Get Your CertAI-103PlayCompete
‹ All AI-103 questions

AI-103 Practice Question 90: Knowledge Store Projections

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 9 · question 10 of 10

Implement information extraction solutionshard

An enterprise runs an Azure AI Search indexer and skillset over scanned invoices, extracting key phrases, entities, and structured line-item tables. Separately, the data engineering team wants to run Power BI dashboards and a nightly Azure Data Factory job over that same enriched, extracted content (the tables and the per-document structured data) entirely independent of the search index, without querying Azure AI Search at query time. They also want the freedom to later change the search index's technology without breaking that downstream pipeline.

What should they add, and where does the enriched content land?

Select one answer
Show answer and explanation

Answer:

  • B. Add a knowledge store definition to the skillset, using table and object projections; the enriched content is written to Azure Table Storage and Blob Storage, and any tool that connects to Azure Storage can consume it, with no query support from Azure AI Search itself

A knowledge store is secondary storage for a skillset's AI-enriched output, physically Azure Table Storage, Azure Blob Storage, or both. Table projections give tabular structures for tools like Power BI or Data Factory, and object projections write a hierarchical JSON document per enriched item to Blob Storage. Microsoft states the decoupling directly: "Any tool or process that can connect to Azure Storage can consume the contents of a knowledge store," and "there's no query support in Azure AI Search for retrieving content from a knowledge store", so the downstream pipeline never touches the search index or its query API, satisfying both the independence and the future index-technology-change requirements.

- A is wrong because semantic ranker is a query-time relevance feature for the search index itself; using it still means Power BI queries Azure AI Search, which is exactly the coupling the team wants to remove. - C is wrong because it's the plausible trap: knowledge store projections are Azure Table Storage and Blob Storage only. Cosmos DB isn't a documented knowledge store projection target; it's the technology behind a different feature (Foundry Agent Service's bring-your-own thread storage), not this one. - D is wrong because a second search index still requires Power BI and Data Factory to query Azure AI Search, and it doubles indexing cost and complexity instead of decoupling anything.

Reference: Knowledge store concepts

Practice Test 9 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.
AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.
How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.
AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.
Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.
Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.
AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.
What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.
Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.