AI-103 Practice Test 19 — 15 Questions

Question 1

You are tuning the prompt for a generative AI application in Azure AI Foundry. The model frequently hallucinates when asked complex multi-part questions. You decide to use chain-of-thought (CoT) prompting. How should you structure the prompt to implement CoT effectively?

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

Accepted Answer

Instruct the model to think step-by-step and show its intermediate reasoning before providing the final answer. Chain-of-thought prompting works by instructing the model to reason step-by-step and show intermediate reasoning before the final answer. This decomposition reduces hallucination on multi-part questions because the model is forced to work through each part logically rather than jumping to a conclusion. The prompt should explicitly ask for step-by-step thinking.

Answer

Set the model seed parameter to a fixed integer value for reproducibility

Answer

Reduce the maximum completion token limit to 150 tokens

Answer

Instruct the model to output its response exclusively in JSON format with strict schema validation

Question 2

When designing an agentic workflow in Azure AI Foundry, which component is used to manage the execution order and decision-making logic of multiple agents?

Accepted Answer

Orchestrator. The orchestrator component in Azure AI Foundry manages the execution order and decision-making logic of multiple agents. It coordinates tasks, routes requests, and determines which agent acts next based on the workflow. This is essential for building complex agentic systems.

Answer

Vector Index

Answer

Model Catalog

Answer

Prompt Template

Question 3

You are implementing a tool call in a Prompt Flow. The tool needs to interact with an external REST API. What is the recommended way to manage the API credentials securely?

Accepted Answer

Use an Azure AI Foundry Connection of type Custom. Azure AI Foundry Connections of type Custom are the recommended way to store and manage credentials for external services such as REST APIs. A Custom connection securely stores the API key or token in the Foundry workspace, and the Prompt Flow tool references the connection by name, so credentials are never exposed in code or prompts. This integrates with Azure RBAC and Key Vault for secure secret storage.

Answer

Pass the key as a parameter in the input prompt

Answer

Hardcode the API key in the Prompt Flow code

Answer

Use an environment variable in the flow definition

Question 4

What is the primary purpose of the 'selection marks' detection in the layout model?

Accepted Answer

To detect checkboxes and radio buttons. Selection marks in Azure AI Document Intelligence's layout model detect and extract checkboxes and radio buttons (and their selected/unselected state) from documents. The model returns each mark with a confidence score and a state of 'selected' or 'unselected', which is essential for processing forms, surveys, and questionnaires. OCR, table borders, and signatures are handled by other capabilities.

Answer

To OCR printed text

Answer

To identify table borders

Answer

To find handwritten signatures

Question 5

You need to ensure that an AI model deployment is resilient to regional outages. What should you implement?

Accepted Answer

Azure Front Door with regional endpoints.. Azure Front Door is a global Layer 7 load balancer and CDN that can route traffic across multiple regional AI endpoints, performing health probes and automatic failover if a region becomes unavailable. By fronting regional endpoints with Front Door, the deployment remains reachable even during a regional outage. This is the standard Azure pattern for cross-region resiliency of HTTP-based AI inference services.

Answer

A single large VM.

Answer

Azure Storage redundancy.

Answer

Local VNET peering.

Question 6

You are building an application that analyzes user feedback. You need to detect instances where users share their phone numbers, email addresses, and credit card numbers so that you can automatically redact them. Which feature should you use?

Accepted Answer

PII detection. PII detection in Azure AI Language is specifically designed to identify and redact personally identifiable information such as phone numbers, email addresses, and credit card numbers. It returns the detected entities along with their categories and confidence scores, enabling automatic redaction. This is the exact feature needed for the scenario.

Answer

Sentiment analysis

Answer

Language detection

Answer

Named Entity Recognition (NER)

Question 7

Which TWO of the following are valid Document Intelligence project types in the Studio?

Accepted Answer

Custom extraction. In Azure AI Document Intelligence Studio, the two valid project types are Custom extraction (B) and Custom classification (D). Custom extraction lets you build a model that pulls specific fields (key-value pairs, tables, entities) from documents using labeled samples, which is the core 'custom form'/'custom extraction' capability of Document Intelligence. Custom classification lets you train a model to categorize incoming documents into user-defined classes, a distinct project type also supported in the Studio. The other options do not belong: Speech-to-text (A) is an Azure AI Speech capability, Sentiment analysis (C) is an Azure AI Language feature, and Face detection (E) is part of Azure AI Vision—none of these are Document Intelligence project types.

Answer

Speech-to-text

Answer

Sentiment analysis

Answer

Face detection

Question 8

Your application uses the Azure AI Document Intelligence Prebuilt Receipt model to process customer receipts. A receipt contains a custom tip amount that is not explicitly categorized by the default prebuilt schema. How should you extract this custom value?

Accepted Answer

Use the Prebuilt Layout model alongside custom regex rules or train a Custom model to capture the custom tip field.. Prebuilt models expose a fixed schema and cannot be extended via request parameters or portal edits. To capture a field outside that schema (like a custom tip), you either use the Layout model to get raw text/lines and apply your own extraction logic (e.g., regex), or train a Custom extraction model with labeled samples that include the tip field. Option D describes both valid paths.

Answer

Call the Azure OpenAI service directly with the raw image to guess the tip amount.

Answer

Pass a custom JSON schema parameter in the Prebuilt Receipt API request body to extend its extraction fields.

