A team wants to promote a prompt from a development environment to a staging environment. What is the recommended approach in a CI/CD context?

Manually copy the prompt text from the development environment and paste it into the staging environment

Email the prompt to the staging environment administrator for manual deployment

Recreate the prompt from scratch in the staging environment

Use a CI/CD pipeline that packages the prompt as an artifact and deploys it to the staging environment

A company has a CI/CD pipeline that deploys a RAG application. The pipeline currently updates the Vector Search index and then deploys the application. They notice that the application sometimes queries the index before the update is complete, causing errors. What is the best way to ensure the index is ready before the application deployment?

Update the index in the application code and redeploy.

Deploy the application first and then update the index.

Add a step in the pipeline that waits for the index sync job to complete successfully before proceeding.

Use a manual approval step before the index update.

In the prompt lifecycle, what typically happens during the 'review' stage?

The prompt is marked as deprecated and no longer recommended

The prompt is evaluated for quality, safety, and alignment with requirements

The prompt is automatically deployed to all environments

The prompt is permanently deleted from the repository

Before calling mlflow.register_model() to register a model to Unity Catalog, what must be configured in the MLflow client?

The experiment name for the training run

The model's training hyperparameters

The registry URI to point to the Unity Catalog registry

The model's serving endpoint configuration

DatabricksCertified Generative AI Engineer Associate

Domain 4Objective 3

Manage Model Lifecycle and Governance GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Part of the Section 4: Assembling and Deploying Applications domain, which makes up ~11% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~4–7 in this domain), expect 1–2 from this objective — we provide 27 practice questions to prepare you well beyond it. (estimate)

27questions here

6free pages

8concepts

Questions 11–15

11foundation · easy
A team wants to promote a prompt from a development environment to a staging environment. What is the recommended approach in a CI/CD context?
Select an answer first
12expert · hard
A company has a CI/CD pipeline that deploys a RAG application. The pipeline currently updates the Vector Search index and then deploys the application. They notice that the application sometimes queries the index before the update is complete, causing errors. What is the best way to ensure the index is ready before the application deployment?
Select an answer first
13foundation · easy
In the prompt lifecycle, what typically happens during the 'review' stage?
Select an answer first
14foundation · easy
A data scientist wants to register a trained model to a specific catalog and schema in Unity Catalog using MLflow. Which MLflow function should be used to accomplish this?
Select an answer first
15foundation · easy
Before calling mlflow.register_model() to register a model to Unity Catalog, what must be configured in the MLflow client?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to GENERATIVE-AI-ENGINEER-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “GENERATIVE-AI-ENGINEER-ASSOCIATE” is a trademark of its owner, used for identification only.

Manage Model Lifecycle and Governance GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Questions 11–15

A team wants to promote a prompt from a development environment to a staging environment. What is the recommended approach in a CI/CD context?

In the prompt lifecycle, what typically happens during the 'review' stage?

A data scientist wants to register a trained model to a specific catalog and schema in Unity Catalog using MLflow. Which MLflow function should be used to accomplish this?

Before calling mlflow.register_model() to register a model to Unity Catalog, what must be configured in the MLflow client?

Keep studying — Section 4: Assembling and Deploying Applications