{ "id": "H2W1Jyu1gKhpQk52", "meta": { "templateCredsSetupCompleted": true }, "name": "AI Agents - Real Time Research", "tags": [], "nodes": [ { "id": "a2b142d1-90ea-42ae-9907-8bc5c4241221", "name": "When chat message received", "type": "@n8n/n8n-nodes-langchain.manualChatTrigger", "position": [ -200, 0 ], "parameters": {}, "typeVersion": 1.1 }, { "id": "358ad390-f42b-411a-8c09-43ddfc406896", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 160, 380 ], "parameters": { "model": "gpt-4", "options": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1 }, { "id": "9dce7253-4994-47f5-a8db-dd7b64f28eb4", "name": "Window Buffer Memory", "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow", "position": [ 320, 220 ], "parameters": {}, "typeVersion": 1.2 }, { "id": "7cf5d7f7-b52b-4512-ba66-7377963b8ce2", "name": "SerpAPI - Research", "type": "@n8n/n8n-nodes-langchain.toolSerpApi", "position": [ 500, 220 ], "parameters": { "options": {} }, "credentials": { "serpApi": { "name": "" } }, "typeVersion": 1 }, { "id": "a590584e-ff8e-4db7-b793-cd0c43dab1b0", "name": "AI Agents - Real Time Research", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ 260, 0 ], "parameters": { "options": {} }, "typeVersion": 1.6 }, { "id": "aaa5e82d-a0ff-4541-936d-2ddcefe447ac", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ -320, -300 ], "parameters": { "color": 4, "width": 360, "height": 820, "content": "## 1. Start When A Chat Message Is Received\n- The workflow is triggered whenever a chat message is received (e.g., a user question, research prompt, or data request)." }, "typeVersion": 1 }, { "id": "77bea2dc-9e15-4cbf-8865-945778138559", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -1120, -300 ], "parameters": { "width": 740, "height": 1420, "content": "## [n8n Automation] Real-time Research AI Agent - Try It Out!\n**This workflow demonstrates how to automate live information gathering, fact-checking, and trend analysis in response to any chat message - using a powerful AI agent, memory, and a real-time search tool.**\n\nUse cases are many: This is perfect for **researchers** needing instant, up-to-date data; **support teams** providing live, accurate answers; **content creators** looking to verify facts or find hot topics; and **analysts** automating regular reports with the freshest information.\n\n## How It Works\n- The workflow is triggered whenever a chat message is received (e.g., a user question, research prompt, or data request).\n- The message is sent to the AI Agent, which follows the following steps:\n - First, it queries **SerpAPI \u2013 Research** to gather the latest real-time information and data from the web.\n - Next, it checks the **Window Buffer Memory** for any related past interactions or contextual information that may be useful.\n - Finally, it sends all collected data and context to the **Google Gemini Chat Model**, which analyzes the information and generates a comprehensive, intelligent response.\n- Then, the AI Agent delivers the analyzed, up-to-date answer directly in the chat, combining live data, context, and expert analysis.\n\n## How To Set Up\n- Download and import the workflow into your n8n workspace.\n- Set up API credentials and tool access for the **AI Agent**:\n - **Google Gemini** (for chat-based intelligence) \u2192 connected to Node **Google Gemini Chat Model**.\n - **SerpAPI** (for real-time web and search results) \u2192 connected to Node **SerpAPI - Research**.\n - **Window Buffer Memory** (for richer, context-aware conversations) \u2192 connected to Node Window **Buffer Memory**.\n- Open the chat in n8n and type the topic or trend you want to research.\n- Send the message and wait for the process to complete.\n- Receive the AI-powered research reply in the chat box.\n\n## Requirements\n- An **n8n** instance (self-hosted or cloud).\n- **SerpAPI** credentials for live web search and data gathering.\n- **Window Buffer Memory** configured to provide relevant conversation context in history.\n- **Google Gemini API** access to analyze collected data and generate responses.\n\n## How To Customize\n- **Choose your preferred AI model**: Replace **Google Gemini** with **OpenAI ChatGPT**, or any other chat model as preferred.\n- **Add or change memory**: Replace **Window Buffer Memory** with more advanced memory options for deeper recall.\n- **Connect your preferred chat platform**: Easily swap out the default chat integration for Telegram, Slack, or any other compatible messaging platform to trigger and interact with the workflow.\n\n## Need Help?\nIf you\u2019d like this workflow customized, or if you\u2019re looking to build a tailored AI Agent for your own business - please feel free to reach out to [**Agent Circle**](https://www.agentcircle.ai/). We\u2019re always here to support and help you to bring automation ideas to life.\n\nJoin our community on different platforms for assistance, inspiration and tips from others.\n\nWebsite: https://www.agentcircle.ai/\nEtsy: https://www.etsy.com/shop/AgentCircle\nGumroad: http://agentcircle.gumroad.com/\nDiscord Global: https://discord.gg/d8SkCzKwnP\nFB Page Global: https://www.facebook.com/agentcircle/\nFB Group Global: https://www.facebook.com/groups/aiagentcircle/\nX: https://x.com/agent_circle\nYouTube: https://www.youtube.com/@agentcircle\nLinkedIn: https://www.linkedin.com/company/agentcircle\n\n\n" }, "typeVersion": 1 }, { "id": "b53905ce-0343-4713-9267-6f9b280a5be8", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ 60, -300 ], "parameters": { "color": 4, "width": 660, "height": 820, "content": "## 2. Process The Request & Return Response\n- The message is sent to the AI Agent, which follows the following steps:\n - First, it queries **SerpAPI \u2013 Research** to gather the latest real-time information and data from the web.\n - Next, it checks the **Window Buffer Memory** for any related past interactions or contextual information that may be useful.\n - Finally, it sends all collected data and context to the **Google Gemini Chat Model**, which analyzes the information and generates a comprehensive, intelligent response.\n- Then, the AI Agent delivers the analyzed, up-to-date answer directly in the chat, combining live data, context, and expert analysis." }, "typeVersion": 1 }, { "id": "b3e0c845-deaa-4147-940b-92efb4ef9475", "name": "Google Gemini Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini", "position": [ 160, 220 ], "parameters": { "options": {}, "modelName": "models/gemini-2.0-flash" }, "credentials": { "googlePalmApi": { "name": "" } }, "typeVersion": 1 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "404f0c7d-c796-40c6-b0e6-7944f1223081", "connections": { "OpenAI Chat Model": { "ai_languageModel": [ [] ] }, "SerpAPI - Research": { "ai_tool": [ [ { "node": "AI Agents - Real Time Research", "type": "ai_tool", "index": 0 } ] ] }, "Window Buffer Memory": { "ai_memory": [ [ { "node": "AI Agents - Real Time Research", "type": "ai_memory", "index": 0 } ] ] }, "Google Gemini Chat Model": { "ai_languageModel": [ [ { "node": "AI Agents - Real Time Research", "type": "ai_languageModel", "index": 0 } ] ] }, "When chat message received": { "main": [ [ { "node": "AI Agents - Real Time Research", "type": "main", "index": 0 } ] ] } } }