AI-102 Practice Test 45 — 15 Questions

Question 1

A company uses Azure Document Intelligence with a custom neural model to extract data from purchase orders. The model was trained on 50 labeled samples and performs well on similar documents. However, when processing new purchase orders from a different supplier, the model fails to extract the 'TotalAmount' field accurately. What should you do to improve the model's performance on the new supplier's documents?

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

Accepted Answer

Add labeled samples from the new supplier's purchase orders and retrain the model.. To improve extraction for documents from a new supplier, the custom neural model needs exposure to that supplier's document variations. Adding labeled samples and retraining is the direct method to enhance the model's field extraction accuracy. Other options do not address the model's knowledge gap.

Answer

Increase the model's confidence threshold for the 'TotalAmount' field.

Answer

Use the model's composed model feature to combine it with a prebuilt model.

Answer

Switch to the prebuilt invoice model and map the 'TotalAmount' field to 'InvoiceTotal'.

Question 2

You are planning to deploy an Azure AI Services multi-service resource. You need to ensure that the resource can be used by applications running in an Azure Kubernetes Service (AKS) cluster without embedding keys in the application code. What should you do?

Accepted Answer

Configure Azure AD Pod Identity or Workload Identity for the AKS cluster and assign the Cognitive Services User role to the identity on the Azure AI Services resource.. To enable keyless authentication for applications in AKS, you should use Microsoft Entra ID Workload Identity (or Pod Identity) to associate a managed identity with the pods. That identity must be granted the Cognitive Services User role on the Azure AI Services resource. The application can then use DefaultAzureCredential to obtain a token and call the service without any keys.

Answer

Store the Azure AI Services key in a Kubernetes secret and mount it as an environment variable in the application pods.

Answer

Enable a system-assigned managed identity on the AKS cluster and assign the Cognitive Services User role to it on the Azure AI Services resource.

Answer

Use Azure Key Vault to store the Azure AI Services key and retrieve it at runtime by using the AKS cluster's managed identity.

Question 3

You are designing a generative AI assistant that must produce deterministic, repeatable answers for a compliance workflow. The assistant uses Azure OpenAI chat completions and must return the same output for identical prompts. Which parameter setting should you apply?

Accepted Answer

Set temperature to 0 and top_p to 1.. Deterministic output requires minimizing sampling randomness. Temperature 0 selects the most probable token each step, and top_p 1 disables nucleus truncation, so identical inputs produce nearly identical outputs. Creative temperatures, penalties, or length and streaming controls do not provide repeatability and can introduce variation across runs.

Answer

Set frequency_penalty to 2 and presence_penalty to 2.

Answer

Increase the max_tokens value and enable streaming responses.

Answer

Set temperature to 1 and top_p to 0.95.

Question 4

You are planning to deploy an Azure AI solution that uses Azure AI Language to analyze text. The solution must be able to process a high volume of requests and provide a service-level agreement (SLA) for availability. You need to choose the appropriate pricing tier. What should you do?

Accepted Answer

Use the Standard (S) tier for the Azure AI Language resource.. The Standard tier is designed for production workloads, offering higher throughput limits and an SLA. The Free tier is for evaluation only and lacks an SLA. Therefore, the Standard tier is necessary to meet the high-volume and availability requirements.

Answer

Use the Free (F0) tier for each Azure AI Language resource to minimize costs.

Answer

Use the Standard (S) tier only for development and switch to Free (F0) for production to save costs.

Answer

Use multiple Free (F0) resources and load-balance requests across them.

Question 5

You are building a solution that must summarize long documents in real time as they are uploaded to Azure Blob Storage. The summaries must be concise and capture the main points. You want to use Azure AI Language. Which feature should you use?

Accepted Answer

Abstractive summarization. Abstractive summarization in Azure AI Language generates new, concise sentences that capture the main ideas of a document. It is designed for producing brief summaries and is available as a real-time API. Extractive summarization selects existing sentences, which may be less concise. Key phrase extraction and NER provide different types of analysis and do not generate summaries.

