A retail company wants to build a chatbot that answers customer questions about product specifications and return policies. The source data is a set of markdown files and CSV tables stored in Unity Catalog. The chatbot should provide answers with citations to the source documents. Which Agent Brick should they use?

Knowledge Assistant with a Multiagent Supervisor

A telecom company is building an assistant that handles customer inquiries. The team has two existing agents: one for billing and one for technical support. They want the assistant to first try to answer using a knowledge base, and only if it cannot, route to the appropriate specialized agent. They also need to log every interaction for audit. Which architecture should they choose?

Knowledge Assistant as the primary agent, with a Multiagent Supervisor that routes to billing or technical support when the primary cannot answer

Knowledge Assistant with billing and technical support defined as tools, and no supervisor

Information Extraction to parse the knowledge base, then a Multiagent Supervisor to route to billing or technical support

Multiagent Supervisor as the primary agent, with billing and technical support as sub-agents, and no Knowledge Assistant

An insurance company receives claim forms as scanned images. Each form contains the claimant's name, policy number, and claim amount in handwritten or typed fields. The company needs to extract these fields into a structured table for automated processing. Which Agent Brick should they use?

Knowledge Assistant with a custom extraction tool

A bank is building a customer-facing assistant. The team has a Knowledge Assistant that answers questions from a FAQ database. They now want to add a feature where, if the assistant cannot answer, it escalates to a human agent. The escalation should include the conversation history and the reason for escalation. The team wants to minimize custom code. What should they do?

Use a second Knowledge Assistant trained on escalation policies to handle the handoff

Use Information Extraction to analyze the conversation and decide when to escalate

Wrap the Knowledge Assistant in a Multiagent Supervisor that detects low-confidence answers and routes to a human-agent handoff

Modify the Knowledge Assistant to call a custom function that sends the conversation to a human agent

What is the key factor in deciding between Knowledge Assistant and Information Extraction?

Whether the task is question-answering or structured data extraction

Whether the model is open-source or proprietary

Whether the data is stored in a lakehouse or a data warehouse

Whether the data is structured or unstructured

DatabricksCertified Generative AI Engineer Associate

Domain 1Objective 6

Determine How and When to Use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to Solve Problems GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Part of the Section 1: Design Applications domain, which makes up ~19% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~7–11 in this domain), expect 1–2 from this objective — we provide 16 practice questions to prepare you well beyond it. (estimate)

16questions here

4free pages

5concepts

Questions 11–15

11application · medium
A retail company wants to build a chatbot that answers customer questions about product specifications and return policies. The source data is a set of markdown files and CSV tables stored in Unity Catalog. The chatbot should provide answers with citations to the source documents. Which Agent Brick should they use?
Select an answer first
12expert · hard
A telecom company is building an assistant that handles customer inquiries. The team has two existing agents: one for billing and one for technical support. They want the assistant to first try to answer using a knowledge base, and only if it cannot, route to the appropriate specialized agent. They also need to log every interaction for audit. Which architecture should they choose?
Select an answer first
13application · medium
An insurance company receives claim forms as scanned images. Each form contains the claimant's name, policy number, and claim amount in handwritten or typed fields. The company needs to extract these fields into a structured table for automated processing. Which Agent Brick should they use?
Select an answer first
14expert · hard
A bank is building a customer-facing assistant. The team has a Knowledge Assistant that answers questions from a FAQ database. They now want to add a feature where, if the assistant cannot answer, it escalates to a human agent. The escalation should include the conversation history and the reason for escalation. The team wants to minimize custom code. What should they do?
Select an answer first
15foundation · easy
What is the key factor in deciding between Knowledge Assistant and Information Extraction?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to GENERATIVE-AI-ENGINEER-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “GENERATIVE-AI-ENGINEER-ASSOCIATE” is a trademark of its owner, used for identification only.

Determine How and When to Use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to Solve Problems GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Questions 11–15

An insurance company receives claim forms as scanned images. Each form contains the claimant's name, policy number, and claim amount in handwritten or typed fields. The company needs to extract these fields into a structured table for automated processing. Which Agent Brick should they use?

What is the key factor in deciding between Knowledge Assistant and Information Extraction?

Keep studying — Section 1: Design Applications