Databricks-GenAI-Assoc Application Development Practice Question
A team is developing a generative AI application that uses an LLM to answer questions based on internal documents. They want to ensure the application is robust and provides accurate responses. Which TWO practices should they implement to improve the reliability of the application? (Choose two.)
⚠ Common exam trap
The trap here is assuming that fine-tuning or using a larger model is the best way to improve reliability, but without retrieval and output validation, these approaches can still produce hallucinations and lack source attribution.
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
✓
Implement retrieval-augmented generation (RAG) to ground the LLM's responses in the internal documents.
The two practices are RAG and guardrails. RAG grounds responses in internal documents, reducing hallucinations and providing accurate, up-to-date information. Guardrails validate outputs to filter out harmful or incorrect content. Together, they significantly improve the reliability and safety of a GenAI application, especially for enterprise use cases.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Implement retrieval-augmented generation (RAG) to ground the LLM's responses in the internal documents.
Why this is correct
RAG retrieves relevant documents and includes them in the prompt, so the LLM generates answers based on factual, up-to-date internal content. This reduces hallucinations and improves accuracy. It is a core practice for building reliable GenAI applications that need to answer domain-specific questions.
- ✗
Fine-tune the LLM on the internal documents to embed knowledge directly into the model weights.
Why it's wrong here
Fine-tuning can help the model learn style or domain-specific language, but it is not ideal for factual recall because it can be expensive, may not update dynamically, and can still hallucinate. It also requires significant data and compute. For reliability and accuracy, RAG is preferred as it provides explicit context and can be updated easily.
- ✓
Implement guardrails to validate and filter the LLM's outputs before returning them to the user.
Why this is correct
Guardrails can check for harmful, off-topic, or incorrect responses and prevent them from reaching users. They add a safety layer that improves reliability by catching errors or hallucinations. In Databricks, you can use built-in guardrails or custom validation logic. This practice complements RAG by ensuring output quality.
- ✗
Use a larger LLM with more parameters to increase the likelihood of correct answers.
Why it's wrong here
A larger model may have better general knowledge, but it does not guarantee accuracy for internal documents. It can still hallucinate and lacks access to private data. Without retrieval, it cannot cite sources. Model size alone does not ensure reliability; grounding with RAG and evaluation are more effective.
- ✗
Set the LLM's temperature to a high value to encourage more creative and diverse responses.
Why it's wrong here
High temperature increases randomness, which leads to less factual and more varied outputs. For reliable question answering, a lower temperature (e.g., 0.0-0.3) is preferred to produce deterministic and focused answers. High temperature would reduce accuracy and consistency.
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.