Answer

Extractive summarization

Answer

Key phrase extraction

Answer

Named entity recognition (NER)

Question 6

A retail company wants to build a knowledge mining solution that indexes product descriptions stored in an Azure SQL Database and makes them searchable through a web application. The descriptions are already plain text. You need to configure Azure AI Search to pull the data into an index with the least effort. What should you create first?

Accepted Answer

An indexer with a data source connection to Azure SQL Database.. Azure AI Search integrates directly with Azure SQL Database through indexers and data source connections. When the source content is already plain text, the indexer can read rows and populate the index without any enrichment skills. This is the least-effort approach and avoids custom code or document extraction models.

Answer

A cognitive skillset that applies OCR to each product description.

Answer

A custom skill that queries the SQL database and writes documents to the index.

Answer

An Azure AI Document Intelligence model trained on the product descriptions.

Question 7

You have a Conversational Language Understanding (CLU) project in Azure AI Language. Users frequently type utterances such as 'Book a flight from Seattle to Tokyo next Friday for two people.' The solution must extract the origin city, destination city, date, and passenger count as separate structured values so the booking system can act on them. You need to configure the project to capture these values. What should you do?

Accepted Answer

Add entities to the project and label them in the training utterances, using prebuilt entities where available.. In Conversational Language Understanding, entity extraction depends on defining entities and labeling their occurrences in training utterances. Adding entities for the four values and labeling them, using prebuilt components such as geography and number where applicable, enables the model to return those values as structured fields for the booking system.

Answer

Add more intents and assign each utterance to a single intent.

Answer

Enable sentiment analysis and opinion mining on the CLU project.

Answer

Increase the training data by duplicating existing utterances with slight wording changes.

Question 8

A retailer wants to analyze thousands of product reviews per day and needs to know which aspects of the products customers mention, such as battery life or screen quality, and whether sentiment toward each aspect is positive or negative. The reviews are already stored as text in an Azure SQL Database. Which Azure AI Language feature should you use?

Accepted Answer

Opinion mining with sentiment analysis on the analyze-text endpoint. Opinion mining, exposed as an extension of sentiment analysis on the analyze-text endpoint, returns aspect-level targets with individual sentiment labels and confidence scores. That output maps directly to the retailer's need to know which product aspects are mentioned and whether sentiment toward each is positive or negative, without the labeling overhead of a custom classification project.

Answer

Custom text classification with a project trained on labeled reviews

Answer

Document-level sentiment analysis with the default opinionMining setting disabled

Answer

Key phrase extraction on each review to list the most frequent terms

Question 9

You are building an Azure AI Language solution that analyzes customer support emails. You need to detect the language of each email before routing it to the correct translation pipeline. You call the Language Detection API with the following request body: {"kind": "LanguageDetection", "analysisInput": {"documents": [{"id": "1", "text": "Bonjour, je besoin d'aide avec mon compte."}]}}. What will the response contain?

Accepted Answer

A single document result with the detected language code 'fr', a confidence score, and the original text with offsets.. The Language Detection API returns the detected language code, confidence score, and text metadata for each document. It does not return all languages, translated text, or errors for common punctuation. The correct response includes the ISO code 'fr' and a confidence score, which you can use to route the email appropriately.

Answer

The translated version of the text in English, because the default target language is English.

Answer

A list of all supported languages with confidence scores for each, allowing you to select the highest-scoring language.

Answer

An error because the text contains an apostrophe, which is not supported in the JSON payload.

Question 10

You are using Azure AI Language's custom question answering feature. Your knowledge base contains 500 FAQ pairs. Users report that the bot returns irrelevant answers when their questions are phrased differently from the stored FAQs. You want to improve the bot's ability to match paraphrased questions without retraining a full model. Which action should you take?

Accepted Answer

Add alternative question phrasings to each FAQ pair in the knowledge base.. Custom question answering learns from the question-answer pairs and their alternative phrasings. Adding alternative questions provides the model with more surface forms of the same intent, which improves semantic matching for paraphrased user queries without requiring a separate model training process.

