AI-103: Developing AI Apps and Agents on AzureDemo

The Document Layout skill (Microsoft.Skills.Util.DocumentIntelligenceLayoutSkill) calls the Azure Document Intelligence layout model to analyze document structure. When its extractionOptions parameter includes "images" and "locationMetadata", the skill's outputs (text_sections and normalized_images) each include a locationMetadata object containing pageNumber and boundingPolygons, giving precise page-level citation data for both text and images. Because it relies on the Document Intelligence layout model, it also detects and preserves table structure, including tables that span multiple pages, as part of its structural analysis. This makes it the single built-in skill that satisfies both the text/image location metadata requirement and the multi-page table extraction requirement, unlike Document Extraction (no location metadata), GenAI Prompt (generative enrichment, not structural extraction), or Azure Content Understanding (a separate content analysis service/skill not aligned with this classic layout-based bounding polygon output).