What's more, part of that ExamDiscuss AI-103 dumps now are free: https://drive.google.com/open?id=1XmCJODzf_x6CMI11Uvk3Sgw4F35pJIP_
If you have ExamDiscuss's Microsoft AI-103 exam training materials, we will provide you with one-year free update. This means that you can always get the latest exam information. As long as the Exam Objectives have changed, or our learning material changes, we will update for you in the first time. We know your needs, and we will help you gain confidence to pass the Microsoft AI-103 Exam. You can be confident to take the exam and pass the exam.
| Section | Weight | Objectives |
|---|---|---|
| Implement text analysis and information extraction solutions | 10-15% | - Analyze and extract information
|
| Implement computer vision solutions | 10-15% | - Analyze visual content
|
| Implement generative AI solutions | 25-30% | - Optimize and evaluate models
|
| Implement agentic solutions | 20-25% | - Build AI agents
|
| Plan and manage Azure AI solutions | 25-30% | - Manage AI solution lifecycle
|
>> Reliable Microsoft AI-103 Study Plan <<
We really take the requirements of our worthy customers into account. Perhaps you know nothing about our AI-103 study guide. Our free demos of our AI-103 learning questions will help you know our study materials comprehensively. As we have three different kinds of the AI-103 Practice Braindumps, accordingly we have three kinds of the free demos as well. They are a small part of the questions and answers of the AI-103 learning quiz.
NEW QUESTION # 98
You have an app named App1 that uses a Microsoft Foundry multimodal model deployment.
App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context.
Some uploaded images contain embedded text.
You need to prevent potentially malicious instructions from being processed by the model.
What should you use?
Answer: D
Explanation:
The correct answer is D. prompt shields for documents . The OCR text is extracted from uploaded images and appended as additional context, so it is third-party content rather than a direct trusted user instruction.
Microsoft Foundry Prompt Shields distinguish between user prompt attacks , which are malicious instructions directly supplied as user prompts, and document attacks , which are hidden or embedded instructions in third-party content such as documents, emails, webpages, or grounded data. Microsoft also notes that Prompt Shields analyze indirect attacks embedded in input documents or images.
This scenario is an indirect prompt injection pattern: an uploaded screenshot may contain text that says to ignore the system prompt or perform unauthorized actions. Because the OCR output is being passed to the multimodal model as contextual content, the appropriate protection is Prompt Shields for documents, which scans externally sourced context for malicious embedded instructions before generation. Protected material text detects known copyrighted text in model outputs, not prompt injection. Image moderation detects harmful visual content categories, not malicious instructions in extracted context. Prompt Shields for user prompts are less precise here because the risk comes from document-like content derived from the uploaded image.
Reference topics: Prompt Shields, document attacks, indirect prompt injection, multimodal safety, OCR- derived context, and Foundry guardrails.
NEW QUESTION # 99
You have a Microsoft Foundry project that contains a customer support agent grounded in internal documentation.
After a recent update, users report the following issues:
* Some answers are unsupported by retrieved documents.
* A small number of responses are flagged for policy violations.
You need to evaluate each issue.
Which observability signals should you use for each issue? To answer, drag the appropriate observability signals to the correct issues. Each observability signal may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Answer:
Explanation:
Explanation:
Unsupported responses: Groundedness evaluation metrics
Policy violations: Risk and safety metrics
For unsupported responses, use Groundedness evaluation metrics . In a Retrieval Augmented Generation scenario, the key question is whether the generated answer is supported by the retrieved context. Microsoft Foundry built-in evaluators define Groundedness as the RAG metric that measures how grounded a response is in retrieved context and returns a model-based score; Groundedness Pro evaluates whether the response is grounded in retrieved context by using Azure AI Content Safety. This directly matches answers that are unsupported by internal documentation.
For policy violations, use Risk and safety metrics . Microsoft Foundry risk and safety evaluators assess generated responses for safety risks such as hate and unfairness, sexual content, violence, self-harm, protected material, indirect attacks, code vulnerability, ungrounded attributes, prohibited actions, and sensitive data leakage. The guidance states that these evaluators assign risk and safety severity or pass/fail outcomes for AI responses and agent behavior.
Latency breakdown traces diagnose performance, not correctness or policy compliance. Token usage analytics diagnose cost and prompt/response size, not unsupported claims or safety violations. Reference topics:
Microsoft Foundry observability, RAG evaluators, groundedness, risk and safety evaluators, and agent quality evaluation.
NEW QUESTION # 100
You have a Microsoft Foundry project that contains an agent.
You need to process mixed-format documents that contain scanned text, tables, and multicolumn layouts. The extracted content must preserve the document structure and be converted into the Markdown format for downstream reasoning.
What should you configure first?
Answer: A
NEW QUESTION # 101
A developer needs a managed identity to call a Microsoft Foundry project endpoint to run inference and use agents. Security policy requires the least-privilege role that grants data-plane access and nothing more. Which built-in role should you assign to the managed identity?
Answer: C
Explanation:
Foundry User is the least-privilege built-in role for Microsoft Foundry projects and grants the data- plane actions needed to call a project endpoint, run inference, and use agents. Microsoft recommends assigning the project's managed identity the Foundry User role on the Foundry resource.
NEW QUESTION # 102
You have a Microsoft Foundry project that contains an agent. The agent uses two tools to perform the following actions:
- Use Azure AI Search to retrieve answers from a private product
documentation index.
- Use the web search tool to retrieve public information on the
internet.
You need to ensure that for a specific run, the agent deterministically retrieves information only from the internet.
To what should you set tool_choice?
Answer: A
Explanation:
To force a specific run to exclusively use public information from the internet instead of your private documents, override the tool orchestration payload at the run level. Set the tool_choice directive specifically to the web grounding tool (e.g., bing_grounding or web_search) and constrain the tools array for that run.
Reference:
https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search
NEW QUESTION # 103
......
Under the tremendous stress of fast pace in modern life, this version of our AI-103 test prep suits office workers perfectly. It can match your office software and as well as help you spare time practicing the AI-103 exam. As for its shining points, the PDF version can be readily downloaded and printed out so as to be read by you. Itโs really a convenient way for those who are fond of paper learning. With this kind of version, you can flip through the pages at liberty and quickly finish the check-up AI-103 Test Prep. And you can take notes on this version of our AI-103 exam questions.
Braindumps AI-103 Downloads: https://www.examdiscuss.com/Microsoft/exam/AI-103/
BONUS!!! Download part of ExamDiscuss AI-103 dumps for free: https://drive.google.com/open?id=1XmCJODzf_x6CMI11Uvk3Sgw4F35pJIP_