AI-102 Practice Question: Implement natural language processing solutions
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?
⚠ Common exam trap
Many exam-takers confuse batch processing with real-time inference, assuming that any API endpoint can provide low latency, or they mistakenly think exporting to a Docker container is the standard way to expose a model via REST in Azure.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Obtain the endpoint URL and primary key from Language Studio
Option D is correct because deploying the custom text classification model to a real-time endpoint in Azure AI Language exposes a synchronous REST API that returns predictions immediately, satisfying the low-latency requirement. Option C is correct because, to call that REST API, the developer must obtain the endpoint URL and the primary key (or a secondary key) from the project's deployment details in Language Studio, which are used in the Ocp-Apim-Subscription-Key header for authentication. Option A is incorrect because the batch processing API is designed for asynchronous, high-volume jobs and does not provide the low-latency synchronous responses required here. Option B is incorrect because exporting the model as a Docker container is for on-premises or disconnected container deployment, not for exposing the model through the managed Azure AI Language REST endpoint. Option E is incorrect because a test endpoint in the Azure portal is intended for validation and does not provide the production-grade, low-latency real-time REST API needed for the application.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use the batch processing API
Why it's wrong here
Batch processing submits asynchronous jobs that return results only after completion, so it cannot serve low-latency synchronous REST calls. It is tempting because it suits high-volume, non-urgent workloads such as bulk document classification, where throughput matters and immediate responses do not.
- ✗
Export the model as a Docker container
Why it's wrong here
Exporting as a Docker container suits on-premises or offline deployment, not the managed Azure AI Language endpoint the scenario requires. It is tempting because containers give latency control, and would be correct where data residency or disconnected operation rules out the hosted service.
- ✓
Obtain the endpoint URL and primary key from Language Studio
Why this is correct
Retrieving the endpoint URL and primary key from Language Studio provides the authentication credentials and base address required to call the deployed model's REST API. Without these, requests cannot be authenticated, regardless of deployment type or latency characteristics.
- ✓
Deploy the model to a real-time endpoint
Why this is correct
Deploying to a real-time endpoint provisions a hosted, always-available inference endpoint with low latency, satisfying the REST API accessibility requirement. Batch or asynchronous deployments introduce queuing delays and are unsuitable when immediate responses are mandated.
- ✗
Deploy to a test endpoint in the Azure portal
Why it's wrong here
A test endpoint is for validation, not production low-latency serving; it lacks the throughput and SLA guarantees of a deployed endpoint. It is tempting because it is quick to provision, and would be correct when evaluating model quality before committing to a production deployment.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.