--- title: Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템 description: Naver Place AI Platform (PAIP) interns built a backoffice AI agent combining RAG and MCP to solve internal knowledge fragmentation across Confluence, GitHub,... canonical: https://daily.dev/posts/3p0wbobld twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템 | daily.dev og:description: Naver Place AI Platform (PAIP) interns built a backoffice AI agent combining RAG and MCP to solve internal knowledge fragmentation across Confluence, GitHub,... og:url: https://daily.dev/posts/3p0wbobld og:image: https://api.daily.dev/og/posts/3P0WbObLD.png og:image:alt: Post cover image og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템 **[Korean Devs](https://daily.dev/sources/koreandevs)** · [@seyoungcho](https://daily.dev/seyoungcho) · 0 upvotes · 0 comments ## Summary Naver Place AI Platform (PAIP) interns built a backoffice AI agent combining RAG and MCP to solve internal knowledge fragmentation across Confluence, GitHub, and external technical docs. The system uses a hybrid search pipeline (Dense + BM25 Sparse via Milvus, fused with RRF) followed by an LLM-based reranker, all exposed as MCP tools callable from Cursor or Dify. A Smart Search pre-retrieval layer normalizes queries—handling relative time expressions, author name variants, and document type filtering—before executing hybrid retrieval. Compared to a lexical search MCP baseline in an A/B test with onboarding scenarios, the new system achieved 2× response satisfaction, 1.4× faster responses, 66% fewer tokens, and 49% fewer tool calls. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [EP202: MCP vs RAG vs AI Agents](https://daily.dev/posts/ep202-mcp-vs-rag-vs-ai-agents-jowyr3vcd) · ByteByteGo · 5 upvotes · 0 comments - [NextGen Search - Where AI Meets OpenSearch Through MCP](https://daily.dev/posts/nextgen-search---where-ai-meets-opensearch-through-mcp-lljqddztt) · InfoQ · 2 upvotes · 0 comments - [RAG vs. MCP: Differences, use cases, and when to use each](https://daily.dev/posts/rag-vs-mcp-differences-use-cases-and-when-to-use-each-sp8efosoj) · Meilisearch · 0 upvotes · 0 comments - [Building Connected AI Agents: How RAG, MCP, and A2A Form the Modern Google AI Stack](https://daily.dev/posts/building-connected-ai-agents-how-rag-mcp-and-a2a-form-the-modern-google-ai-stack-1tteka54k) · Medium · 7 upvotes · 0 comments - [Building effective AI agents with Model Context Protocol \(MCP\)](https://daily.dev/posts/building-effective-ai-agents-with-model-context-protocol-mcp--1k6pmnpvj) · Red Hat Developer · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#rag](https://daily.dev/tags/rag), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/3p0wbobld) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/3p0wbobld","headline":"Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템","text":"Shared: Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템","url":"https://daily.dev/posts/3p0wbobld","datePublished":"2026-02-19T00:45:58.507Z","dateModified":"2026-02-19T00:46:46.095Z","author":{"@type":"Person","name":"SeyoungCho","url":"https://daily.dev/seyoungcho","image":"https://media.daily.dev/image/upload/s---QniJFEK--/f_auto/v1724901542/avatars/avatar_O3ucZSadxc0iLADSOH3rX","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":9350}},"image":"https://media.daily.dev/image/upload/s--2-1xRawN--/f_auto/v1722860399/public/Placeholder%2011","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/znp3fszYt"},"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/koreandevs","name":"Korean Devs"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Korean Devs","item":"https://daily.dev/squads/koreandevs"},{"@type":"ListItem","position":3,"name":"Backoffice AI Agent 구축기 — RAG+MCP 기반 플레이스AI 특화 지식 검색 시스템"}]} ```