Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft AB-620 Exam - Topic 2 Question 5 Discussion

A company is configuring an agent in Copilot Studio that uses a generative answers node inside multiple topics.The company requires responses to meet the following requirements.* Must use an executive summary format* Must apply only within a specific topic.* Must continue using configured knowledge sources.* Must comply with connector security controls.You need to configure a custom prompt to meet the formatting requirementsSolution: Create a custom prompt tool in the specific topic that instructs the model to respond using an executive-summary structure.Does the solution meet the goal?
B) No
A) Yes

Microsoft AB-620 Exam - Topic 2 Question 5 Discussion

Actual exam question for Microsoft's AB-620 exam
Question #: 5
Topic #: 2
[All AB-620 Questions]

A company is configuring an agent in Copilot Studio that uses a generative answers node inside multiple topics.

The company requires responses to meet the following requirements.

* Must use an executive summary format

* Must apply only within a specific topic.

* Must continue using configured knowledge sources.

* Must comply with connector security controls.

You need to configure a custom prompt to meet the formatting requirements

Solution: Create a custom prompt tool in the specific topic that instructs the model to respond using an executive-summary structure.

Does the solution meet the goal?

Show Suggested Answer Hide Answer
Suggested Answer: B

Comprehensive and Detailed Explanation From Microsoft AB-620 Study Guide: A separate custom prompt tool that merely requests an executive-summary structure does not, by itself, guarantee that the existing generative answers node and its configured knowledge sources remain in the response path. Prompt tools have their own inputs, knowledge configuration, model settings, and completion behavior. If the tool is invoked independently, it can generate correctly formatted text without using the sources selected for the topic's generative answer, which violates a stated requirement. The safer design is to keep the generative answers node and apply topic-specific custom instructions or prompt modification to that node, or explicitly pass its grounded output into a downstream formatting prompt with a controlled contract. Connector security remains enforced by the underlying connections and data policies; wording in a prompt cannot override those controls. Therefore, the proposed solution is incomplete and does not meet the goal as written. Testing should confirm not only the output format but also the sources used and the identity under which any connector retrieval occurred. Study Guide alignment: Plan and configure agent solutions > Configure topics > Configure advanced agent responses with custom prompts and custom knowledge sources.

===============


Contribute your Thoughts:

0/2000 characters

Currently there are no comments in this discussion, be the first to comment!


Save Cancel