You are integrating knowledge for multi-agent consumption: product manuals in Azure AI Search, live inventory via an MCP tool, and policy PDFs requiring semantic retrieval. Which knowledge integration design is most appropriate?
Select an answer to reveal the explanation.
Short Explanation
Different knowledge, different channels. Manuals/policies go through semantic/hybrid RAG search; live inventory is a transactional MCP tool; each source keeps its ACLs. Option D. Public web only (A) skips enterprise sources. Hourly prompt stuffing of inventory (B) is stale and huge. Filename-only (C) kills semantic discovery of policy language.
Full Explanation
Knowledge integration for multi-agent consumption includes search, RAG, MCP-available sources, and semantic search. Option D assigns each knowledge type to the right access pattern with security preserved.
Option A loses private corpus fidelity and governance.
Option B confuses operational data with prompt memory and scales poorly.
Option C underpowers policy retrieval needs.
Exam tip: RAG for documents; tools/MCP for live systems of record.