AI-103 Certification Practice Question #47

Question

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?

Accepted Answer

The requirement is to extract content *and* layout elements (tables, sections) so downstream processing can reference structure, detect QR codes, and do so *without a language-model deployment*. `prebuilt-layout` is the content-extraction analyzer that captures words, paragraphs, tables, figures, and document structure — and, like `prebuilt-read`, it is built on `prebuilt-document` and "doesn't require a language model or embedding model." It also detects barcodes/QR codes, which Content Understanding supports across the read/layout content-extraction analyzers (QRCode is in the supported barcode list). `prebuilt-read` is eliminated because it provides OCR "without layout analysis," failing the explicit layout/table-preservation requirement; the schema and search analyzers don't fit the layout-extraction goal. The official Suggested Answer (D) matches MS Learn. Confidence 89% — strong doc support, no community votes in file.

More AI-103 practice questions