt-layout model

Question 4

Your company wants to build a custom generative AI model that generates architectural designs. The model should be trained on the company's proprietary dataset of floor plans and designs. Which Azure service should you use?

Accepted Answer

Azure Machine Learning. Azure Machine Learning is the correct service because it provides a comprehensive platform for training custom generative AI models using your own proprietary datasets. It supports deep learning frameworks like PyTorch and TensorFlow, enabling you to build, train, and deploy a custom generative model for architectural designs, whereas Azure OpenAI Service is limited to pre-trained models and fine-tuning, not custom training from scratch.

Answer

Azure OpenAI Service

Answer

Azure AI Vision

Answer

Azure AI Document Intelligence

Question 5

A healthcare organization uses Custom Vision to classify X-ray images. They have a small dataset of 200 images per class. Which strategy will most likely improve model accuracy?

Accepted Answer

Use data augmentation and transfer learning with a pre-trained model.. Data augmentation artificially expands the small dataset (200 images per class) by applying transformations like rotation, scaling, and flipping, which helps the model generalize better. Transfer learning with a pre-trained model (e.g., ResNet or EfficientNet) leverages features learned from large datasets like ImageNet, allowing the Custom Vision model to achieve higher accuracy with limited data.

Answer

Reduce the image dimensions to speed up training.

Answer

Add more negative samples to the dataset.

Answer

Increase the number of training iterations significantly.

Question 6

A company is using Azure OpenAI Service to power a customer support agent. The agent sometimes generates incorrect information when it cannot find an answer in the knowledge base. The team wants to ensure the agent only responds using information from the knowledge base and explicitly states when it does not know the answer. Which configuration should the team use?

Accepted Answer

Use 'use your own data' feature with strict content filtering and set the model to only respond based on retrieved documents.. The 'use your own data' feature in Azure OpenAI Service allows you to restrict the model to answer only from the retrieved documents, ensuring responses are grounded in the knowledge base. Strict content filtering further prevents the model from generating unverified information, and the explicit setting to respond based solely on retrieved documents directly addresses the requirement to state when it does not know the answer.

Answer

Use a custom model fine-tuned on the knowledge base and disable content filtering.

Answer

Use a system message that says 'If you don't know, say you don't know' and rely on the model's training.

Answer

Use prompt engineering with a system message that instructs the model to only answer from the knowledge base, with no additional filtering.

Question 7

You are designing an enterprise search solution using Azure AI Search. The solution must index data from multiple sources: SQL Database, SharePoint Online, and custom REST APIs. The search index must support faceted navigation and filtering by metadata such as department and document type. You also need to ensure that updates to source data are reflected in the index within 5 minutes. Which approach should you use?

Accepted Answer

Configure indexers for SQL and SharePoint, and use the push API for the REST API. Schedule indexers to run every 5 minutes.. It combines the strengths of indexers (for SQL Database and SharePoint Online, which have native connectors) with the push API for custom REST APIs, which lack a built-in indexer. Scheduling the indexers to run every 5 minutes ensures that updates are reflected within the required latency window, while the push API can be triggered on demand or via a polling mechanism to meet the same 5-minute SLA.

Answer

Use the push API to index all data from a custom application that polls all sources.

Answer

Create a single indexer that reads from all three sources using a data source definition.

Answer

Use only indexers for all sources by creating a custom indexer for the REST API.

Question 8

You are deploying a conversational AI solution using Microsoft Copilot Studio. The solution must provide responses based on data from an internal knowledge base stored in SharePoint. Which feature should you configure?

Accepted Answer

Enable Generative Answers and add SharePoint as a data source.. Microsoft Copilot Studio natively supports Generative Answers, which allows the AI to dynamically generate responses from specified data sources without requiring a separate QnA or custom question-answering service. By adding SharePoint as a data source, the solution can directly query the internal knowledge base stored in SharePoint and produce contextually relevant answers. This is the most straightforward and integrated approach within Copilot Studio for this scenario.

Answer

Configure Azure AI Language with custom question answering.

Answer

Create an Azure Bot Service with a QnA Maker knowledge base.

Answer

Use Azure OpenAI Service with data integration (Bring Your Own Data).

