Key details for this exam, checked against the published exam outline
Each question shows the correct answer and an explanation of why it is right
You have a Microsoft Foundry project that contains an agent and an image generation model deployment.
The agent generates original images from user-supplied product photos.
You need to ensure that the generated images maintain the product identity and visual characteristics of the provided photo.
What should you do?
The correct answer is A. Set the input_fidelity parameter to high. The scenario requires the generated image to preserve the identity and visual characteristics of the user-supplied product photo. In Azure OpenAI image editing and generation workflows, input_fidelity controls how strongly the model attempts to match the style and features of the input image. Microsoft's documentation states that this parameter lets you make subtle edits without changing unrelated areas, and that high input fidelity preserves input-image features more accurately than standard mode.
Including a prompt and input image is necessary for image-guided generation, but it does not by itself maximize preservation of the product's appearance. The explicit preservation control is input_fidelity, and the requirement specifically asks to maintain product identity and visual characteristics. A groundedness detection filter applies to validating generated text against source data, not preserving visual features in image generation. Lowering temperature may reduce randomness in text generation, but it is not the image-control parameter used to retain product-specific visual details. Reference topics: Azure OpenAI image generation, image edit API, input images, input_fidelity, image-to-image generation, and visual identity preservation.
You have a Microsoft Foundry project that generates product marketing images from text prompts.
After publishing several images, the legal team at your company identifies a competitor's logo on a sign in the background of an image.
You need to remove only the logo, while preserving the rest of the image.
What should you do?
The correct answer is C because the requirement is a localized image edit: remove only the competitor logo while preserving the rest of the already generated image. Azure OpenAI image editing is designed for modifying existing images based on a text instruction, rather than regenerating the entire image from scratch. Microsoft's Azure OpenAI image guidance states that the Image Edit API modifies existing images and requires an input image as part of the request. In a mask-based inpainting workflow, the mask identifies the exact region to change, allowing the model to replace only the logo area while retaining surrounding background, composition, lighting, and product content.
Increasing prompt guidance strength would affect adherence during generation, but it would not safely remove a specific logo from a completed image. Modifying the original prompt and regenerating may create a different image and does not guarantee preservation of the approved visual content. Rerunning with a different random seed also changes the image unpredictably and may introduce new brand or legal issues. Mask-based inpainting is the minimal-change remediation method for post-generation brand cleanup. Reference topics: Azure OpenAI image editing, inpainting, mask-guided edits, image generation governance, and computer vision solutions.
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?
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.
You have a Microsoft Foundry project that contains an agent. The agent uses Azure Al Search as the retriever.
You plan to ingest PDFs into an Azure Al Search index to ensure that the agent can ground responses in texts in both documents and embedded images.
Users require citations that link to the source files.
You need to ensure that during indexing, the images are extracted into a structure that can be used as input for the built-in optical character recognition (OCR) skill.
Which indexing approach should you use?
The correct indexing approach is to use an indexer to extract image data into a normalized_images collection. In Azure AI Search enrichment pipelines, embedded images in PDFs are not passed directly from the text content field into OCR. Instead, the indexer must perform document cracking and image extraction by enabling the indexer image action. Microsoft's Azure AI Search documentation states that image-processing skills such as OCR and image analysis expect normalized images, and that enabling imageAction causes embedded images to be extracted and normalized for downstream skills.
The OCR skill is designed to receive image input from /document/normalized_images/*. Microsoft's skillset tutorial specifically states that the OCR skill assumes a normalized_images field exists and that this field is generated by setting the indexer imageAction configuration to generateNormalizedImages. The document extraction skill reference also confirms that generateNormalizedImages creates an array of normalized images during document cracking for OCR and image analysis.
Option A is incorrect because OCR does not run directly against the index content field. Option B maps outputs after enrichment; it does not extract images. Option D reshapes data but does not create the required normalized image collection. Reference topics: Azure AI Search indexers, AI enrichment, OCR skill, imageAction, and normalized_images.
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 add a reflection pass that regenerates the response if the required clauses are missing.
Does this meet the goal?
Yes, the solution meets the goal. The problem is not retrieval availability, because the required regulatory clauses are already present in the retrieved policy documents. The failure occurs during generation: the agent produces a summary that omits required content. A reflection pass is the correct application-level control because it adds a verification step before the response is returned. The pass can compare the draft answer against the retrieved clauses, detect missing mandatory content, and trigger regeneration or revision until the summary includes the required clauses.
