Databricks-GenAI-Assoc Design Applications Practice Question
An engineer is designing a Databricks GenAI application that summarizes customer meeting notes. The notes contain personally identifiable information, and company policy requires that the summarization model never sends note text to an external provider. The team already has a fine-tuned open model registered in Unity Catalog. Which deployment choice satisfies the policy?
⚠ Common exam trap
The trap here is equating a Databricks-hosted model API with in-workspace inference, when only serving the model inside the workspace guarantees the data boundary the policy demands.
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
✓
Serve the registered open model on a Databricks Model Serving endpoint and call it from the application
The policy requires that note text never reach an external provider, so inference must run inside the company's Databricks environment. Serving the registered open model on a Databricks Model Serving endpoint keeps prompts and responses within the workspace while still offering a scalable API, and Unity Catalog continues to govern access to the model.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Serve the registered open model on a Databricks Model Serving endpoint and call it from the application
Why this is correct
Hosting the registered open model on a Model Serving endpoint keeps all inference inside the Databricks workspace, so note text never leaves the company's boundary. The endpoint exposes a standard API the application can call, and Unity Catalog governance continues to apply to the model artifact and its access controls.
- ✗
Use Databricks Foundation Model APIs with the pay-per-token option for a supported open model
Why it's wrong here
Foundation Model APIs are convenient, but pay-per-token endpoints may be served from capacity outside the customer's workspace, and the policy demands that note text never leave the boundary. Choosing this route introduces uncertainty about where inference occurs, so it does not provide the guarantee the scenario requires.
- ✗
Export the notes to a local workstation, run an open model there, and upload the summaries back
Why it's wrong here
Moving personally identifiable information to a local workstation takes it outside governed Databricks storage and access controls, creating an unmanaged copy of sensitive data. This violates the spirit and letter of the policy, and it also breaks lineage and auditability that Unity Catalog would otherwise provide.
- ✗
Call a third-party foundation model API directly from the notebook and pass the notes in the request body
Why it's wrong here
Sending note text to a third-party API transmits personally identifiable information to an external provider, which the policy explicitly forbids. Even if the provider offers strong security, the data crosses the company boundary, so this option fails the requirement regardless of model quality or convenience.
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.