Question 9

A company is building a chatbot using Azure OpenAI Service to handle customer inquiries. The bot sometimes responds with incorrect or fabricated information. The team wants to ground the model responses using their own product documentation stored in Azure Cognitive Search. Which configuration should they implement?

Accepted Answer

Configure Azure OpenAI on your data with Azure Cognitive Search as the data source.. It directly integrates Azure Cognitive Search as a data source for Azure OpenAI, enabling the model to retrieve and ground its responses in the indexed product documentation. This approach uses a 'retrieve-then-read' pattern where the search results are injected into the prompt, reducing hallucinations by constraining the model's output to verified content.

Answer

Use Azure AI Document Intelligence to extract text and generate embeddings, then store them in a vector database for direct similarity search.

Answer

Fine-tune the GPT model on the product documentation dataset.

Answer

Enable the semantic ranker in Azure Cognitive Search to improve the relevance of search results.

Question 10

Your organization runs a popular news website. You want to use Azure AI Language to automatically generate summaries of news articles for the homepage. The summaries must be concise (under 100 words), extractive (selecting key sentences from the article), and available in both English and Spanish. You have a large corpus of articles in both languages. You need to implement a solution that requires minimal custom development and leverages Azure AI Language's prebuilt capabilities. Which approach should you take?

Accepted Answer

Use the prebuilt extractive summarization API in Azure AI Language for both languages, specifying the maximum summary length.. The prebuilt extractive summarization API in Azure AI Language natively supports both English and Spanish, can generate summaries under 100 words by specifying the maximum summary length, and requires no custom development. This directly meets the requirements for concise, extractive summaries with minimal effort.

Answer

Train a custom extractive summarization model using Azure AI Language's custom text summarization feature with labeled data in both languages.

Answer

Use the conversation summarization API to summarize each article.

Answer

Use the prebuilt abstractive summarization API to generate summaries.

Question 11

Which THREE are required when planning to use Azure OpenAI Service for a generative AI application that must comply with responsible AI principles?

Accepted Answer

Implement content filters to block harmful outputs.. Azure OpenAI Service provides built-in content filtering that can block harmful outputs such as hate speech, violence, or self-harm. This is a core requirement for responsible AI compliance, as outlined in Microsoft's Responsible AI Standard, and must be configured to prevent the model from generating unsafe content.

Answer

Restrict the model to a maximum of 1000 tokens.

Answer

Enable rate limiting to prevent abuse.

Question 12

Your team is building an application that uses Azure OpenAI Service to summarize legal documents. You need to ensure that the summaries do not include any personally identifiable information (PII) that might appear in the source documents. Which feature should you configure in the Azure OpenAI Service?

Accepted Answer

Enable content filtering with PII detection.. Azure OpenAI Service's content filtering system includes built-in PII detection capabilities that can automatically identify and redact personally identifiable information from model inputs and outputs. This feature operates at the platform level, ensuring PII is filtered regardless of how the model is prompted, providing a reliable safeguard for sensitive legal documents.

Answer

Configure rate limiting to reduce processing volume.

Answer

Set the system message to instruct the model to exclude PII.

Answer

Use the 'Add your data' feature to ground the model.

Question 13

A developer is deploying a custom text classification model in Azure AI Language. The model must be accessible via a REST API with low latency. Which TWO actions should the developer take?

Accepted Answer

Obtain the endpoint URL and primary key from Language Studio. The endpoint URL and primary key are required to authenticate and route REST API requests to the deployed model. Language Studio provides these credentials after the model is deployed to a real-time endpoint, enabling low-latency inference via the Azure AI Language API.

Answer

Use the batch processing API

Answer

Export the model as a Docker container

Answer

Deploy to a test endpoint in the Azure portal

Question 14

You are implementing a RAG (Retrieval-Augmented Generation) solution using Azure AI Search and Azure OpenAI Service. The solution is returning answers that are not relevant to the user query. What is the most likely cause?

Accepted Answer

The relevance score threshold is set too low.. A low relevance score threshold in Azure AI Search allows documents with low semantic or vector similarity to be returned as results. When these poorly matched documents are passed to Azure OpenAI Service for answer generation, the model may produce answers that are not relevant to the user query, as the retrieved context is noisy or unrelated.

Answer

The max_tokens parameter is set too high.

Answer

The chunk size is too small.

Answer

The index includes too many documents.

