AI-102 Practice Test 44 — 15 Questions

Question 1

Refer to the exhibit. You deploy an Azure AI Services multi-service account using this ARM template. After deployment, developers cannot access the service from their local machines. What is the most likely reason?

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

Accepted Answer

The network ACLs block all traffic by default. The ARM template for an Azure AI Services multi-service account includes a `networkAcls` property with `defaultAction` set to `Deny`. This configuration blocks all traffic by default, including requests from developers' local machines, unless an explicit IP rule or virtual network rule is added to allow access. Since no such rules are shown in the exhibit, the network ACLs are the most likely cause of the connectivity failure.

Answer

The location is not specified correctly

Answer

The pricing tier S0 does not support network restrictions

Answer

The custom subdomain name is not globally unique

Question 2

A company is building a chatbot using Azure AI Language. The chatbot must detect user intent from utterances and also extract key entities like dates and product names. The solution must minimize latency for real-time conversation. Which approach should the team use?

Accepted Answer

Use the Conversational Language Understanding (CLU) feature of Azure AI Language, which supports both intent and entity extraction in a single API call.. The Conversational Language Understanding (CLU) feature of Azure AI Language is specifically designed to handle both intent recognition and entity extraction in a single API call, which minimizes latency for real-time conversations. CLU is the modern replacement for LUIS and is optimized for conversational scenarios, supporting orchestration and prebuilt entities like dates and product names.

Answer

Use QnA Maker with a custom question-answer pair for each intent and entity.

Answer

Use the Language Understanding (LUIS) service with a single call for both intent and entity extraction.

Answer

Use two separate calls to the Azure AI Language API: one for intent recognition and one for entity extraction.

Question 3

Refer to the exhibit. You have an Azure AI Search skillset with the custom skill shown. When you run the indexer, you notice that many documents fail with a timeout error. What is the most likely cause of the timeouts?

Accepted Answer

The degreeOfParallelism is set too high, overwhelming the Azure Function.. The custom skill in Azure AI Search is configured with a `degreeOfParallelism` of 10, meaning up to 10 concurrent requests are sent to the Azure Function. If the function cannot handle this level of concurrency (e.g., due to limited resources or cold starts), requests will queue up and eventually time out. Reducing the `degreeOfParallelism` would throttle the load and prevent the function from being overwhelmed.

Answer

The HTTP method should be GET instead of POST.

Answer

The timeout value is too short for the function to complete.

Answer

The batch size is too large, causing each request to process too many documents.

Question 4

Your company has a large set of PDF documents stored in Azure Blob Storage. You need to index these documents in Azure Cognitive Search so that users can search the text content. What is the first step you should take?

Accepted Answer

Create a data source that connects to Azure Blob Storage.. The correct first step is to create a data source that connects to Azure Blob Storage (option C). In Azure Cognitive Search, the indexing pipeline requires a data source definition to specify the location and type of data. After creating the data source, you can then create an index, and finally an indexer to automate the process. Creating a skillset (option B) or an indexer running daily (option D) would come later. Option A is incorrect because the index fields are defined when you create the index, which is not the first step.

Answer

Create an index with a field for each metadata property.

Answer

Create a skillset to extract text from PDFs.

Answer

Create an indexer that runs daily.

Question 5

Refer to the exhibit. You are calling the Azure AI Language API for extractive summarization. What will be the output of this request?

Accepted Answer

The three sentences in the order they appear in the document.. The Azure AI Language API for extractive summarization returns the most relevant sentences from the original document in the order they appear, not reordered by score. The API extracts sentences based on a ranker, but the output preserves the original sentence sequence to maintain readability and context. Option D is correct because the default behavior is to return the extracted sentences in their original order.

Answer

Only the first sentence because the document is short.

Answer

An abstractive summary generated from the text.

Answer

The three sentences ranked by confidence score.

Question 6

Your Azure AI Document Intelligence model is failing to extract tables from scanned PDFs. The PDFs are low-quality images. What should you do first?

Accepted Answer

Verify that the Read OCR step is extracting text correctly.. The Read OCR step is the foundational layer for table extraction in Azure AI Document Intelligence. If the OCR cannot accurately recognize text from low-quality images, subsequent table extraction models will fail regardless of training or image enhancement. Verifying OCR output first isolates whether the issue is at the text recognition stage or the table parsing stage, following a systematic troubleshooting approach.

Answer

Use Azure AI Computer Vision to enhance the image.

Answer

Retrain the model with more table examples.

Answer

Use a higher resolution scanner for input PDFs.

Question 7

A research organization uses Azure AI Language to process large volumes of scientific papers. They need to extract specific entities such as gene names, protein names, and chemical compounds. The entity types are highly specialized and not covered by prebuilt models. The organization has a labeled dataset of 10,000 documents. You need to recommend the most efficient approach to build the entity extraction solution. What should you do?

Accepted Answer

Train a Custom Named Entity Recognition (NER) model using the labeled dataset in Azure AI Language.. Custom Named Entity Recognition (NER) in Azure AI Language allows you to train a model on your own labeled dataset (10,000 documents) to extract highly specialized entity types like gene names, protein names, and chemical compounds that are not covered by prebuilt models. This approach is the most efficient as it leverages the labeled data directly, avoiding the need for complex post-processing or hybrid solutions.

Answer

Use the prebuilt NER model and map the recognized entities to the required types.

Answer

Use Azure Logic Apps to call the Text Analytics API and post-process the results.

Answer

Train a custom NER model for genes and use prebuilt NER for chemicals.

