Question 1

An AI transformation lead notices that their Azure OpenAI–based assistant often jumps straight to a recommendation without explaining why. For risk and compliance reasons, the business needs the model to show its intermediate reasoning steps so humans can review the logic.Which prompt engineering change best addresses this requirement?

Options :

A : Add instructions like “Think step by step and show your reasoning before the final answer”

B : Only increase the maximum tokens allowed for the response

C : Remove all system instructions and rely on the model defaults

D : Ask users to add extra questions manually when they want more detail

Answer: A

Question 2

Fabrikam is deploying an AI copilot that can see sensitive project documents and internal chat data. A manager argues that because the copilot is only available on the internal network, there’s no need for extra security work.From a secure AI perspective, which requirement is most important to highlight?

Options :

A : Enforce identity, least privilege, and continuous verification

B : Trust any request that originates from the corporate network

C : Turn off encryption on AI traffic to reduce latency

D : Avoid logging so there is no record of prompts or responses

Answer: A

Question 3

Tailwind Traders wants a custom agent that can look up order status, create cases in their service system, and update records in Dynamics 365, all from a single Copilot conversation. You are asked which Copilot Studio capability makes this type of end-to-end integration possible.To enable a Copilot Studio agent to call external systems and orchestrate business processes, the design should primarily rely on ______.

Options :

A : Static text prompts with no external calls

B : Manual copy-and-paste between apps

C : Local CSV files attached to the chat

D : Connectors and plugin actions that call APIs and flows

Answer: D

Question 4

A national health agency wants to use AI to summarize clinical notes but must comply with strict privacy regulations.Question:Why is secure AI critical in this context?

Options :

A : Improve creativity in generated summariesImprove creativity in generated summaries

B : Protect sensitive data and control accessProtect sensitive data and control access

C : Avoid using encryption controls to cut cost

D : Share all system logs with every staff member

Answer: B

Question 5

Contoso’s leadership wants to use generative AI to boost everyday productivity: drafting emails, summarizing meetings, and improving documents in Word, Excel, PowerPoint, Outlook, and Teams.They have no urgent requirement to integrate external line-of-business systems yet, but want to show clear value in 3–6 months without a large engineering project.Which approach should they take first?

Options :

A : Build a custom AI app on Azure OpenAI and roll it out separately from Microsoft 365

B : Roll out Microsoft 365 Copilot out of the box, then plan extensibility in a later phase

C : Immediately build custom agents and connectors before enabling any Copilot features

D : Block Copilot and wait until all business systems are modeled as custom agents

Answer: B

Free AB-731 Mock Exam – Practice Online Confidently

Buying Options: