Microsoft AI-103 Exam Prep
Developing AI Apps and Agents on Azure (Page 6 )

Updated On: 3-Oct-2026
View Related Case Study

You have a Microsoft Foundry project that contains a customer support agent. The agent calls an internal knowledge API tool before generating responses.
Users report the following issues:
▪ Some requests take more than 15 seconds to complete.
▪ Some responses are incorrect, even when the knowledge API returns the expected data.
You need to inspect individual agent runs to view the ordered sequence of large language model (LLM) calls,
tool invocations, and timing information.
Which observability capability should you use?

  1. token usage
  2. monitoring
  3. safety metrics
  4. tracing

Answer(s): D

Explanation:

Here is LLM tracing (also known as trace view or distributed tracing for GenAI) needed.
Tracks Execution Flow: It captures the exact ordered sequence of LLM calls and tool invocations.
Pinpoints Latency: It provides timestamps and durations for every individual step to catch the 15-second bottlenecks.
Inspects Inputs/Outputs: It lets you see the exact payload sent to and from the knowledge API and the final
LLM prompt to find out why the agent hallucinated or ignored the data.


Reference:

https://coralogix.com/ai-blog/advanced-techniques-for-monitoring-traces-in-ai-workflows/



View Related Case Study

Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.
After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.
You have a multimodal AI generative model that accepts image uploads and uses extracted image text to generate responses.
You discover that users can upload unsafe images and embed hidden instructions into images to manipulate the model.
You need to implement controls to mitigate the risk.
Solution: You configure a prompt shield for user prompts.
Does this meet the goal?

  1. Yes
  2. No

Answer(s): B



View Related Case Study

Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.
After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.
You have a multimodal AI generative model that accepts image uploads and uses extracted image text to generate responses.
You discover that users can upload unsafe images and embed hidden instructions into images to manipulate the model.
You need to implement controls to mitigate the risk.
Solution: You configure image moderation to block unsafe content before processing the images.
Does this meet the goal?

  1. Yes
  2. No

Answer(s): B



View Related Case Study

Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.
After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.
You have a multimodal AI generative model that accepts image uploads and uses extracted image text to generate responses.
You discover that users can upload unsafe images and embed hidden instructions into images to manipulate the model.
You need to implement controls to mitigate the risk.
Solution: You configure a prompt shield for documents.
Does this meet the goal?

  1. Yes
  2. No

Answer(s): A

Explanation:

Correct:
* You configure a prompt shield for documents.
Prompt Shield for Documents: Highly Effective (Critical Defense)
How it helps: This shield specifically scans untrusted, third-party data inputs (like external documents or text extracted from uploaded images).
Mechanism: It evaluates the extracted image text before it is sent to the LLM to identify hidden jail
* You configure a prompt shield for user prompts.
Prompt Shield for User Prompts: Partially Effective (Defense in Depth)
How it helps: This shield targets direct jailbreak attempts written manually by the user in the text prompt field accompanying the upload.
Mechanism: It prevents the user from typing supporting instructions that prime the model to execute the hidden instructions found within the image.
* You configure image moderation to block unsafe content before processing the images.
Implementing rigorous image moderation is one of the most effective ways to secure multimodal AI systems against these threats. Moderation acts as a necessary gatekeeper, preventing malicious inputs from ever reaching the generative model.
Incorrect:
* You configure protected material detection.
Protected Material Detection: Ineffective for this Threat
Why it does not help: This feature is designed to scan model outputs to prevent the generation of copyrighted text, proprietary source code, or licensed imagery.
Limitation: It does not scan inputs for adversarial instructions and will not prevent a user from manipulating the model's logic.


Reference:

https://www.upgrad.com/blog/what-is-multimodal-ai/
https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection



View Related Case Study

Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.
After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.
You have a multimodal AI generative model that accepts image uploads and uses extracted image text to generate responses.
You discover that users can upload unsafe images and embed hidden instructions into images to manipulate the model.
You need to implement controls to mitigate the risk.
Solution: You configure protected material detection.
Does this meet the goal?

  1. Yes
  2. No

Answer(s): B

Explanation:

Correct:
* You configure a prompt shield for documents.
Prompt Shield for Documents: Highly Effective (Critical Defense)
How it helps: This shield specifically scans untrusted, third-party data inputs (like external documents or text extracted from uploaded images).
Mechanism: It evaluates the extracted image text before it is sent to the LLM to identify hidden jail
* You configure a prompt shield for user prompts.
Prompt Shield for User Prompts: Partially Effective (Defense in Depth)
How it helps: This shield targets direct jailbreak attempts written manually by the user in the text prompt field accompanying the upload.
Mechanism: It prevents the user from typing supporting instructions that prime the model to execute the hidden instructions found within the image.
* You configure image moderation to block unsafe content before processing the images.
Implementing rigorous image moderation is one of the most effective ways to secure multimodal AI systems against these threats. Moderation acts as a necessary gatekeeper, preventing malicious inputs from ever reaching the generative model.
Incorrect:
* You configure protected material detection.
Protected Material Detection: Ineffective for this Threat
Why it does not help: This feature is designed to scan model outputs to prevent the generation of copyrighted text, proprietary source code, or licensed imagery.
Limitation: It does not scan inputs for adversarial instructions and will not prevent a user from manipulating the model's logic.


Reference:

https://www.upgrad.com/blog/what-is-multimodal-ai/
https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection



Viewing page 6 of 39
Viewing questions 26 - 30 out of 187 questions


Post your Comments and Discuss Microsoft AI-103 exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!