Effective context engineering for AI agents
Published Sep 29, 2025 Context is a critical but finite resource for AI agents. In this post, we explore strategies for effectively curating and managing the context that powers them. After a few years of prompt engineering being the focus of attention in applied AI, a new term has come to prominence: context engineering. Building with language models is becoming less about finding the right words
データ分æžã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆ Socrates ã®è‚²ã¦æ–¹
メルカリã§ã®AI Agentã®ç¾åœ¨åœ°ã‚’大公開㣠https://mercari.connpass.com/event/366804/
手触り感ã®ã‚ã‚‹Context Engineering - LayerX エンジニアブãƒã‚°
ã“ã¡ã‚‰ã¯LayerX AI エージェントブãƒã‚°ãƒªãƒ¬ãƒ¼2日目ã®è¨˜äº‹ã§ã™ï¼ˆ1日目ã®ponã•ã‚“ã®æ€’涛ã®TKG記事（not Tamago kake gohan）もãœã²ã”覧ãã ã•ã„）。 ã“ã‚“ã«ã¡ã¯ã€CEO室ã§AI Agent開発ã®PdMã‚’ã‚„ã£ã¦ã„ã‚‹Kenta Watanabeã§ã™ã€‚ è¿‘å¹´ã®LLM関連技術ã®æ€¥é€Ÿãªç™ºé”ã«ã‚ˆã‚Šã€è‡ªç¤¾ãƒ—ãƒãƒ€ã‚¯ãƒˆã®é–‹ç™ºã«LLMを活用ã™ã‚‹æ–¹ã‚‚増ãˆã¦ãã¦ã„ã‚‹ã®ã§ã¯ãªã„ã‹ã¨æ€ã„ã¾ã™ã€‚一方ã§ã€LLMã®ç¢ºçŽ‡çš„ãªæŒ¯ã‚‹èˆžã„ã‹ã‚‰ãƒ—ãƒãƒ€ã‚¯ã‚·ãƒ§ãƒ³ã§å®‰å®šç¨¼åƒã™ã‚‹æ©Ÿèƒ½ã‚„AI Agentã®é–‹ç™ºã«è‹¦æˆ¦ã—ã¦ã„る方もåŒæ™‚ã«å¤šã„ã®ã§ã¯ãªã„ã‹ã¨æ€ã„ã¾ã™ã€‚ ãã†ã„ã£ãŸä¸ã§ã€6æœˆé ƒã‹ã‚‰Context Engineeringã¨å‘¼ã°ã‚Œã‚‹LLMã‚’ã†ã¾ã稼åƒã•ã›ã‚‹ãŸã‚ã®æŠ€è¡“ãŒè©±é¡Œã«ãªã£ã¦ãã¾ã—ãŸã€‚Context Engineeringã¨ã„ã†ã‚ーワードãŒãƒã‚ºã‚Šå‡ºã—ãŸèµ·æºã‚„Context Engineering自体ã®è§£èª¬ã¯å„所
ã€å®Ÿä¾‹ä»˜ãã€‘ã‚ªãƒ¬ã‚ªãƒ¬ï¼ MCP Server デザインパターンã€æ±Žç”¨Agentã¸ã®ç†Ÿç·´çŸ¥ã®ãƒ—ラグイン】