This aligns with Microsoft Foundry's evaluation and observability model, where generated responses are assessed for reliability, groundedness, relevance, and quality throughout the AI application lifecycle. Foundry observability guidance describes evaluation as a mechanism for measuring response quality and improving AI outputs across development and production workflows. The Azure AI evaluation SDK also defines completeness as the extent to which a generated response contains all necessary and relevant information with respect to the provided ground truth. Reflection operationalizes that quality check inside the application flow, rather than merely reporting the defect after the fact. Reference topics: model reflection, response completeness, RAG generation quality, retrieved context verification, and agent response optimization.
You have an application that processes scanned PDF invoices. The invoices have varied layouts and include multipage tables.
You have a pipeline that uses optical character recognition (OCR) and extracts totals and invoice numbers. The results are often incorrect because the document structure is ignored.
You need to implement a solution that provides OCR, layout analysis, and template-generalizing field extraction. The solution must NOT require training a custom model. The solution must minimize administrative effort.
What should you include in the solution?
The correct answer is Azure Content Understanding in Foundry Tools. The scenario requires more than basic OCR because scanned invoices have varied layouts and multipage tables. Content Understanding is designed for intelligent document processing and provides OCR, layout detection, table extraction, field extraction, confidence scores, and grounding in a managed service. Microsoft describes Content Understanding as a service that transforms unstructured content into structured outputs and supports invoice processing by extracting and validating fields from complex documents.
This also meets the requirement to avoid training a custom model. Content Understanding includes prebuilt and domain-specific analyzers, including invoice and procurement-style document processing, and Microsoft states that these analyzers provide structured extraction without custom training. It generalizes across visual template variations by using semantic document categories rather than requiring separate models per invoice layout.
Azure Machine Learning would increase administrative effort because it requires model development, training, deployment, and monitoring. Azure Language is optimized for text analytics tasks such as classification and entity extraction after text is available, but it does not provide document layout analysis or multipage table structure extraction. Reference topics: Content Understanding, intelligent document processing, OCR, layout analysis, analyzers, field schemas, and structured extraction.
You are deploying a support agent that enables users to upload photos.
You need to automatically classify uploaded images for harmful content. The solution must block content based on severity levels.
What should you do?
The correct answer is A. Implement image moderation. Azure AI Content Safety provides image analysis that classifies uploaded images for harmful content, including harm categories such as hate, sexual content, violence, and self-harm. Microsoft's Content Safety overview states that the Analyze Image API scans images for harmful content with multi-severity levels, which directly matches the requirement to automatically classify uploaded photos and block content based on configured severity thresholds.
Prompt Shields are intended to detect prompt injection and jailbreak-style attacks against generative models, not to classify image harm categories. Keyword scanning OCR output would only detect visible text extracted from the image and would miss visual harm in the image itself. Blocklists can help match known words or custom patterns, but they are not a complete image safety classifier and do not provide the built-in severity-based image harm classification required here. Image moderation is therefore the correct control for user-uploaded photos. Reference topics: Azure AI Content Safety, image moderation, harm categories, severity levels, Foundry guardrails, and responsible AI controls.
Exam domains verified against: Official Microsoft AI-103 exam guide, last checked October 2026.
Choose the right Foundry services and models for your AI workload, then design the infrastructure to support agents and generative applications. You need to know how to set up model deployments, integrate CI/CD pipelines, manage quotas and costs, monitor drift and safety, and apply security controls like managed identity and role policies. Configuration of responsible AI guardrails and audit logging also falls into this area.
Build applications using LLMs and multimodal models, implement retrieval-augmented generation with proper grounding, and create agents with conversation tracking and tool integration. This domain covers designing workflows, evaluating model quality and safety, integrating SDKs and connectors, tuning generation behavior with prompt engineering, and orchestrating multi-agent systems with monitoring and error handling.
Sample question from this domain above: Q5
Generate images and videos from text and reference media, configure editing workflows like inpainting and prompt-driven modifications, and implement video editing. You also need to analyze visual content using multimodal models, generate captions and alt text for accessibility, extract visual characteristics with Content Understanding, and detect unsafe visual content while protecting against prompt injection through embedded images.
Extract entities, topics, summaries, and structured outputs from text using generative prompting and Foundry Tools. Configure detection of sentiment, tone, safety issues, and sensitive content. Build translation solutions using Azure Translator or LLM-powered flows, and customize outputs for domain-specific tasks like compliance summarization. This includes implementing speech-to-text and text-to-speech for agent interactions.
Build retrieval pipelines that ingest and index documents, images, audio, and video. Configure semantic and hybrid vector search for grounding, enrich content using custom or built-in skills for text and layout, and implement RAG ingestion including optical character recognition. Connect these retrieval pipelines directly to workflows and agent tools so that information flows seamlessly through your system.
Common questions about the exam itself