Answer

Enable the 'chit-chat' personality in the project settings to make responses more conversational.

Answer

Increase the confidence threshold in the project settings to filter low-scoring answers.

Answer

Switch the project to use a custom text classification model instead of question answering.

Question 11

You are building a solution that uses Azure AI Language to analyze transcribed call-center conversations. The transcripts are stored as plain text in Azure Blob Storage. You need to identify the specific products, dates, and monetary amounts mentioned in each conversation while distinguishing them from generic nouns. You also need to return the character offset and length for each detected mention so the UI can highlight them. Which Azure AI Language feature should you use?

Accepted Answer

Named Entity Recognition (NER). Named Entity Recognition in Azure AI Language is designed to detect entity categories such as Product, DateTime, and Quantity and to return each mention with its offset and length. Those offsets allow the application to highlight exact spans in the transcript, and the category labels let developers filter products from dates and amounts.

Answer

Key Phrase Extraction

Answer

Extractive Summarization

Answer

Conversation Summarization

Question 12

Your team is building a generative AI application on Azure OpenAI that must call an internal order-lookup REST API whenever a user asks about an order status. The model must decide when to call the API, and the application must execute the call and return the result to the model for the final answer. Which capability should you implement?

Accepted Answer

Function calling (tools) on the chat completions request, defining the order-lookup API as a tool.. The requirement is a model-driven decision to invoke a live REST API and then incorporate the returned data. Function calling provides exactly that contract: tools are declared, the model emits a structured call, the host application performs the HTTP request, and the result is fed back for final generation. The other options either constrain formatting, rely on training data, or only rank search results.

Answer

Semantic ranker enabled on an Azure AI Search index that stores order records.

Answer

A system message instructing the model to answer order questions only from its training data.

Answer

A JSON mode response format that forces the model to emit a schema-conforming order status object.

Question 13

You are creating an Azure AI Search index that will be populated from an enrichment pipeline. You need to ensure that the original content of each document is searchable. Which index field should you map the document content to?

Accepted Answer

A field with the searchable attribute set to true. To make document content searchable, the index field must have the searchable attribute set to true. This enables full-text search capabilities, allowing users to query the content using keywords and phrases. Other attributes like filterable or retrievable serve different purposes and do not provide search functionality. Therefore, mapping content to a searchable field is essential.

Answer

A field with the key attribute set to true

Answer

A field with the retrievable attribute set to true

Answer

A field with the filterable attribute set to true

Question 14

A financial services firm needs to extract structured fields such as invoice date, vendor name, and total amount from thousands of PDF invoices. The documents vary in layout across vendors. The firm wants a pretrained model that requires no custom training and can return field-level confidence scores. Which Azure AI Document Intelligence model should they use?

Accepted Answer

Prebuilt invoice model. The firm needs invoice-specific structured fields with confidence scores and no custom training. The prebuilt invoice model in Azure AI Document Intelligence is designed exactly for that, recognizing common invoice fields across varied layouts. General document, custom template, and Read models either lack invoice-specific fields, require training, or return only raw text.

Answer

Read model

Answer

Custom template model

Answer

General document model

Question 15

A developer is using the Azure AI Vision Image Analysis API to extract text from a photo of a street sign. The sign contains text in both English and Japanese arranged in multiple columns. The developer needs the response to include the detected language and the bounding box for each text line. Which feature should they use?

Accepted Answer

The 'read' feature in Image Analysis. The read feature in Azure AI Vision Image Analysis is specifically designed for OCR. It returns extracted text with bounding boxes for lines and words, and it detects the language of the text. This matches the need to capture English and Japanese text in multiple columns and provide bounding boxes for each line. Other features like caption, detectObjects, and tags do not perform OCR.

Answer

The 'detectObjects' feature in Image Analysis

Answer

The 'caption' feature in Image Analysis

Answer

The 'tags' feature in Image Analysis