クライアントã®æŽ¨è«–能力を借りã¦æ€è€ƒã‚’ä¼´ã†ã‚¿ã‚¹ã‚¯ã‚’実装ã§ãã‚‹ samplingã‚„ human in the loopã¨ã—ã¦ã® elicitationã¯é¢ç™½ã„ãªã€œã¨æ€ã£ã¦ã„ã‚‹ã®ã§ã€ã‚ˆã‘ã‚Œã°ãã“ã ã‘ã§ã‚‚見ã¦ã¿ã¦ãã ã•ã„。 1. コンセプト 昨今ã€ã‚¢ãƒ—リケーション開発ã«å¤‰åŒ–ãŒç”Ÿã˜ã¦ã„ã¾ã™ã€‚（toBã®ä¾‹ã§è€ƒãˆã¾ã™ã€‚） 「ドメインエã‚スパートã®ç†Ÿç·´çŸ¥è˜ã‚’システムã«å†™ã™ã€ã¨ã„ã†é¢ã¯å¤‰ã‚ã£ã¦ã„ã¾ã›ã‚“ãŒã€ã€Œéžå®šåž‹ãƒ»éžæ±ºå®šè«–的判æ–ã€ã€Œå®Ÿè¡Œã‚’ä¼´ã†çŸ¥æµå¯„ã‚Šã®çŸ¥è˜ã€ã®ã‚ˆã†ãª"熟練知(Expertise)"ã‚’å«ã‚ã€å®Ÿè£…ã«å†™ã™ã“ã¨ãŒã§ãる範囲ãŒå¤§ãã拡大ã—ã¦ã„ã¾ã™ã€‚ 従æ¥çš„ã«ã¯ æ©Ÿæ¢°çš„ï¼ˆãƒ«ãƒ¼ãƒ«ãƒ™ãƒ¼ã‚¹ï¼‰çŸ¥è˜ -> プãƒã‚°ãƒ©ãƒŸãƒ³ã‚°è¨€èªžï¼ˆãƒ‰ãƒ¡ã‚¤ãƒ³ãƒ¢ãƒ‡ãƒ«ï¼‰ã¨ã„ã†"写ã—"ãŒãƒ¡ã‚¤ãƒ³ã ã£ãŸã‹ã¨æ€ã„ã¾ã™ã€‚ 上記ã¯AI Agentã®ä¾‹ã§ã™ãŒã€ç†Ÿç·´çŸ¥ã‚’ MCP Serverã¨ã—ã¦å®Ÿè£…ã™ã‚‹ãƒ‘ターンã«ã¤ã„ã¦ã‚‚自分ãªã‚Šã®è€ƒãˆãŒè“„ç©ã•ã‚ŒãŸã®ã§ã€æˆ‘
マルãƒã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆã‚·ã‚¹ãƒ†ãƒ ã®ã‚¢ãƒ¼ã‚テクãƒãƒ£ãƒ¼ã‚’ç´è§£ã
ã¯ã˜ã‚ã« 2025å¹´8月5日〜6æ—¥ã«é–‹å‚¬ã•ã‚ŒãŸ Google Cloud Next Tokyo ã®ãƒ–レークアウトセッションã§ã€å›³ã®ã‚ˆã†ãªãƒžãƒ«ãƒã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆã‚·ã‚¹ãƒ†ãƒ ã®ãƒ‡ãƒ¢ã‚’紹介ã—ã¾ã—ãŸã€‚ã“ã‚Œã«å¯¾ã—ã¦ã€äºˆæƒ³å¤–ã«å響ãŒå¤§ããã€è©³ã—ã„アーã‚テクãƒãƒ£ãƒ¼ã‚’知りãŸã„ã¨ã„ã†å•ã„åˆã‚ã›ã‚’多数ã®æ–¹ã‹ã‚‰ã„ãŸã ãã¾ã—ãŸã€‚ãã“ã§ã“ã®è¨˜äº‹ã§ã¯ã€ã“ã®ãƒ‡ãƒ¢ã‚·ã‚¹ãƒ†ãƒ ã®ã‚¢ãƒ¼ã‚テクãƒãƒ£ãƒ¼è¨è¨ˆã‚’例ã«ã—ã¦ã€ADK ã«ã‚ˆã‚‹å®Ÿè£…例ã¨ã‚ã‚ã›ã¦ãƒžãƒ«ãƒã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆè¨è¨ˆã®åŸºæœ¬ã‚’紹介ã—ã¾ã™ã€‚ マルãƒã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆã‚·ã‚¹ãƒ†ãƒ ã®ãƒ‡ãƒ¢æ§‹æˆ デモã®å†…容 ã“ã®ãƒ‡ãƒ¢ã§ã¯ã€ã€Œãƒãƒƒãƒˆè¨˜äº‹ã®ä½œæˆæ¥å‹™ã€ã‚’例ã¨ã—ã¦ã„ã¾ã™ã€‚Gemini ã«ã€Œè¨˜äº‹ã‚’書ã„ã¦ï¼ã€ã¨ãŠé¡˜ã„ã™ã‚‹ã ã‘ã§ã‚‚ãれらã—ã„記事ã¯ç”Ÿæˆã§ãã¾ã™ãŒã€ã“ã“ã§ã¯ã€ã‚ˆã‚Šå®Ÿæ¥å‹™ã«å³ã—ãŸæ¥å‹™ãƒ•ãƒãƒ¼ã‚’マルãƒã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆã§å®Ÿç¾ã—ã¦ã„ã¾ã™ã€‚具体的ã«ã¯ã€æ¬¡ã®ã‚ˆã†ãªæµã‚Œã«ãªã‚Šã¾ã™ã€‚ (1) ユーザーãŒè¨˜äº‹ã®ãƒ†ãƒ¼ãƒžã‚’入力ã™ã‚‹ ↓ (2