Question 15

You are designing a solution that uses Azure AI Vision to analyze images for moderation. The solution must detect adult content and identify text in images. You need to minimize latency and cost. Which approach should you recommend?

Accepted Answer

Call the Analyze Image API with the 'adult' and 'read' visual features. The Analyze Image API in Azure AI Vision supports multiple visual features in a single call, including 'adult' for adult content detection and 'read' for OCR (text extraction). This minimizes latency by avoiding multiple API calls and reduces cost since you are billed per API call, not per feature.

Answer

Call the Analyze Image API twice: once for adult content and once for OCR

Answer

Use the Computer Vision 3.2 API with the 'adult' and 'OCR' parameters

Answer

Use the Read API for text and the Content Moderator API for adult content

Question 16

Which THREE components are required to build a knowledge mining solution using Azure AI Search that extracts and enriches content from PDF files?

Accepted Answer

Skillset. To build a knowledge mining solution that extracts and enriches content from PDF files using Azure AI Search, three components are required: a data source (to connect to the PDFs), a skillset (to apply AI enrichment like OCR and entity extraction), and an indexer (to orchestrate the pipeline and ingest the enriched content into the index). While an index is also necessary to store the results, it is not considered a pipeline component in the same context, and the question asks for the three components of the extraction and enrichment pipeline.

Answer

Index

Answer

Semantic configuration

Question 17

A multinational corporation uses Azure AI Language to analyze customer feedback in multiple languages. The solution must detect the language of incoming text and then perform sentiment analysis. Which approach minimizes latency and cost?

Accepted Answer

Call the language detection API followed by the sentiment analysis API. The requirement is to detect the language of incoming text and then perform sentiment analysis. The sentiment analysis API in Azure AI Language does not detect language; it requires the language to be specified. Therefore, you must first call the language detection API to identify the language, then pass that language code to the sentiment analysis API. While this involves two API calls, it is still more efficient than translating text (Option B) which adds significant latency and cost, or using cognitive skills with Azure AI Search (Option C) which adds indexing overhead. Option A is wrong because the sentiment analysis API cannot detect language on its own; it requires the language as an input parameter. Thus, Option D minimizes latency and cost by only performing the necessary steps without unnecessary transformations.

Answer

Use the sentiment analysis API with multilingual support

Answer

Use the Translator service to translate text to English, then call sentiment analysis

Answer

Store text in Azure AI Search and use cognitive skills for sentiment

Question 18

Match each Azure AI concept to its description.

Accepted Answer

Azure AI Perception: Processes visual and auditory data to understand the world. The correct matches pair each Azure AI concept with its primary function. Common confusions occur between Perception and Content Safety (both deal with content analysis) and between Decision and Communication (both involve interaction but different purposes).

Answer

Azure AI Perception: Detects and monitors offensive or risky content

Answer

Azure AI Decision: Creates conversational agents and speech-based interactions

Question 19

Match each Azure AI tool to its purpose.

Accepted Answer

Azure Cognitive Search: AI-powered cloud search service for indexing and querying diverse content.. Correct matches: Azure Cognitive Search is an AI search service; Azure Bot Service is for building bots; Azure Cognitive Services offers pre-built AI APIs. Common confusions include swapping Cognitive Search with Machine Learning, and Bot Service with Cognitive Services.

Answer

Azure Cognitive Search: Platform for building, training, and deploying machine learning models.

Answer

Azure Bot Service: Pre-built APIs for vision and speech.

Answer

Azure Cognitive Services: Tools to build and manage bots.

Question 20

You are building a multilingual chatbot using Azure AI Language. The chatbot must handle English, Spanish, and French. You need to configure the LUIS (Language Understanding) model to support multiple languages efficiently. What is the best practice?

Accepted Answer

Create a separate LUIS app for each language and use the same intents and entities structure.. LUIS does not support a single multilingual model; each LUIS app is designed for a single primary language. To handle multiple languages efficiently, you must create a separate LUIS app per language, each with the same intent and entity schema, and route user queries to the appropriate app based on the detected language. This ensures optimal language-specific model training and accuracy.

Answer

Use the prebuilt multilingual LUIS model and fine-tune it with your intents.

Answer

Create a single LUIS app and add utterances in all three languages.

Answer

Create one LUIS app with language set to 'Multilingual' and add utterances in all languages.