Microsoft Developing AI Apps and Agents on Azure AI-103 Exam Questions

Page: 1 / 14
Total 67 questions
Question 1

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 Al 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?



Answer : B

The solution does not fully meet the goal. A prompt shield for documents is the correct control for the embedded-instruction portion of the scenario. Microsoft defines Prompt Shields as protection against prompt manipulation, including attacks embedded in third-party or document-like content that is supplied to a generative model. OCR-extracted text from uploaded images is untrusted contextual content, so document attack protection is appropriate for detecting hidden instructions that attempt to override the model's intended behavior.

However, the scenario contains two separate risks: unsafe image uploads and hidden instructions embedded in images. Prompt Shields for documents address indirect prompt injection, but they do not classify or block harmful visual content in the uploaded image itself. Azure AI Content Safety image moderation is the control that scans images for harmful content categories such as sexual content, violence, hate, and self-harm with severity levels that can be used for blocking decisions.

Therefore, document prompt shielding alone is incomplete. A complete mitigation would combine image moderation for unsafe images with Prompt Shields for document attacks, and optionally Spotlighting for lower-trust third-party content. Reference topics: Content Safety image moderation, Prompt Shields, document attacks, indirect prompt injection, and multimodal safety.


Question 2

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?



Answer : B

The solution does not fully meet the goal. Image moderation is appropriate for one part of the risk: blocking unsafe image content before the image is processed. Azure AI Content Safety provides image APIs that detect harmful content, and its harm categories and severity levels can be used to classify and block objectionable image content. This addresses unsafe photos, but it does not address hidden instructions embedded in images.

The second risk is prompt manipulation through extracted image text. After OCR extracts text from the uploaded image, that text becomes untrusted third-party content supplied to a generative model. Microsoft defines document attacks as malicious instructions embedded in third-party content, where the objective is to cause the model to execute unintended commands or alter intended behavior. Prompt Shields are the control designed to detect user prompt attacks and document attacks, including indirect attacks that come from uploaded or referenced content.

Therefore, image moderation alone is incomplete. A complete mitigation would combine image moderation for harmful visual content with Prompt Shields for document attacks, and optionally Spotlighting, so extracted or embedded text is treated as lower trust. Reference topics: Azure AI Content Safety, image moderation, Prompt Shields, document attacks, indirect prompt injection, and multimodal safety.


Question 3

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 increase the value of the temperature parameter.

Does this meet the goal?



Answer : B

The solution does not meet the goal. Increasing temperature changes the sampling behavior of the generative model, not the completeness-checking logic of the application. Microsoft's Azure OpenAI reference defines temperature as a sampling control where higher values make output more random, while lower values make output more focused and deterministic. Raising the value can increase variation and creativity, but it does not ensure that all required regulatory clauses from the retrieved policy documents are included.

The reported issue is a recall/completeness failure: relevant clauses are already present in retrieved content, but the generated summary omits them. Microsoft Foundry RAG evaluator guidance defines Response Completeness as whether a response covers critical information compared to expected information or ground truth, and distinguishes it from groundedness, which checks that responses do not go beyond grounding context.

A more suitable implementation would add a reflection, verification, or completeness review pass that compares the draft summary against the retrieved clauses and revises the response before returning it. Increasing temperature could make outputs less predictable and may worsen omission risk. Reference topics: model parameters, temperature, RAG response completeness, retrieved context, and model reflection.


Question 4

You have a Microsoft Foundry project that contains an agent.

The agent ingests scanned PDF vendor invoices that contain tables and embedded QR codes.

The agent must preserve the PDF layout in the extracted output to ensure that downstream processing can reference sections and

tables.

You plan to call Azure Content Understanding in Foundry Tools.

You need to extract content and layout elements and detect QR codes without requiring a language model deployment.

Which built-in analyzer should you use?



Answer : A

The correct built-in analyzer is prebuilt-layout because the requirement is to preserve document layout while extracting content from scanned PDFs. Microsoft's Content Understanding prebuilt analyzer guidance states that prebuilt-layout extracts content and layout elements such as words, figures, paragraphs, and tables, identifies document structure including sections and formatting, and provides detailed layout information beyond basic text extraction. It also states that prebuilt-layout does not require a language model or embedding model, which directly satisfies the no language model deployment requirement.

