Skip to content

Design Applications Questions

Practice questions for Design Applications topic in Databricks Certified Generative AI Engineer Associate. 28 questions covering this domain.

28 questions9 easy11 medium8 hard
Q1
hard

A customer support chatbot consistently hallucinates product specifications. The team maintains a well-structured product catalog Delta table. Which d...

Q2
medium

An LLM application must: (1) retrieve relevant documents, (2) summarize each document, and (3) generate a consolidated final answer. Which architectur...

Q3
easy

What is Retrieval Augmented Generation (RAG)?

Q4
medium

An ML team is choosing between fine-tuning a foundation model and building a RAG solution to improve an LLM's responses about specialized medical term...

Q5
easy

An enterprise needs an LLM to answer questions about its large, frequently updated internal knowledge base. Which approach is most appropriate?

Q6
medium

Which components are essential in a standard RAG pipeline?

Q7
hard

A team is building an application that must answer general questions via web search, query an internal SQL database for sales data, and summarize docu...

Q8
easy

What is a "system prompt" in the context of an LLM-powered chat application?

Q9
easy

What does "prompt engineering" refer to in the context of LLM-powered applications?

Q10
medium

A team is building a customer service bot that must answer questions about product warranties. The warranty terms change every quarter. The team wants...

Q11
easy

Which Databricks tool allows engineers to interactively test and compare different large language models directly within the Databricks workspace befo...

Q12
hard

An ML team has a working RAG chatbot grounded on an internal knowledge base. Users frequently ask follow-up questions like "What about the pricing for...

Q13
hard

An engineering team is building an application that: (1) receives a user question, (2) decides whether to answer from a product catalog, an HR policy ...

Q14
medium

A generative AI engineer is deciding between zero-shot prompting, few-shot prompting, and fine-tuning for a task that involves classifying short custo...

Q15
easy

Which Databricks capability standardizes how agents connect to data sources and tools through a secure, consistent interface?

Q16
medium

An HR assistant must answer policy questions from a knowledge base and also submit leave requests through an HR API when the user asks to take action....

Q17
easy

A product team wants a no-code place to prototype an agent, try different tool integrations, and compare behavior before generating Python code. Which...

Q18
hard

A company is building an assistant with one specialist for billing disputes and another for troubleshooting product failures. User questions should be...

Q19
medium

A team is building a batch workflow that converts free-form support notes into a fixed schema of fields for downstream analytics. According to Databri...

Q20
medium

A business analyst wants to build a domain-specific chatbot with an intuitive interface instead of authoring an agent directly in Python. Which Databr...

Sign in to see all 28 questions

Create a free account to browse all questions — completely free during our launch phase.