Drag steps to the numbered slots on the right, or tap a step then tap a slot.
Steps
Order
1Step 1
2Step 2
3Step 3
4Step 4
5Step 5
Describe features of Natural Language Processing workloads on Azure →mediumDrag & DropObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
Drag and drop the steps to deploy a model as a real-time inference endpoint in Azure Machine Learning into the correct order.
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
✓
Register the model, then create the scoring script, then deploy the model to a compute target
Deploying a real-time endpoint requires registering the model, creating a scoring script, and deploying to compute.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Register the model, then create the scoring script, then deploy the model to a compute target
Why this is correct
This is correct because the model must be registered first in the Azure Machine Learning workspace, then you need a scoring script that defines how to run the model for inference, and finally you deploy the model to a compute target (e.g., Azure Container Instance) to create the real-time endpoint.
- ✗
Create the scoring script, then register the model, then deploy the model to a compute target
Why it's wrong here
This is incorrect because the scoring script references the model, so the model must be registered before the scoring script is created. Creating the script first would require knowledge of the model's registration details, but the model is not yet registered.
- ✗
Register the model, then deploy the model to a compute target, then create the scoring script
Why it's wrong here
This is incorrect because deployment requires the scoring script to be ready. Without the scoring script, the deployment configuration is incomplete, and the endpoint cannot be created. The scoring script must be created before deployment.
- ✗
Deploy the model to a compute target, then register the model, then create the scoring script
Why it's wrong here
This sequence is invalid because Azure Machine Learning cannot deploy a model that does not yet exist in the workspace registry. The compute target needs the model's registered name, version, and path to pull the artifacts, and without prior registration the deployment service has nothing to package. Additionally, the scoring script must be present before deployment so the endpoint knows how to load the model and process incoming requests; attempting to deploy first would fail at configuration time because both the model reference and the scoring entry point are missing. In practice, the SDK's Model.deploy() call references an already-registered model and a scored script, so reversing the order breaks the dependency chain.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Azure Machine Learning
Azure Machine Learning is a cloud service for building, training, and deploying machine learning models at scale.
Key term
Machine learning
Machine learning is a branch of artificial intelligence where computers learn patterns from data to make decisions or predictions without being explicitly programmed for every task.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 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-900 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-900 exam.