AI-102 Plan and manage an Azure AI solution Practice Test 4 — 15 Questions

Question 1

You are responsible for ensuring that an Azure AI solution complies with data residency requirements. The solution processes personal data from users in the European Union. You must ensure that data does not leave the EU region. Which two actions should you take?

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

Accepted Answer

Configure the Azure AI services to disable cross-region replication.. Disabling cross-region replication ensures that data processed by Azure AI services remains within the specified region and is not automatically replicated to another geographic location for redundancy or disaster recovery. This is a critical control for meeting data residency requirements, as it prevents data from leaving the EU region even during failover scenarios.

Answer

Use the global Azure AI services endpoint for simplicity.

Answer

Enable data encryption at rest and in transit.

Answer

Store data in Azure Blob Storage with hot tier.

Question 2

You need to provision an Azure AI Language resource that supports custom text classification. Which pricing tier should you select to use the custom training feature?

Accepted Answer

Standard (S). The Standard (S) tier is the only pricing tier for Azure AI Language that supports custom text classification, including the custom training feature. The Free (F0) tier is limited to pre-built capabilities and cannot be used for training custom models, while Basic (B) and Premium (P) tiers do not exist for this service.

Answer

Free (F0)

Answer

Basic (B)

Answer

Premium (P)

Question 3

You deployed a custom neural voice in Azure AI Speech. The model generates poor prosody for long sentences. What should you do?

Accepted Answer

Re-record the training audio at 24 kHz sample rate.. A custom neural voice model requires high-quality training data. A 24 kHz sample rate is the standard for Azure AI Speech's neural voices, as it captures the full frequency range needed for natural prosody. Re-recording at this rate ensures the model learns proper intonation and rhythm for long sentences, directly addressing the poor prosody issue.

Answer

Switch to a prebuilt neural voice.

Answer

Increase the number of training scripts.

Answer

Use SSML tags to control prosody at runtime.

Question 4

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.. Option A is correct because enabling multiple read replicas for the knowledge base distributes query traffic across replicas, providing redundancy and improving throughput and availability for a production custom question answering project. Option D is correct because deploying the Azure AI Language resource in a region that supports availability zones ensures the service can be spread across physically separate datacenters, protecting against zone-level failures and supporting high availability. Option B is incorrect because disabling redundant infrastructure reduces resilience and directly undermines high availability rather than improving it. Option C is incorrect because the Free (F0) pricing tier has strict quota and throughput limits and is not intended for production workloads. Option E is incorrect because training the model in a single language has no bearing on availability and would actually limit multilingual coverage.

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 5

Which TWO Azure AI services can be used to implement a content moderation pipeline that detects hate speech and blocks violent images?

Accepted Answer

Azure AI Content Safety. Azure AI Content Safety (A) is correct because it is the dedicated Azure service for detecting harmful content such as hate speech, violence, self-harm, and sexual content in both text and images, making it the primary component for a moderation pipeline. Azure AI Vision Image Analysis (E) is correct because its image analysis capabilities can detect violent or otherwise unsafe visual content, which supports the requirement to block violent images. Azure AI Translator (B) only translates text between languages and does not perform moderation. Azure AI Speech to Text (C) transcribes spoken audio and has no hate-speech or violent-image detection role. Azure AI Language sentiment analysis (D) only returns positive/negative/neutral sentiment scores and does not detect hate speech or violent imagery.

Answer

Azure AI Translator

Answer

Azure AI Speech to Text

Answer

Azure AI Language sentiment analysis

Question 6

Refer to the exhibit. The indexer using this skillset fails with an error that the skill cannot be executed. The Azure Function is deployed and responds correctly when tested directly. What is the most likely cause?

Accepted Answer

The skill endpoint is using HTTP instead of HTTPS.. Azure AI Search indexers that invoke custom skills via Azure Functions require the endpoint to use HTTPS. If the endpoint is configured with HTTP, the indexer will fail with a 'skill cannot be executed' error, even if the function itself works when tested directly. This is because the indexer enforces secure communication to protect data in transit.