Agent2Agent 入門 (4) - A2Aã¨MCP｜npaka
1. ã¯ã˜ã‚ã«ã€ŒMCPã€ãŒAIエージェントã¨ãƒ„ール・リソースã®é€£æºã«é–¢ã™ã‚‹ãƒ—ãƒãƒˆã‚³ãƒ«ã ã£ãŸã®ã«å¯¾ã—ã€ã€ŒA2Aã€ã¯AIエージェントåŒå£«ã®é€£æºã«ã™ã‚‹ãƒ—ãƒãƒˆã‚³ãƒ«ã«ãªã‚Šã¾ã™ã€‚エージェントアプリケーションã«ã¯ã€ŒA2Aã€ã¨ã€ŒMCPã€ã®ä¸¡æ–¹ãŒå¿…è¦ã§ã™ã€‚ 2. ç•°ãªã‚‹ãƒ—ãƒãƒˆã‚³ãƒ«ãŒå¿…è¦ãªç†ç”±ã€ŒMCPã€ã¨ã€ŒA2Aã€ã®é•ã„ã¯ã€ã‚¨ãƒ¼ã‚¸ã‚§ãƒ³ãƒˆãŒå¯¾è©±ã™ã‚‹å¯¾è±¡ã®æ€§è³ªã«ã‚ã‚Šã¾ã™ã€‚ 2-1. ツール ・ リソース「ツールã€ã¨ã€Œãƒªã‚½ãƒ¼ã‚¹ã€ã¯ã€å®šç¾©ãŒæ˜Žç¢ºã§æ§‹é€ 化ã•ã‚ŒãŸå…¥å‡ºåŠ›ã‚’æŒã¡ã¾ã™ã€‚。多ãã®å ´åˆã‚¹ãƒ†ãƒ¼ãƒˆãƒ¬ã‚¹ (状態をä¿æŒã—ãªã„) ã§ã€é›»å“やデータベースクエリAPIã€å¤©æ°—äºˆå ±æ¤œç´¢ã‚µãƒ¼ãƒ“ã‚¹ãªã©å˜ä¸€ã®æ©Ÿèƒ½ã‚’実行ã—ã¾ã™ã€‚ãã®å‹•ä½œã¯äºˆæ¸¬å¯èƒ½ã§ã€ã‚¤ãƒ³ã‚¿ãƒ©ã‚¯ã‚·ãƒ§ãƒ³ã¯åŸºæœ¬çš„ã«ã€Œãƒªã‚¯ã‚¨ã‚¹ãƒˆ → レスãƒãƒ³ã‚¹ã€ã®ä¸€å›žé™ã‚Šã§ã™ã€‚ 2-2. エージェント「エージェントã€ã¯ã‚ˆã‚Šè‡ªå¾‹çš„ã§è¤‡é›‘ãªã‚·ã‚¹ãƒ†ãƒ ã§ã™ã€‚推論や計画立案ã€è¤‡æ•°ã®ãƒ„ール連æºã€é•·æœŸã«ã‚ãŸã‚‹çŠ¶
Google主催『AI エージェント 実践集ä¸ã‚³ãƒ¼ã‚¹ã€ã«å‚åŠ ã—ãŸ
å€‹äººæƒ…å ±ã‚’é™¤ã講義内容ã®æŠ•ç¨¿ãŒå¯èƒ½ãªæ—¨ã‚’主催者様ã«ç¢ºèªã®ä¸ŠæŠ•ç¨¿ã—ã¦ãŠã‚Šã¾ã™ã€‚ リスニングã—ãªãŒã‚‰ã®ãƒ¡ãƒ¢æ›¸ãã®ãŸã‚一部内容ãŒé©åˆ‡ã§ãªã„å¯èƒ½æ€§ãŒã‚ã‚Šã¾ã™ã€‚ã”了承ãã ã•ã„。 ã¾ãŸã€è‡ªåˆ†ãŒèˆˆå‘³ã‚’æŒã£ãŸç®‡æ‰€ã®ãƒ¡ãƒ¢ã®ãŸã‚記載ã®å†…容ã¯è¬›ç¾©ã®å†…容ã®ã”ã一部ã§ã™ã€‚ 詳ã—ã„内容ã¯Googleå…¬å¼ã®white paperã‚’ã”確èªãã ã•ã„。 ðŸ‘Great References 🟢 Foundational Large Language Models & Text Generation 🟢 Prompt Engineering 🟢 Embeddings & Vector Stores 🟢 Agents 🟢 Agents Companion 🟢 Solving Domain-Specific Problems Using LLMs 🟢 Operationalizing Generative AI on