Answer

Modify the prebuilt receipt model schema directly in the Azure Portal to add a new required field.

Question 9

You are developing a .NET application that extracts bounding boxes of text from scanned documents using Azure AI Vision 4.0. Which asynchronous API operation should you call first to initiate the OCR process?

Accepted Answer

POST /computervision/imageanalysis:analyze?api-version=2024-02-01. The Azure AI Vision 4.0 Image Analysis analyze endpoint is POST /computervision/imageanalysis:analyze with api-version=2024-02-01, and it supports the 'read' feature for OCR with bounding boxes. This is the correct modern endpoint for initiating asynchronous OCR in the 4.0 API surface.

Answer

POST /vision/v3.2/ocr

Answer

POST /vision/v2.1/recognizeText

Answer

POST /customvision/v3.3/Prediction

Question 10

You are migrating an existing solution from the legacy Text Analytics API v3.1 to the current Azure AI Language REST API. You notice changes in the JSON request body structure. Where should the document text array now be nested in the payload for a sentiment analysis request?

Accepted Answer

Nested inside an 'analysisInput' object under the root.. In the current Azure AI Language REST API (formerly Text Analytics), the request body for sentiment analysis nests the documents array inside an 'analysisInput' object at the root. The structure is: { "analysisInput": { "documents": [ { "id": "1", "text": "...", "language": "en" } ] }, "parameters": { ... } }. This change from the legacy v3.1 API, where documents were directly under the root, reflects a more organized payload with separate sections for input and parameters.

Answer

Inside the HTTP header as a base64 encoded string.

Answer

Directly under the root object as a 'documents' array.

Answer

Nested inside a 'parameters' object.

Question 11

You need to extract key concepts and main ideas from long-form technical support articles using the Azure AI Language service. Which feature should you invoke?

Accepted Answer

Key phrase extraction. Key phrase extraction is the Azure AI Language feature designed to identify the main concepts and important terms from unstructured text. It analyzes the text and returns a list of key phrases that represent the core ideas, making it ideal for extracting key concepts from long-form technical support articles. Summarization, while related, produces a condensed version of the text rather than a list of key phrases, and is typically used for creating abstracts or summaries. Therefore, key phrase extraction directly fulfills the requirement to extract key concepts and main ideas.

Answer

Personal Personally Identifiable Information (PII) detection

Answer

Language detection

Answer

Summarization

Question 12

You are processing medical intake forms using Azure AI Language. You need to identify and categorize medical terms, medications, and dosages. Which feature should you use?

Accepted Answer

Health text analytics. Health text analytics in Azure AI Language is specifically designed for the medical domain and can identify medical entities such as medications, dosages, diagnoses, and symptoms. It goes beyond generic NER by recognizing healthcare-specific terminology and relationships. This makes it the correct choice for processing medical intake forms where medications and dosages must be categorized.

Answer

Key phrase extraction

Answer

Standard Named Entity Recognition (NER)

Answer

Custom text classification

Question 13

You are training a Custom Vision object detection model. You have 1,000 images, but only 200 of them contain the rare object you want to detect. The other 800 images are background images without the object. What impact will this class imbalance have on training, and how should you address it?

Accepted Answer

Ensure that you have tagged at least 15 bounding boxes per tag; having background images is beneficial for reducing false positives.. Custom Vision object detection requires a minimum of 15 tagged bounding boxes per tag for a tag to be trainable, and background (negative) images are explicitly beneficial because they teach the model what the object is not, reducing false positives. With only 200 positive images, keeping the 800 backgrounds provides valuable negative examples. The correct guidance is to ensure sufficient tagged instances while retaining background images.

Answer

Reduce training iteration time to 1 minute.

Answer

Convert the project to multilabel classification.

Answer

Delete all 800 background images immediately, as they will cause training to fail.

Question 14

Which TWO of the following are valid ways to provide context to an agent in Prompt Flow?

Accepted Answer

Passing conversation history as part of the messages list. Option B is correct because Prompt Flow agents accept a messages list in which prior user/assistant turns are included, so passing conversation history as part of that messages list supplies the dialogue context the agent needs to resolve references and maintain continuity. Option C is correct because injecting retrieved documents into the prompt template (the retrieval-augmented generation pattern, e.g., via a vector index lookup node whose output is bound into the prompt) places relevant grounding text directly in the model's context window. Option A is wrong because region selection only affects data residency, latency, and model availability, not the contextual information given to the agent. Option D is wrong because increasing the model output length (max_tokens) only changes how many tokens can be generated, not what context is provided. Option E is wrong because training a new model changes weights rather than supplying runtime context, and it is not a Prompt Flow context-injection mechanism.

Answer

Deploying the model in a different region

Answer

Increasing the model output length

Answer

Training a new model on the context

Question 15

You are managing an Azure AI Search service with multiple replicas and partitions. During peak query hours, latency increases significantly, and CPU utilization on the search service hits 95%. You need to scale the service to improve query throughput without altering the index data schema. Which scaling action should you take?

Accepted Answer

Increase the number of search replicas in the Azure portal or via CLI.. Adding replicas increases the number of copies of the index that can serve queries, directly improving query throughput and distributing CPU load across more nodes. Since the issue is high query CPU utilization and latency during peak hours, scaling replicas is the correct horizontal scale-out for read/query performance.

Answer

Increase the number of search partitions.

Answer

Disable semantic ranking to reduce compute overhead.

Answer

Migrate the service to the Free pricing tier.