Databricks-GenAI-Assoc Assembling and Deploying Apps Practice Question
A GenAI engineer has a Mosaic AI Agent application packaged as a Databricks Asset Bundle with a serving endpoint defined in the bundle's resources. A teammate recently updated the agent's prompt template in the source files, and the engineer now needs to push that change to the existing production endpoint without recreating it. Which Databricks CLI command should the engineer run from the bundle root?
⚠ Common exam trap
The trap here is assuming a serving-endpoint-specific CLI command updates bundle-managed endpoints, when only the bundle deploy command reconciles the declarative bundle state.
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
✓
databricks bundle deploy --target prod
Deploying a modified Mosaic AI Agent that is defined as a bundle resource requires applying the bundle state to the target workspace, which the Databricks CLI does with bundle deploy. Selecting the production target ensures the correct workspace, variables, and permissions are used, and the existing serving endpoint is updated in place instead of being recreated.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
databricks bundle validate --target prod
Why it's wrong here
The bundle validate command only checks that the bundle's configuration is syntactically valid and that referenced variables and resources resolve correctly; it performs no deployment. Running it would confirm the databricks.yml is well-formed but would leave the production endpoint untouched, so the updated prompt template would never reach the running agent application.
- ✗
databricks serving-endpoints update --name agent-endpoint
Why it's wrong here
There is no standalone databricks serving-endpoints update subcommand that applies a bundle's declarative configuration. The serving-endpoints CLI group supports operations such as get, list, and create/put, but it does not read databricks.yml or reconcile bundle resources. Using it here would bypass the bundle's target variables and permissions, so the engineer's prompt change would not be deployed through the managed bundle workflow.
- ✗
databricks bundle run agent_app --target prod
Why it's wrong here
The bundle run command executes a job or pipeline defined in the bundle, not a serving endpoint resource. It is used for workflows such as training or evaluation jobs. Since the change here is a prompt template inside a deployed serving endpoint, running a job would not push the updated agent configuration to the endpoint, leaving production on the old prompt.
- ✓
databricks bundle deploy --target prod
Why this is correct
The Databricks CLI bundle deploy command reads the bundle's databricks.yml, resolves the specified target, and applies the current state of the resources to the workspace, updating the existing serving endpoint definition in place rather than recreating it. Running it with --target prod selects the production target's workspace host, variables, and permissions so the prompt change is deployed to the correct environment.
About these practice questions
One of 330 original Databricks-GenAI-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks 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 Databricks-GenAI-Assoc exam.