Databricks-GenAI-Assoc Assembling and Deploying Apps Practice Question
A data science team wants to expose a fine-tuned LLM as a REST API for an internal web application. They have registered the model in Unity Catalog and want Databricks to manage the serving infrastructure, autoscaling, and request routing. Which Databricks capability should they use?
⚠ Common exam trap
The trap here is equating any compute that runs model code with a managed serving endpoint, when only Model Serving provides autoscaling REST inference.
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 Model Serving, which creates a managed endpoint that autoscales and routes requests to the model.
Databricks Model Serving is the managed capability that turns registered models into autoscaling REST endpoints with routing and load balancing. The other options either run unmanaged code on clusters, execute SQL, or precompute batch outputs, none of which deliver interactive, managed model inference for a web 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.
- ✗
A Delta Live Tables pipeline that materializes model outputs into a table the web app polls.
Why it's wrong here
Delta Live Tables is a declarative data pipeline framework for transforming data, not an inference API. Precomputing outputs cannot answer arbitrary prompts, and polling a table introduces latency and cannot support interactive generation. It does not provide autoscaling or request routing for a model.
- ✓
Databricks Model Serving, which creates a managed endpoint that autoscales and routes requests to the model.
Why this is correct
Model Serving provides managed endpoints with autoscaling, load balancing, and a REST API, and it loads models directly from Unity Catalog. It matches every stated requirement: managed infrastructure, autoscaling, request routing, and REST access for the web application without the team operating servers.
- ✗
A Databricks job cluster running a notebook that starts a Flask server on the driver.
Why it's wrong here
A job cluster with a Flask server on the driver is not a managed serving product. It lacks autoscaling, request routing, and high availability, and the driver is not reachable as a stable REST endpoint. This pattern is fragile and unsupported for production API traffic compared with managed serving.
- ✗
A Databricks SQL warehouse with a custom HTTP connection to the model.
Why it's wrong here
SQL warehouses execute SQL workloads and do not host arbitrary model inference or expose a model REST API. While they can call remote endpoints through SQL functions, they do not serve the model themselves or provide the autoscaling inference infrastructure the team needs.
About these practice questions
This Databricks-GenAI-Assoc question is part of Courseiva's 330-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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.