AI Agent × Cursor ã§è¦ä»¶æ•´ç†ã‹ã‚‰å®Ÿè£…ã¾ã§
Introduction Zennã®ã¿ãªã•ã‚“ã€ã“ã‚“ã«ã¡ã¯ï¼ TSUKURUBAã§ã€Web フãƒãƒ³ãƒˆã‚¨ãƒ³ãƒ‰ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ã‚’ã—ã¦ã„ã‚‹kiiã§ã™ 最近ã€ãƒ—ãƒã‚¸ã‚§ã‚¯ãƒˆã®ä¸ã§AI Agent（Cursor）を活用ã—ãŸé–‹ç™ºã«å–り組ã¿ã€è©¦è¡ŒéŒ¯èª¤ã‚’é‡ãã¦ãã¾ã—ãŸã€‚ ãã®éŽç¨‹ã§è¦‹ãˆã¦ããŸã€åŠ¹æžœçš„ãªé–‹ç™ºãƒ•ãƒãƒ¼ã‚„ノウãƒã‚¦ã‚’本記事ã§ã¾ã¨ã‚ã¦å…±æœ‰ã—ã¾ã™ã€‚ ã„ã‚ã‚“ãªAI Agent利用記事ã‚ã‚‹ã®ã§ã™ãŒã€æŠ½è±¡çš„ãªã‚‚ã®ãŒå¤šãã€ã‚‚ã£ã¨å…·ä½“例教ãˆã¦ã»ã—ã„ãªã€œã¨æ€ã£ãŸã®ã§æ›¸ã„ã¦ã¿ã¾ã—ãŸï¼ 実際ã«ä½¿ã£ã¦ã„るドã‚ュメントや命令ã®ä¾‹ã€é‹ç”¨ã®ã‚³ãƒ„も紹介ã—ã¾ã™ã®ã§ã€ ã¿ãªã•ã‚“ã®é–‹ç™ºã‚„AI活用ã®å‚考ã«ãªã‚Œã°å¹¸ã„ã§ã™ã€‚ ã“ã®è¨˜äº‹ã§å¾—られるã“㨠AI Agent（Cursor）を活用ã—ãŸé–‹ç™ºãƒ•ãƒãƒ¼ã®å…·ä½“çš„ãªé€²ã‚æ–¹ AI AgentãŒå®Ÿè£…ã§ãるよã†ãªã€è¦æ±‚æ•´ç†ã‹ã‚‰å®Ÿè£…ã¾ã§ã®Document作æˆæ‰‹é † AIã¨ã®ã‚„ã‚Šã¨ã‚Šã‚’効率化ã™ã‚‹ãŸã‚ã®å®Ÿè·µçš„ãªTips
リモートMCPãŒã‚„ã£ã¦ãã‚‹ã€ãã—ã¦A2Aã«ã¤ã„ã¦
リモートMCPãŒã‚„ã£ã¦ãã‚‹ã€ãã—ã¦A2Aã«ã¤ã„㦠先日 Streamable HTTP Transportã«å¯¾å¿œã—ãŸMCP TypeScript SDK 1.10.0ãŒãƒªãƒªãƒ¼ã‚¹ã•ã‚Œã¾ã—ãŸã€‚ã“ã‚Œã¯ã€ä»¥å‰ã®SSE Transport（2024-11-05）を置ãæ›ãˆã‚‹ã‚‚ã®ã§ã™ã€‚Python SDK（最新ãƒãƒ¼ã‚¸ãƒ§ãƒ³1.6.0）ã«ã¯ã¾ã ã“ã®æ›´æ–°ãŒå«ã¾ã‚Œã¦ã„ãªã„よã†ã§ã™ã€‚ Streamable HTTP release This is the first release supporting the new Streamable HTTP transport from protocol version 2025-03-26, which supersedes the SSE transport from protocol version 2024-11-05.… Streamable HTTP Tr
Why We're All-In on MCP - Mastra Blog