Answer

The context is set incorrectly to '/document'.

Answer

The input source '/document/content' is invalid.

Answer

The skill's output targetName does not match the index field.

Question 7

Refer to the exhibit. You deployed this Azure AI Service resource. Developers report that they cannot call the service from their local machines using the API endpoint. The developers are not connected to the corporate VPN. What should you do?

Accepted Answer

Add the developers' public IP addresses to the ipRules list.. The exhibit shows that the Azure AI Service resource's network configuration has 'Selected Networks and Private Endpoints' enabled with a defaultAction of 'Deny'. This means only traffic from explicitly allowed IP addresses or virtual networks can reach the endpoint. Since the developers are not on the corporate VPN, they cannot use a virtual network rule. The correct solution is to add their public IP addresses to the ipRules list, which explicitly permits traffic from those specific IPs while keeping the default deny for all other traffic.

Answer

Disable network ACLs entirely.

Answer

Change defaultAction to Allow and remove all rules.

Answer

Add a second virtual network rule for the developers' subnet.

Question 8

Your organization is deploying Azure AI Document Intelligence to process invoices. You need to ensure that the solution meets compliance requirements by preventing data from being stored outside the European Union. What should you configure?

Accepted Answer

Create the Azure AI Document Intelligence resource in a region within the European Union and configure data residency settings.. Creating the Azure AI Document Intelligence resource in an EU region and configuring data residency settings ensures that all data processed by the service remains within the European Union, meeting compliance requirements. Azure AI Document Intelligence does not automatically guarantee data residency based solely on the resource region; explicit data residency configuration is required to prevent data from being stored or processed outside the specified geographic boundary.

Answer

Deploy Azure AI Document Intelligence in a multi-region configuration across EU datacenters.

Answer

Enable the Resource Firewall on the Azure AI Document Intelligence resource.

Answer

Use a Private Endpoint to connect to the Azure AI Document Intelligence resource.

Question 9

You are using Azure AI Language to perform sentiment analysis on customer feedback. You need to monitor the number of requests sent to the endpoint per minute. Which Azure service should you use?

Accepted Answer

Azure Monitor. Azure Monitor is the correct service because it provides platform metrics, including the 'Requests Per Minute' metric for Azure AI Language endpoints. This metric is automatically collected and can be viewed in the Azure portal, set up alerts on, or queried via the Azure Monitor REST API. It directly answers the need to monitor request rate without additional configuration.

Answer

Azure Cost Management

Answer

Azure Advisor

Answer

Azure Log Analytics

Question 10

Your team is developing a chatbot using Azure AI Bot Service with language understanding via Azure AI Language (CLU). You need to ensure that the chatbot can handle multiple intents in a single user utterance and return confidence scores for each. Which configuration should you use?

Accepted Answer

Use a Conversational Language Understanding (CLU) project with the 'Multiple intents' setting enabled.. Azure AI Language's Conversational Language Understanding (CLU) supports a 'Multiple intents' setting that allows the model to predict multiple intents from a single utterance, each with its own confidence score. This is the native way to handle multi-intent scenarios without requiring orchestration or custom logic.

Answer

Use an Orchestration workflow project that connects to multiple CLU projects.

Answer

Use a standard CLU project and manually combine intents.

Answer

Use Azure AI QnA Maker with custom logic to detect intents.

Question 11

You are planning an Azure AI solution that uses Azure AI Document Intelligence to extract data from scanned PDFs. The solution must support both structured and unstructured documents. The extracted data must be validated against a predefined schema before being stored in Azure Cosmos DB. What should you use for schema validation?

Accepted Answer

Azure AI Document Intelligence custom extraction model with a defined schema.. Azure AI Document Intelligence custom extraction models allow you to define a schema (field names, types, and relationships) that the service uses to extract data. The model enforces this schema during extraction—only fields defined in the schema are extracted, and missing fields are returned as null—effectively validating the extracted data against your predefined structure before it is stored in Azure Cosmos DB. This built-in constraint eliminates the need for additional validation logic.

