Itexamdump에서는 IT인증시험에 관한 모든 덤프를 제공해드립니다. 우선 시험센터에서 정확한 시험코드를 확인하시고 그 코드와 동일한 코드로 되어있는 덤프를 구매하셔서 덤프에 있는 문제와 답을 기억하시면 시험을 쉽게 패스하실수 있습니다.AI-103시험은 IT인증시험중에서 많은 인기를 가지고 있는 시험입니다.AI-103시험을 패스하여 자격증을 취득하시면 취업이나 승진에 많은 가산점이 되어드릴것입니다.
| Section | Weight | Objectives |
|---|---|---|
| Topic 1: Implement computer vision solutions | 10-15% | - Analyze visual content
|
| Topic 2: Implement text analysis and information extraction solutions | 10-15% | - Analyze and extract information
|
| Topic 3: Implement generative AI solutions | 25-30% | - Develop generative AI applications
|
| Topic 4: Plan and manage Azure AI solutions | 25-30% | - Manage AI solution lifecycle
|
| Topic 5: Implement agentic solutions | 20-25% | - Manage agent operations
|
최근들어 Microsoft AI-103시험이 큰 인기몰이를 하고 있는 가장 핫한 IT인증시험입니다. Microsoft AI-103덤프는Microsoft AI-103시험 최근문제를 해석한 기출문제 모음집으로서 시험패스가 한결 쉬워지도록 도와드리는 최고의 자료입니다. Microsoft AI-103인증시험을 패스하여 자격증을 취득하면 보다 쉽고 빠르게 승진할수 있고 연봉인상에도 많은 도움을 얻을수 있습니다.
질문 # 121
Hotspot Question
You have a Microsoft Foundry project that contains an agent.
The agent uses a stored access key to retrieve secrets from an Azure key vault, which violates a keyless-credentials requirement.
You need to ensure that the agent can retrieve the secrets. The solution must follow the principle of least privilege.
What should you configure? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
정답：
설명：
Explanation:
Box 1: Enable a system-assigned managed identity at the project level
The correct configuration is to enable a system-assigned managed identity at the project level.
This is the correct approach. Azure AI Foundry (formerly Azure Machine Learning) allows you to enable a system-assigned managed identity directly at the project level. This identity acts as a keyless credential native to Azure. To follow the principle of least privilege, you then assign this project-level identity a specific role (such as Key Vault Secrets User) restricted only to the required Azure Key Vault. This ensures that the agent can retrieve secrets securely without exposing credentials to other projects or resources Box 2: Assign the Key Vault Secrets User role to the managed identity To comply with the keyless-credentials requirement and follow the principle of least privilege, you should configure the Key Vault authorization method to assign the Key Vault Secrets User role to the managed identity using Azure Role-Based Access Control (Azure RBAC).
Reference:
https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway
https://learn.microsoft.com/en-us/azure/app-service/app-service-key-vault-references
질문 # 122
You have a Microsoft Foundry project that contains an agent and uses a GitHub repository. The repository contains a YAM file named File1 that defines the evaluation settings of the agent. You need to create a GitHub Actions workflow that runs the evaluation defined in File1 when a pull request (PR) is opened. How should you configure the workflow?
정답：B
설명：
The correct configuration choice is to set project-endpoint to the endpoint of the project.
azure-ai-project-endpoint: This parameter is required and must be set to the URL endpoint of your Microsoft Foundry project. This aligns with setting project-endpoint.
Reference:
https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action
질문 # 123
You have an app that uses Azure Al Custom Vision and a custom trained classifier to identify products in images. You need to add new products to the classifier. The solution must meet the following requirements:
* Minimize how long it takes to add the products.
* Minimize development effort.
Which five actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
정답：
설명：
Explanation:
Because the existing classifier is an Azure AI Custom Vision project, the lowest-effort workflow is performed directly in the Custom Vision portal , not Azure Machine Learning studio or Vision Studio. Open the existing project so that the new product classes can be incorporated into its current training dataset.
Next, upload representative sample images of each new product. The images should include sufficient variation in viewing angle, lighting, background, size, and presentation to support reliable classification.
Label each image with the appropriate new product tag. Custom Vision uses these tags as the target classes during supervised training. Microsoft's portal workflow explicitly supports uploading and manually tagging images without requiring application code.
Retrain the classifier after the labeled images have been added. Training creates a new iteration based on all current training images and tags, including the newly introduced product categories.
Finally, publish the trained iteration to the prediction resource. Publishing makes that iteration available through the Custom Vision Prediction API used by the application.
Study Guide alignment: create, train, evaluate, retrain, publish, and consume custom image- classification models .
질문 # 124
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?
정답：A
설명：
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
질문 # 125
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?
정답：B
설명：
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/
질문 # 126
......
Microsoft인증 AI-103시험은 중요한 IT인증자격증을 취득하는 필수시험과목입니다Microsoft인증 AI-103시험을 통과해야만 자격증 취득이 가능합니다.자격증을 많이 취득하면 자신의 경쟁율을 높여 다른능력자에 의해 대체되는 일은 면할수 있습니다.Itexamdump에서는Microsoft 인증AI-103시험대비덤프를 출시하여 여러분이 IT업계에서 더 높은 자리에 오르도록 도움드립니다. 편한 덤프공부로 멋진 IT전문가의 꿈을 이루세요.
AI-103유효한 덤프문제: https://www.itexamdump.com/AI-103.html