Question 8

A financial services company is building an agent that uses Azure OpenAI to generate investment advice. The agent must be monitored for toxicity and bias. Which combination of services should the team use to implement content safety monitoring?

Accepted Answer

Azure AI Content Safety and Azure OpenAI content filtering.. Azure AI Content Safety provides built-in models for detecting harmful content such as hate speech, self-harm, and sexual content, while Azure OpenAI content filtering applies configurable severity-level filters (e.g., low, medium, high) to model inputs and outputs. Together, they enable real-time monitoring of toxicity and bias in generated investment advice, meeting compliance requirements for financial services.

Answer

Azure Cognitive Search and Azure AI Language.

Answer

Azure Bot Service and Azure Logic Apps.

Answer

Azure Machine Learning and Azure Functions.

Question 9

You are analyzing an image using the Azure AI Vision REST API with the JSON request above. The response includes a description: 'a person holding a smartphone'. However, the response does not include any brand information even though the smartphone is clearly visible. What is the most likely reason?

Accepted Answer

The smartphone brand is not in the Microsoft brand catalog.. The Azure AI Vision API's brand detection feature relies on a predefined Microsoft brand catalog. If the smartphone brand is not included in that catalog, the API will not return brand information even if the brand is clearly visible in the image. The catalog covers major brands but may not include all niche or regional smartphone manufacturers.

Answer

The 'brands' feature was not included in the request.

Answer

The 'model-version' is set to 'latest' which does not support brand detection.

Answer

The API only detects one brand per image, and a different brand was detected.

Question 10

You are developing a solution that uses Azure OpenAI to generate customer support responses. You want to prevent the model from repeating the same phrases. Which parameter should you adjust?

Accepted Answer

frequency_penalty. The frequency_penalty parameter (option D) is correct because it directly reduces the likelihood of the model repeating the same phrases by penalizing tokens that have already appeared in the generated text. A higher frequency_penalty value (e.g., 0.5 to 1.0) decreases the probability of reusing tokens, making the output more diverse and less repetitive. This is specifically designed to address repetition in generative AI responses.

Answer

top_p

Answer

presence_penalty

Answer

temperature

Question 11

Which TWO actions should you take to ensure your Azure AI Language custom question answering project can be used in a production environment with high availability?

Accepted Answer

Enable multiple read replicas for the knowledge base.. Enabling multiple read replicas for the knowledge base in Azure AI Language custom question answering distributes read traffic across replicas, ensuring high availability and fault tolerance. This is a key production requirement to handle concurrent user queries without a single point of failure.

Answer

Disable redundant infrastructure to optimize performance.

Answer

Use the Free (F0) pricing tier to reduce costs.

Answer

Train the model using only a single language.

Question 12

You have an Azure AI Vision resource named MyVisionService. You run the above Azure CLI command and get the keys. Your application uses key1 for authentication. You need to rotate the keys without downtime. What should you do?

Accepted Answer

Update the application to use key2, then regenerate key1. It enables key rotation without downtime. By first updating the application to use key2 (the secondary key), you ensure that authentication continues to work while key1 is being regenerated. After key1 is regenerated, you can optionally update the application back to key1 at a later time. This pattern is standard for Azure Cognitive Services to maintain continuous access.

Answer

Delete and recreate the Cognitive Services resource

Answer

Regenerate key1 immediately and update the application to use the new key1

Answer

Regenerate both keys at the same time

Question 13

Which TWO actions should you take to optimize a custom text classification model in Azure Cognitive Service for Language?

Accepted Answer

Ensure that training examples for different labels do not have overlapping content.. Overlapping content between labels (e.g., the same text appearing in both 'positive' and 'negative' training examples) confuses the custom text classification model, leading to poor decision boundaries. Azure Cognitive Service for Language uses a multi-class or multi-label classifier that learns distinct patterns for each label; overlapping content introduces ambiguity, reducing precision and recall. Ensuring distinct, non-overlapping training examples per label helps the model learn clear, separable features.

Answer

Oversample the minority classes to balance the dataset.

Answer

Remove all stop words from the training data.

Answer

Remove examples with neutral sentiment to focus on positive and negative classes.

Question 14

You are developing a multilingual chatbot that must understand user intents in English, Spanish, and French. You are using the Azure AI Language service with a Conversational Language Understanding (CLU) project. What is the recommended approach to handle multiple languages?

Accepted Answer

Add utterances in all three languages to the CLU project and enable multi-lingual detection.. The Azure AI Language service's Conversational Language Understanding (CLU) supports multi-lingual projects natively. By adding utterances in English, Spanish, and French to a single CLU project and enabling multi-lingual detection, the model learns to recognize intents across languages without needing separate projects or translation steps. This approach leverages the underlying multilingual BERT-based model, which shares language-agnostic representations, making it the recommended and most efficient method.

Answer

Use Azure AI Translator to translate all input to English before sending to CLU.

Answer

Use the Translator service to detect language and route to language-specific CLU endpoints.

Answer

Create separate CLU projects for each language.

Question 15

Your organization is using Azure AI Search with semantic ranking. Users report that search results are not showing relevant documents at the top. You need to improve relevance. What should you configure?

Accepted Answer

Enable semantic search configuration on the index. Semantic search configuration is required to enable semantic ranking, which uses deep learning models to re-rank search results based on contextual relevance rather than just keyword matching. Without this configuration, the index cannot leverage semantic ranking even if the service tier supports it, so enabling it directly addresses the user's complaint about irrelevant documents appearing at the top.

Answer

Add synonyms to the index

Answer

Define a custom scoring profile

Answer

Change the index analyzer to a different language analyzer