Tool integration for AI agents is a mess. Even for developers building agents every day, it's frustrating to navigate the fragmented ecosystem. Finding high-quality tools is difficult - search for "MCP Calendar integration" and you'll find ten different implementations with no way to know which one is best. If you've ever tried to integrate tools with an LLM, you know this pain. Tool discovery, in
AI_Agent_ã®ä½œã‚Šæ–¹_近藤憲å…
1万人を変ãˆæ—¥æœ¬ã‚’変ãˆã‚‹!!å¤šå±¤æ§‹é€ åž‹ãµã‚Šã‹ãˆã‚Šã®å¤§è¦æ¨¡çµ„ç¹”å¤‰é© / 20260108 Kazuki Mori
Beyond RAG: Implementing Agent Search with LangGraph for Smarter Knowledge Retrieval
Beyond RAG: Implementing Agent Search with LangGraph for Smarter Knowledge Retrieval Editor's note: this is a guest post from our friends at Onyx. As LangGraph has matured, we've seen more and more companies (Klarna, Replit, AppFolio, etc) start to use it as their agent framework of choice. We thought this was a great blog describing in detail how that evaluation is done. You can read a version of
ã€ç¿»è¨³ã€‘Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG - Qiita
Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? 2025/2/4 ã«å‡ºãŸ "Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG"(Agentic RAGã®èª¿æŸ») v3 を訳ã—ãŸã‚‚ã®ã§ã™ã€‚ 原文ã¯ã“ã¡ã‚‰ æ¦‚è¦ å¤§è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ«(LLM)ã¯ã€äººé–“ã®ã‚ˆã†ãªãƒ†ã‚スト生æˆã¨è‡ªç„¶è¨€èªžç†è§£ã‚’å¯èƒ½ã«ã™ã‚‹ã“ã¨ã§ã€äººå·¥çŸ¥èƒ½(AI)ã‚’é©æ–°ã—ã¾ã—ãŸã€‚ã—ã‹ã—ã€é™çš„ãªè¨“練データã«ä¾å˜ã—ã¦ã„ã‚‹ãŸã‚ã€å‹•çš„ã§å®Ÿæ™‚é–“ã®ã‚¯ã‚¨ãƒªã«å¿œç”ã™ã‚‹èƒ½åŠ›ãŒé™ã‚‰ã‚Œã€å‡ºåŠ›ãŒæ™‚代é…れやä¸æ£ç¢ºã«ãªã‚‹å¯èƒ½æ€§ãŒã‚ã‚Šã¾ã™ã€‚RAG ã¯ã€ã“ã®å•é¡Œã®è§£æ±ºç–ã¨ã—ã¦ç™»å ´ã—ã€LLM ã«