QR codes are handled through barcode extraction. The analyzer configuration reference states that enableBarcode detects and extracts barcodes and QR codes, returns decoded values, and supports QR Code and Micro QR Code among other barcode types. This option is supported by document-based analyzers, making it compatible with layout-oriented document processing.

prebuilt-read is insufficient because it provides OCR and barcode extraction but foundational text extraction without layout analysis. prebuilt-documentSearch is optimized for RAG ingestion and semantic analysis, which is broader than required. prebuilt-documentFieldSchema proposes extraction schemas rather than extracting full document layout. Reference topics: Content Understanding prebuilt analyzers, layout analysis, OCR, barcode detection, QR code extraction, and document-based analyzers.


Question 5

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 increase the value of the max_tokens parameter.

Does this meet the goal?



Answer : B

The solution does not meet the goal. Increasing max_tokens only raises the maximum number of tokens the model is allowed to generate. Microsoft's Azure OpenAI reference defines max_tokens as the maximum number of tokens allowed for the generated answer, and the quota guidance notes that increasing it can help when responses are being truncated.

In this scenario, the problem is not described as output truncation. The required regulatory clauses are already present in the retrieved policy documents, but the agent omits them during summarization. That is a response completeness issue: Microsoft Foundry RAG evaluator guidance defines response completeness as the recall aspect of the response, meaning the response should not miss critical information compared with expected content or ground truth.

A larger token budget might permit a longer answer, but it does not force the model to identify, verify, or include each mandatory clause. It can also increase cost and latency. The appropriate control is a reflection or completeness verification pass that checks the draft against the retrieved policy clauses and regenerates or revises the response when required content is missing. Reference topics: RAG response completeness, model output limits, max_tokens, reflection, and response validation.


Question 6

You have an Azure Speech in Foundry Tools resource that hosts a custom speech to text model deployed to a custom endpoint. An agent uses the endpoint to perform real-time speech recognition.

You are approaching the expiration date of the custom speech to text model.

What is the expected behavior when the model expires?



Answer : A

The correct answer is A. Speech recognition requests will fall back to the most recent base model for the same locale. Microsoft's custom speech model lifecycle guidance states that when a model expires, it is no longer available for transcription. For the custom endpoint route, speech recognition requests fall back to the most recent base model for the same locale. The documentation also warns that recognition results might still be returned, but the transcription may no longer reflect the domain-specific adaptation of the custom model.

This distinguishes real-time custom endpoint behavior from batch transcription behavior. Batch transcription requests that specify an expired model fail with a 4xx error, but that is not the route described in this question. The agent is using a custom endpoint for real-time recognition, so fallback to the latest base model is the expected behavior. The model is not automatically deleted merely because it expires, and it does not continue to use the expired custom model indefinitely. The operational recommendation is to update the endpoint's model before expiration by redeploying the endpoint with a newer custom model. Reference topics: Azure Speech custom speech model lifecycle, custom endpoints, model expiration, real-time speech recognition, and endpoint redeployment.


Question 7

You have a chat app in a Microsoft Foundry project and an Azure AI Search vectorized index.

You need to connect to the index to meet the following requirements:

* Complex questions must retrieve information from multiple chunks.

* Multi-turn conversations must influence retrieval planning.

* Retrievals must run in parallel to reduce latency.

Which retrieval approach should you use?



Answer : C

The correct answer is agentic Retrieval Augmented Generation (RAG) because the requirements describe the agentic retrieval pipeline in Azure AI Search. Agentic retrieval is designed for chat and copilot scenarios where a user's request can be complex, conversational, and dependent on prior turns. Azure AI Search agentic retrieval uses an LLM-assisted planning stage to break a complex request into focused subqueries, allowing the system to retrieve grounding information from multiple chunks rather than relying on a single query path. Microsoft's Azure AI Search guidance describes agentic retrieval as a multi-query pipeline for complex questions in chat and agent workflows, with subqueries that can include chat history for additional context.

This also satisfies the latency requirement because agentic retrieval runs the generated subqueries in parallel and then merges and reranks the best results for use by the generative model. Classic RAG is simpler and typically sends a single query to search, making it less suitable for multi-hop or conversational retrieval planning. Chain of thought is a reasoning technique, not an Azure AI Search retrieval approach, and iterative retrieval does not specifically provide the built-in query planning, conversation-aware retrieval, and parallel execution described here. Reference topics: Azure AI Search agentic retrieval, RAG with Azure AI Search, knowledge bases, query planning, and generative AI grounding.


Page:    1 / 14   
Total 67 questions