Answer

Azure Functions to parse and validate the extracted data.

Answer

Azure AI Document Intelligence prebuilt model for invoices.

Answer

Azure Logic Apps with a JSON schema validation step.

Question 12

You need to provide a team of developers with access to manage Azure AI resources in a specific resource group. The developers should be able to create, read, update, and delete AI resources, but not manage access control (IAM). Which built-in role should you assign?

Accepted Answer

Contributor. The Contributor role grants full access to manage all resources within a resource group, including creating, reading, updating, and deleting Azure AI resources, but explicitly denies the ability to manage access control (IAM). This matches the requirement exactly, as developers need full resource management without IAM permissions.

Answer

Cognitive Services Contributor

Answer

Owner

Answer

Reader

Question 13

You are designing a solution that uses Azure AI Translator to translate documents in real-time. The solution must handle up to 10,000 characters per request and must be cost-effective. Which pricing tier should you select?

Accepted Answer

S1 (Standard). The S1 (Standard) tier is correct because it supports up to 10,000 characters per request for real-time document translation, which meets the requirement, and it is the most cost-effective paid tier for this workload. The Free tier (F0) has a limit of 5,000 characters per request and is not suitable for production use, while higher tiers like S2 and D3 are unnecessary and more expensive for this character limit.

Answer

F0 (Free)

Answer

D3 (Volume)

Answer

S2 (Standard)

Question 14

Which TWO actions are valid ways to authenticate to Azure AI services?

Accepted Answer

Use an API key.. Option B is correct because Azure AI services (such as Azure OpenAI, Computer Vision, and Language) support key-based authentication, where a subscription key or resource key is passed in the request header (e.g., 'Ocp-Apim-Subscription-Key' or 'api-key') to authenticate the caller. Option C is correct because Azure AI services integrate with Microsoft Entra ID, allowing a service principal (an app registration with a client ID and secret or certificate) to obtain an OAuth 2.0 token from the Microsoft identity platform and present it as a Bearer token for role-based access. Option A is not a standalone authentication mechanism for Azure AI services; client certificates are used within Entra ID service principal credential flows, not directly against the service endpoint. Option D is incorrect because shared access signatures are used for Azure Storage (and similar resources), not for authenticating to Azure AI services. Option E is incorrect as a distinct answer because managed identity is a form of Microsoft Entra ID authentication (covered by option C); while managed identities can authenticate to Azure AI services, the question asks for two valid ways and the marked correct pair is API key and Entra ID with service principal.

Answer

Use a client certificate.

Answer

Use a shared access signature (SAS) token.

Answer

Use a managed identity.

Question 15

Which TWO factors should you consider when choosing between Azure AI Document Intelligence and Azure AI Language for extracting information from documents?

Accepted Answer

Need to process handwritten text. Option B is correct because Azure AI Document Intelligence includes prebuilt and custom models specifically designed to recognize handwritten text in scanned documents, whereas Azure AI Language's text analytics capabilities operate on already-extracted text and do not perform OCR or handwriting recognition. Option C is correct because extracting tables from scanned PDFs requires document layout analysis and OCR, which are core features of Document Intelligence (e.g., the prebuilt-layout and prebuilt-document models), while Azure AI Language cannot parse PDFs or analyze visual table structures. Option A is not a distinguishing factor since both services are consumed via REST APIs (and SDKs). Option D is not decisive because key-value pair extraction is a Document Intelligence capability, but Azure AI Language also offers entity/key-phrase extraction from text, so it does not cleanly separate the two for document scenarios. Option E is not a differentiator because both services can be called in real time or in batch pipelines, so latency requirements alone do not determine which service to choose.

Answer

Use of REST APIs

Answer

Ability to extract key-value pairs

Answer

Real-time processing requirements