AI-900 Practice Question: Describe Artificial Intelligence workloads and considerations

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Using Azure Blob Storage to store and manage document files efficiently

  Why it's wrong here

  Azure Blob Storage provides cost-effective, scalable, durable object storage for document files, but it has no inherent ability to read, extract, or interpret the content inside those files. It is infrastructure that can hold source documents as inputs or store extraction outputs, yet the actual document processing AI — OCR, field extraction, and NLP — must be built separately and invoked against those blobs. Storing files efficiently is a prerequisite for many pipelines, but fails to deliver the understanding and automation described in the correct answer.

• ✓

  Automating extraction, understanding, and routing of business documents through OCR, extraction, and NLP

  Why this is correct

  This is correct because document processing AI combines OCR to read text, Azure AI Document Intelligence (formerly Form Recognizer) to extract structured fields, and NLP to understand context, classify intent, and route documents to downstream systems like Logic Apps or Power Automate. This pipeline fully automates tasks that previously required manual data entry, turning raw files into actionable business information. The emphasis is on automated understanding and action, not merely digitising or storing the file.

• ✗

  Digitising physical documents by scanning them and converting to PDF format

  Why it's wrong here

  Scanning physical documents and saving them as PDFs is only the capture phase in a document workflow; it records a static image or text layer but applies no interpretation, field extraction, or semantic analysis. Document processing AI goes far beyond digitisation by using OCR plus extraction models to understand the content, classify it, and pull meaningful data such as invoice totals or contract parties. Without this intelligence, a scanned PDF remains just a digital picture of a paper document, not a processed business record.

• ✗

  Managing document access permissions and version control in SharePoint

  Why it's wrong here

  SharePoint is a collaboration and governance platform that manages document permissions, access controls, version histories, and content lifecycle — crucial for compliance and team workflows, but not for understanding what a document means. It does not natively perform OCR, field extraction, or natural language processing on the document content to derive structured business data. While SharePoint can host documents before or after an AI pipeline, the task of extracting, understanding, and routing that information is performed by cognitive services, not by document management features.

Go deeper

Related to this question