Determine How and When to Use Agent Bricks (Knowledge Assistant, Multiagent Supervisor, Information Extraction) to Solve Problems GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 2)

Questions 6–10

1. 6foundation · easy

   Which Agent Brick is designed to orchestrate multiple agents to handle complex, multi-step workflows?

   • AKnowledge Assistant
   • BInformation Extraction
   • CData Assistant
   • DMultiagent Supervisor
   Reveal Solution Discussion Select an answer first
2. 7foundation · easy

   Which Agent Brick should you choose if your problem involves extracting structured fields from unstructured PDF documents?

   • AMultiagent Supervisor
   • BInformation Extraction
   • CKnowledge Assistant
   • DData Assistant
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   A healthcare company wants to build an internal assistant that answers employee questions about HR policies. The assistant must retrieve answers from a curated set of policy PDFs stored in Unity Catalog. The team also wants to add a fallback that escalates unresolved questions to a specialized benefits agent. Which Agent Brick approach should they use?

   • AKnowledge Assistant only, with the benefits agent defined as a custom tool within the same assistant
   • BInformation Extraction to parse the policy PDFs into a structured table, then use a Multiagent Supervisor to answer questions from the table
   • CMultiagent Supervisor alone, configured with a single agent that uses the policy PDFs as its knowledge base
   • DKnowledge Assistant with a Multiagent Supervisor that routes to a benefits agent when the primary agent cannot answer
   Reveal Solution Discussion Select an answer first
5. 9foundation · easy

   How does Knowledge Assistant integrate with Databricks to answer questions over enterprise data?

   • AIt uses retrieval-augmented generation over data stored in the Databricks lakehouse
   • BIt requires data to be stored in a separate vector database outside Databricks
   • CIt uses a pre-trained model without accessing any data
   • DIt runs SQL queries directly on external databases only
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   What is the primary purpose of Multiagent Supervisor?

   • ATo generate answers from a single knowledge base
   • BTo train machine learning models
   • CTo extract structured data from documents
   • DTo manage and coordinate the execution of multiple agents
   Reveal Solution Discussion Select an answer first