Important Microsoft AI-103 Exam Questions

Answer: D, E

Explanation:

The correct built-in skills are Azure OpenAI Embedding and Text Split. The case study requires an indexing pipeline that enables semantic and vector search over the product sheets stored in Azure Blob Storage, so Agent1 can retrieve relevant product information for natural language customer questions. For a RAG pipeline, long PDF content must first be broken into retrievable chunks, and each chunk must then be vectorized for semantic similarity retrieval.

Microsoft's Azure AI Search integrated vectorization guidance states that you create a skillset that calls the Text Split skill for chunking and the Azure OpenAI Embedding skill to vectorize the chunks. The Text Split skill breaks text into chunks and provides positional metadata, making it suitable when downstream embedding skills have input-length limits. The Azure OpenAI Embedding skill connects to an embedding model deployed in Azure OpenAI or a Microsoft Foundry project and generates embeddings during indexing.

Language Detection, Entity Recognition, and key phrase extraction can enrich text, but they do not create vector embeddings. Merge is useful for combining OCR text with document text, but it does not satisfy the core vector-search requirement. Reference topics: Azure AI Search skillsets, Text Split skill, Azure OpenAI Embedding skill, integrated vectorization, and RAG indexing.

Answer: A

Explanation:

The correct role is Cognitive Services OpenAl User. The application is using DefaultAzureCredential, so az login only proves the developer's Microsoft Entra identity and enables token acquisition. It does not by itself grant authorization to the model deployment. Azure OpenAI and Microsoft Foundry separate authentication from authorization; Microsoft Entra ID provides token-based authentication, while Azure RBAC controls whether the signed-in principal can perform data-plane actions such as model inference. Microsoft's Foundry guidance states that Microsoft Entra ID supports granular RBAC and that data-plane operations include runtime usage such as chat completions and embedding generation.

For Azure OpenAI resources, the Cognitive Services OpenAI User role specifically allows users to make inference API calls with Microsoft Entra ID against deployed models, while preventing higher-privilege actions such as creating deployments, copying keys, fine-tuning, or managing the resource.

The other roles are not least privilege. Contributor grants broad management-plane permissions. Cognitive Services User is broader and less specific than the Azure OpenAI inference role. Cognitive Services Data Reader is read-oriented and does not provide the required model inference data action. Reference topics: Microsoft Foundry authentication and authorization, Azure RBAC, Microsoft Entra ID keyless authentication, Azure OpenAI v1 API, and least-privilege model inference.

Answer: C

Explanation:

The correct answer is C because the requirement is structured field extraction from invoices across varying templates, not only OCR or layout preservation. Azure Content Understanding analyzers are reusable configurations that combine content extraction, AI-powered analysis, and structured data output, and Microsoft states that custom analyzers can be created for specific extraction needs. In this case, the analyzer schema should define fields such as invoice number, invoice date, vendor name, and total amount so the output can be returned as structured JSON for downstream RAG grounding.

The confidence-routing requirement also points to Content Understanding field confidence scores. Microsoft documentation states that every field can include a confidence score from 0 to 1, and that confidence scores can be used to automate high-confidence results while routing low-confidence results for human review. A threshold such as 0.80 is therefore an application routing rule based on the returned field confidence. The prebuilt-layout analyzer preserves layout but does not define invoice-specific business fields. Groundedness guardrails evaluate generated answers, not invoice field extraction. Azure AI Search search.score measures retrieval relevance, not extraction confidence. Reference topics: Content Understanding custom analyzers, document field extraction, structured JSON output, confidence scoring, and RAG grounding.

Answer: C

Explanation:

The correct approach is to create and reuse a conversation by storing the conversation's ID and supplying that ID on subsequent requests. In Microsoft Foundry Agent Service, conversations are durable objects with unique identifiers that can be reused across sessions. The official runtime guidance states that conversations store items, including messages, tool calls, tool outputs, and other data, and are intended for multi-turn continuity, cross-session continuity, and inspection of what happened over time. This directly satisfies the requirement to resume the same support case days later with the full historical context.

Persisting only the final model response is insufficient because it loses the full interaction chain, especially tool calls and tool outputs that may be essential to case state. Memory summarization is also not the best fit because the requirement asks for the complete history, not a compressed representation that may omit details. Reusing the conversation ID allows Foundry to maintain the conversation server-side so the next turn can reuse prior context without the client manually rebuilding prompts. Reference topics: Foundry Agent Service runtime components, conversations, conversation items, multi-turn continuity, cross-session continuity, and tool output history.

Answer: C

Explanation:

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.