AI-103 Certification Practice Question #52

Question

You have a Microsoft Foundry project that contains an agent.
You need to process mixed-format documents that contain scanned text, tables, and multicolumn layouts. The extracted content must preserve the document structure and be converted into the Markdown format for downstream reasoning.
What should you configure first?

Accepted Answer

The requirement is to process mixed-format documents with scanned text, tables, and multicolumn layouts, preserve the structure, and convert it to Markdown for downstream reasoning. MS Learn describes the Content Understanding document analyzer as doing precisely this — OCR of printed/handwritten text, structure-aware extraction of tables (including cross-page/spanning cells) and hierarchical sections, with Markdown output optimized for RAG. It is the component you "configure first" to feed the agent. Language text analysis (A) targets NLP tasks, not layout, and the two generative-model options (B, C) are reasoning steps that consume already-structured content rather than producing the structured Markdown. Suggested Answer and MS Learn agree; held at 89% due to no community vote data.

More AI-103 practice questions