Microsoft AI-103 Practice Test Questions Answers

type: ask_question

condition: approval == " approved "

The approval step must use type: ask_question because the workflow must pause and wait for a human response before the refund execution proceeds. Microsoft Foundry workflows support human-in-the-loop patterns where the workflow asks the user a question and awaits input before continuing; this pattern is explicitly intended for approval requests and clarifying questions. The workflow guidance also identifies workflows as declarative sequences that orchestrate agents and business logic, including branching logic and human-in-the-loop steps.

The refund execution step must use condition: approval == " approved " so that the second invocation of PaymentAgent runs only when the approval response matches the required approval value. Using true would always execute the refund, bypassing the approval control. Using propose_refund.output != null would only confirm that the first agent step produced output; it would not prove that a human approved the refund. data_transformation is also incorrect for the approval node because it sets or parses values rather than pausing for user input. Reference topics: Microsoft Foundry workflows, human-in-the-loop workflow pattern, YAML workflow editing, agent orchestration, conditional execution, and workflow approval gates.

credential = DefaultAzureCredential

response = openai_client.responses.create

The correct authentication class is DefaultAzureCredential because the requirement is Microsoft Entra-based authentication, and this credential supports managed identity in hosted Azure environments. The Microsoft Foundry quickstart for Python shows the project client being created with AIProjectClient(endpoint=PROJECT_ENDPOINT, credential=DefaultAzureCredential()), which enables the Foundry SDK to authenticate without using API keys or embedded secrets. The same guidance shows creating an OpenAI-compatible client from the project by calling project.get_openai_client().

The correct Responses API method is create because the application must send a new prompt to the deployed model and receive generated output. Microsoft’s Foundry quickstart demonstrates the exact pattern: response = openai.responses.create(model= " gpt-5-mini " , input= " ... " ), followed by reading response.output_text. The retrieve operation is used to fetch an existing response, not submit a new inference request, and compact is not the correct method for generating a model response. AzureKeyCredential would violate the Microsoft Entra managed identity requirement, while ClientSecretCredential uses an application secret rather than managed identity. Reference topics: Microsoft Foundry SDK, AIProjectClient, Microsoft Entra authentication, DefaultAzureCredential, and Azure OpenAI Responses API.

The correct answer is A. Enable estimateFieldSourceAndConfidence . Azure Content Understanding document analyzers support an opt-in confidence and grounding capability for field extraction. Microsoft documentation states that to opt in for confidence and grounding, you set estimateFieldSourceAndConfidence = true in the analyzer configuration, or configure estimateSourceAndConfidence = true for specific fields. This enables each extracted field to include a confidence score and references back to the original document source location.

This directly satisfies both stakeholder requirements: source grounding allows users to verify where the extracted value came from in the scanned PDF, and the confidence score supports downstream automation rules, such as sending low-confidence fields to manual review. Microsoft’s analyzer improvement guidance describes confidence scoring as a value between 0 and 1 and grounding as references or citations for extracted outputs to the original document content.

Generative extraction does not guarantee per-field confidence and source grounding. enableSegment is used for document segmentation, not confidence scoring. Labeled samples can improve extraction quality, but they do not by themselves enable confidence and grounding output. Reference topics: Content Understanding document analyzers, field extraction, confidence scoring, grounding, and RAG ingestion.

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.

The correct configuration is advanced data parsing because the issue is not merely OCR; the ingestion job must preserve document structure for reliable RAG retrieval. Microsoft guidance for advanced parsing states that it automatically detects tables across all pages, including tables in scanned documents, merges tables that span multiple pages, restores column headers, and creates table chunks with metadata such as table index, shape, page numbers, section headings, and table previews. This directly satisfies the requirement to retrieve specific rows from multipage tables while retaining source-page context.

Basic parsing with fixed-size chunking would flatten the document into arbitrary text fragments, which is the current failure mode. OCR with page-level chunking improves text extraction from scanned PDFs, but it does not provide structure-aware chunks that preserve headings and table relationships across pages. Storing each page as a single chunk is too coarse for row-level retrieval and can bury relevant table rows in excessive context. Advanced data parsing is purpose-built for RAG ingestion because it produces semantically meaningful, retrievable chunks and enriches them with metadata needed for citations and grounding. Reference topics: RAG ingestion, advanced parsing, OCR, table extraction, structure-aware chunking, page metadata, and Azure Blob Storage document ingestion.