当社Xhs1991は常に業界標準を順守しています。最新のAI-103実際のダンプの定期的な試験問題に精通している専門家の助けを借りて。彼らはあなたの知識に飢えた心を満たすことができます。また、AI-103試験クイズは品質保証されています。ここ数年、お客様に高品質のAI-103実践教材を提供することに専念することで、すべてのコンテンツが実践と記憶に不可欠な部分であることを保証できます。
| Section | Objectives |
|---|---|
| Topic 1: Implement Natural Language Processing Solutions | - Translation and multilingual support - Language understanding and intent recognition - Text analytics and summarization |
| Topic 2: Develop Generative AI Applications and Agents | - Azure OpenAI Service integration
|
| Topic 3: Implement Computer Vision Solutions | - OCR and document intelligence - Image classification and object detection |
| Topic 4: Plan and Manage Azure AI Solutions | - Azure AI resource provisioning and configuration - Model selection and lifecycle management - Responsible AI principles and governance |
| Topic 5: Knowledge Mining and Information Retrieval | - Indexing and semantic search - Azure AI Search configuration - RAG (Retrieval Augmented Generation) patterns |
成功の秘Theは目的への不変です。 試験に合格し、認定を取得することが目的の場合。 AI-103試験クラムPDFは、試験の正しいショートカットになります。 目標を達成する可能性や方法を逃さないでください。特に、AI-103試験のクラムPDFには常に100％の合格率があります。 ほとんどの場合、選択は努力よりも重要です。 テストのきちんとした準備は、多くの時間を節約するのに役立ちます。 Microsoft AI-103試験クラムPDFは、間違いなく今後の試験に役立つでしょう。
質問 # 126
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?
正解：B
解説：
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
質問 # 127
You are building an app by using the Semantic Kernel.
You need to include complex objects in the prompt templates of the app. The solution must support objects that contain subproperties.
Which two prompt templates can you use? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
正解：C、E
解説：
Semantic Kernel provides support for the following template formats:
semantic-kernel - Built-in Semantic Kernel format.
handlebars - Handlebars template format.
liquid - Liquid template format
The Semantic Kernel prompt template language is a simple way to define and compose AI functions using plain text. You can use it to create natural language prompts, generate responses, extract information, invoke other prompts or perform any other task that can be expressed with text.
Reference:
https://learn.microsoft.com/en-us/semantic-kernel/concepts/prompts/prompt-template-syntax
質問 # 128
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 Microsoft Foundry project that contains an agent. The agent generates summaries from retrieved policy documents.
Users report that some responses omit required regulatory clauses, even when the clauses are present in the retrieved content.
You need to improve response completeness.
Solution: You run an evaluation flow that scores responses for completeness and blocks responses that fall below a defined threshold.
Does this meet the goal?
正解：A
解説：
Correct:
* You add a reflection pass that regenerates the response if the required clauses are missing.
This is Self-Correction Strategy: A reflection pass allows an agent to evaluate its own initial output against specified constraints (e.g., checking for the presence of mandatory regulatory clauses). If the required text is missing, the agent triggers a programmatic self-correction or regeneration loop to include them before final delivery.
Incorrect:
* You increase the value of the max_tokens parameter.
Increasing the max_tokens parameter prevents the response from being cut off mid-sentence due to length constraints. However, it does not force the model's logic to explicitly include missing information that it chose to leave out earlier in the text.
* You increase the value of the temperature parameter.
Raising the temperature parameter increases randomness and creativity. For rigid compliance tasks like summarizing regulatory documents, higher temperature actually increases the risk of hallucination and omission.
* You run an evaluation flow that scores responses for completeness and blocks responses that fall below a defined threshold.
Evaluation Flow Block: Running an evaluation flow to score completeness and blocking bad responses identifies and stops low-quality outputs, but it does not fix or actively improve the response completeness. It simply filters failures out of the system.
Reference:
https://pub.towardsai.net/reflection-with-llm-how-to-make-ai-review-its-own-work-2db122fca1d8
質問 # 129
You build a chatbot that uses the Azure OpenAI GPT-4 model to generate song lyrics.
You need to ensure that responses do NOT contain lyrics from popular songs that might have been ingested during model training.
Which Azure AI Content Safety API should you use?
正解：D
解説：
The Protected material text detection feature in Azure AI Content Safety is specifically designed to identify and block responses that may contain copyrighted or protected content, such as lyrics from popular songs. Since GPT-4 may have been trained on publicly available data, this feature helps ensure that the chatbot does not generate copyrighted lyrics by detecting and filtering out protected material.
質問 # 130
You configure Azure AI Content Safety to moderate user-uploaded images in a generative application. During testing, a colleague claims an image returned a Violence severity score of 3.
Why is this result impossible?
正解：C
解説：
The Azure AI Content Safety image model uses a trimmed severity scale that returns only 0, 2, 4, and 6, so an odd value such as 3 cannot occur for image content. The text model uses the full 0 to 7 scale, which is where odd-numbered severities appear.
質問 # 131
......
私たちは本当にお客様の貴重な意見をAI-103試験資料の作りの考慮に入れます。おそらく、君たちは私たちのAI-103試験資料について何も知らないかもしれません。でも、私たちのAI-103試験資料のデモをダウンロードしてみると、全部わかるようになります。そのデモはAI-103試験資料の一部を含めています。
AI-103最新受験攻略: https://www.xhs1991.com/AI-103.html