Exam AI-901 Topic 1 Question 4 Discussion

Explanation:
Box 1: No
No, an Azure Content Understanding analyzer does not return results in HTML format. Instead, it processes your input files (which can include HTML) and structures the extracted output into Markdown, JSON fields, and segments.
Box 2: No
Only if you use the newly released synchronous operations introduced in the 2026-06-01-preview API version. If you are using the standard or generally available (GA) versions of the API, the process runs asynchronously by default.
Box 3: Yes
Yes, Azure Content Understanding in Foundry Tools can ingest and extract structured information from documents, images, audio, and video files Multimodal Ingestion: Processes unstructured data across text, images, audio recordings, and video files into user-defined formats like JSON or Markdown.
Schema-Driven Extraction: Uses prebuilt or custom schemas to extract, classify, or generate specific fields without complex prompt engineering.
Confidence & Grounding: Returns confidence scores and source grounding to verify accuracy and minimize manual oversight.
Reference:
https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference
https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/whats-new