research Agent

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "\ud83e\udd16Research Agent",
  "nodes": [
    {
      "parameters": {},
      "id": "14ad81bc-fb39-40b7-ae35-d28203122973",
      "name": "Execute Workflow Trigger",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1,
      "position": [
        440,
        260
      ]
    },
    {
      "parameters": {
        "model": "gpt-4o",
        "options": {}
      },
      "id": "a00ab383-c7d9-4b6d-af13-1bf2cdb642ac",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        560,
        520
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "7ab380a2-a8d3-421c-ab4e-748ea8fb7904",
              "name": "response",
              "value": "Unable to perform task. Please try again.",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "038ada41-e162-4053-bae6-1c44b4a1a42d",
      "name": "Try Again",
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        1160,
        400
      ]
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "39c2f302-03be-4464-a17a-d7cc481d6d44",
              "name": "=response",
              "value": "={{$json.output}}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "aa7da50b-42ad-47cd-8adf-c6536544486d",
      "name": "Success",
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        1160,
        140
      ]
    },
    {
      "parameters": {
        "options": {}
      },
      "id": "73156937-ec81-4e51-93cc-4243fcebc1c6",
      "name": "SerpAPI",
      "type": "@n8n/n8n-nodes-langchain.toolSerpApi",
      "typeVersion": 1,
      "position": [
        900,
        520
      ],
      "credentials": {
        "serpApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {},
      "id": "78a3a242-473d-4544-9e1b-ae80498feb83",
      "name": "Wikipedia",
      "type": "@n8n/n8n-nodes-langchain.toolWikipedia",
      "typeVersion": 1,
      "position": [
        680,
        520
      ]
    },
    {
      "parameters": {
        "resource": "all",
        "limit": "={{ $fromAI(\"limit\",\"number of articles\") }}",
        "additionalFields": {
          "keyword": "={{ $fromAI(\"keywords\",\"keywords for the articles\") }}"
        }
      },
      "id": "c289d7fe-da13-4a2f-ba49-19acdb6bc7ce",
      "name": "Hacker News",
      "type": "n8n-nodes-base.hackerNewsTool",
      "typeVersion": 1,
      "position": [
        800,
        520
      ]
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.query }}",
        "options": {
          "systemMessage": "You are a research assistant agent. You have Wikipedia, Hacker News API, and Serp API at your disposal. \n\nTo answer the user's question, first search wikipedia. If you can't find your answer there, then search articles using Hacker News API. If that doesn't work either, then use Serp API to answer the user's question.\n"
        }
      },
      "id": "fe1d46a0-7524-4b11-889c-10c2fd2debbf",
      "name": "Research Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.6,
      "position": [
        660,
        260
      ],
      "onError": "continueErrorOutput"
    }
  ],
  "connections": {
    "Execute Workflow Trigger": {
      "main": [
        [
          {
            "node": "Research Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Research Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "SerpAPI": {
      "ai_tool": [
        [
          {
            "node": "Research Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Wikipedia": {
      "ai_tool": [
        [
          {
            "node": "Research Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Hacker News": {
      "ai_tool": [
        [
          {
            "node": "Research Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Research Agent": {
      "main": [
        [
          {
            "node": "Success",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Try Again",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "a2211983-f8ab-4f45-8be2-3b5ad585a891",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "Hgm5BTXAKjDnLOof",
  "tags": []
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• openAiApi
• serpApi

About this workflow

🤖Research Agent. Uses executeWorkflowTrigger, lmChatOpenAi, toolSerpApi, toolWikipedia. Event-driven trigger; 8 nodes.

Source: https://github.com/yashsoni102-prog/Yash-Soni-Portfolio/blob/main/n8n/personal-assistant-agent/research-agent.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.