A company is building a multi-agent system where one agent is responsible for retrieving data from Genie Spaces, and another agent generates reports. The report agent needs to request data from the Genie agent. What is the most effective way for these agents to communicate?

Have the report agent directly query Genie Spaces using the Genie API

Use a shared message queue for agents to send requests and responses

Use a direct function call from the report agent to the Genie agent

Have the report agent write a file that the Genie agent reads

A team has deployed an agentic system that uses multiple tools to answer user queries. They want to monitor the performance of the agent over time, including which tools are called, the prompts sent, and the responses generated. They also need to compare different versions of the agent to see if changes improve accuracy. Which approach should they use?

Use MLflow to log prompts, responses, and metrics, and register agent versions

Rely on the LLM provider's built-in logging only

Use a simple Python dictionary to store metrics in memory

Log prompts and responses to a file and manually review them

A developer is building an agent that uses the conversational API to retrieve data. They need to ensure that only authorized users can access the API and that queries are logged for audit purposes. What should they do?

Use personal access tokens and store them in the code

Use no authentication and rely on the network firewall

Use shared access keys and disable logging

Use service principal authentication and enable query logging

What is the primary benefit of using a conversational API for data retrieval in an agentic system?

It allows direct access to the underlying database schema

It eliminates the need for authentication

It allows agents to query data using natural language, simplifying the interaction

It guarantees faster query performance than SQL

DatabricksCertified Generative AI Engineer Associate

Domain 3Objective 5

Tooling and Frameworks GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Part of the Section 3: Application Development domain, which makes up ~18% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~6–11 in this domain), expect 1–2 from this objective — we provide 24 practice questions to prepare you well beyond it. (estimate)

24questions here

5free pages

6concepts

Questions 11–15

11application · medium
A company is building a multi-agent system where one agent is responsible for retrieving data from Genie Spaces, and another agent generates reports. The report agent needs to request data from the Genie agent. What is the most effective way for these agents to communicate?
Select an answer first
12application · medium
A team has deployed an agentic system that uses multiple tools to answer user queries. They want to monitor the performance of the agent over time, including which tools are called, the prompts sent, and the responses generated. They also need to compare different versions of the agent to see if changes improve accuracy. Which approach should they use?
Select an answer first
13foundation · easy
Which component of Agent Framework is responsible for persisting and retrieving information across different turns of a conversation?
Select an answer first
14application · medium
A developer is building an agent that uses the conversational API to retrieve data. They need to ensure that only authorized users can access the API and that queries are logged for audit purposes. What should they do?
Select an answer first
15foundation · easy
What is the primary benefit of using a conversational API for data retrieval in an agentic system?
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.

Tooling and Frameworks GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Questions 11–15

A company is building a multi-agent system where one agent is responsible for retrieving data from Genie Spaces, and another agent generates reports. The report agent needs to request data from the Genie agent. What is the most effective way for these agents to communicate?

Which component of Agent Framework is responsible for persisting and retrieving information across different turns of a conversation?

A developer is building an agent that uses the conversational API to retrieve data. They need to ensure that only authorized users can access the API and that queries are logged for audit purposes. What should they do?

What is the primary benefit of using a conversational API for data retrieval in an agentic system?

Keep studying — Section 3: Application Development