96%ãŒæº€è¶³ï¼ã€Œã‚ã‹ã‚‹ã€AIエージェント実践型ワークショップ | Fintan
ã¯ã˜ã‚㫠本レãƒãƒ¼ãƒˆã¯ã€TIS テクノãƒã‚¸ãƒ¼ï¼†ã‚¤ãƒŽãƒ™ãƒ¼ã‚·ãƒ§ãƒ³æœ¬éƒ¨ 開発基盤センターã®ç”ŸæˆAI利用促進ãƒãƒ¼ãƒ ãŒ2024å¹´12月3æ—¥ã«å®Ÿæ–½ã—ãŸã€ŒAIエージェントワークショップã€ã®æ¦‚è¦ã¨æˆæžœã‚’ã¾ã¨ã‚ãŸã‚‚ã®ã§ã‚ã‚‹ ワークショップã¯ï¼’部構æˆã§å®Ÿæ–½ã—ã€æ ªå¼ä¼šç¤¾ã‚¸ã‚§ãƒãƒ©ãƒ†ã‚£ãƒ–エージェンツ代表 西見 å…¬å®æ°ã¨ã€AI論文メディア『AIDBã€ã®é‹å–¶ç‰ã‚’è¡Œã†æ ªå¼ä¼šç¤¾Parks代表 æ°´è°· å¥æ°ã®ï¼’åをゲスト講師ã¨ã—ã¦æ‹›è˜ã€‚両æ°ã«ã¯è¬›æ¼”ã¨ãƒ•ã‚¡ã‚·ãƒªãƒ†ãƒ¼ã‚·ãƒ§ãƒ³ã‚’ã”担当ã„ãŸã ã„㟠本ワークショップã¯æ¥ç•Œã§ã‚‚先進的ãªå–り組ã¿ã§ã‚ã£ãŸãŒã€å‚åŠ è€…æº€è¶³åº¦96%ã‚’é”æˆã—ã€å®Ÿè·µçš„ãªå¦ã³ã®å ´ã‚’æä¾›ã™ã‚‹ã“ã¨ãŒã§ã㟠当記事を通ã—ã€æœ¬ãƒ¯ãƒ¼ã‚¯ã‚·ãƒ§ãƒƒãƒ—ã¸ã®ã”関心を寄ã›ã¦ã„ãŸã ã‘ã¾ã™ã¨å¹¸ã„ã§ã™ã€‚ãŠæ€¥ãŽã®æ–¹ã¯ã€Œãƒ¯ãƒ¼ã‚¯ã‚·ãƒ§ãƒƒãƒ—ã®æ¦‚è¦ã€ã¾ã§ã®ç« ã‚’ã”一èªã„ãŸã ã‘ã¾ã™ã¨ãƒ¯ãƒ¼ã‚¯ã‚·ãƒ§ãƒƒãƒ—全体ã®ã‚¤ãƒ¡ãƒ¼ã‚¸ã‚’掴むã“ã¨ãŒã§ãã¾ã™ã€‚ 想定èªè€… 生æˆAIエージェントを活
Agents
Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines the field of AI research as “the study and design of rational agents.†The unprecedented capabilities of foundation models have opened the door to agentic applications that were previously unimaginabl
ランã‚ング
ランã‚ング
メンテナンス
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
https://fintan.jp/wp-content/uploads/2025/07/20250711_TIS_Event_AI-Agent.pdf
20250423_AIエージェントã¯å†…製ã™ã‚‹ã¸ã‚™ãã‹ï¼ŸAlgomaticウェビナー
AIエージェントã®åœ°ä¸Šæˆ¦ 〜開発計画ã¨é‹ç”¨å®Ÿè·µ / 2025/04/08 Findy W&Bミートアップ #19
https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf
generative-ai/gemini/sample-apps/swot-agent at main · GoogleCloudPlatform/generative-ai
{{#tags}}- {{label}}
{{/tags}}