AZ-900 Describe Azure architecture and services Practice Question

Answer analysis

Option-by-option breakdown

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

• ✗

  Azure Form Recognizer

  Why it's wrong here

  Azure Form Recognizer is a specialized document analysis service focused on extracting structured data such as key-value pairs, tables, and fields from forms, invoices, and receipts using prebuilt or custom models. While it can perform OCR, its output is a structured representation of the input form, not a search index over a document corpus, and it does not offer query-time full-text search or relevance ranking. Form Recognizer can be used as a skill within Cognitive Search's enrichment pipeline, but by itself it cannot power search across many documents.

• ✓

  Azure Cognitive Search

  Why this is correct

  Azure Cognitive Search is a fully managed search-as-a-service solution that creates a persistent inverted index over content from various data sources, enabling full-text, fuzzy, and faceted search with relevance scoring. It natively supports AI enrichment through skillsets that invoke OCR, entity recognition, key phrase extraction, and translation, allowing unstructured documents to be turned into searchable knowledge. This combination of indexing, query capabilities, and AI-based enrichment makes it the correct choice for building an enterprise search experience over large document collections.

• ✗

  Azure Language Understanding

  Why it's wrong here

  Azure Language Understanding (LUIS) is a conversational AI service designed to identify intents and extract entities from user utterances so that bots can understand and respond to natural language instructions. It is not a document search engine; it does not index file content, perform full-text queries, or integrate with document stores like Blob Storage for large-scale retrieval. The core purpose of LUIS is dialog and task automation, not locating information across a document collection, which is why it cannot replace Cognitive Search for that scenario.

• ✗

  Azure Text Analytics

  Why it's wrong here

  Azure Text Analytics is a natural language processing service that performs sentiment analysis, key phrase extraction, language detection, and named entity recognition on individual text inputs. It does not build a persistent searchable index or support relevance-ranked queries across a large document corpus, nor does it provide full-text search capabilities. For a scenario requiring users to find and retrieve relevant content from thousands of documents, Cognitive Search is the appropriate service because it ingests, enriches, and indexes content for querying.

Go deeper

Related to this question