Oka Hironobu This workflow corresponds to n8n.io template #17692 — we link there as the canonical source.
This workflow follows the Agent → Chainllm recipe pattern — see all workflows that pair these two integrations.
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 →
{
"id": "c8i4Nyd5gZL5LOPx",
"meta": {
"builderVariant": "mcp",
"aiBuilderAssisted": true
},
"name": "Turn a topic into a research-backed article with a multi-agent AI pipeline",
"tags": [],
"nodes": [
{
"id": "f0f62f74-e5a1-42fd-a8d3-7d9c27659b35",
"name": "Article Brief Form",
"type": "n8n-nodes-base.formTrigger",
"position": [
48,
48
],
"parameters": {
"options": {
"buttonLabel": "Write my article",
"respondWithOptions": {
"values": {
"formSubmittedText": "Thanks! Your article is being researched and written and will arrive by email shortly."
}
}
},
"formTitle": "Topic to article",
"formFields": {
"values": [
{
"fieldType": "email",
"fieldLabel": "Your email",
"requiredField": true
},
{
"fieldLabel": "Topic",
"placeholder": "e.g. Benefits of intermittent fasting",
"requiredField": true
},
{
"fieldLabel": "Audience",
"placeholder": "e.g. Busy beginners",
"requiredField": true
},
{
"fieldLabel": "Keyword",
"placeholder": "e.g. intermittent fasting for beginners"
}
]
},
"formDescription": "Give a topic and audience and get a research-backed, SEO-edited article by email."
},
"typeVersion": 2.6
},
{
"id": "079e697c-d427-46ad-baaa-1884af787605",
"name": "Research Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
240,
48
],
"parameters": {
"text": "=Research the topic \"{{ $json.Topic }}\" for an audience of {{ $json.Audience }}. Use the Wikipedia tool to gather accurate facts. Produce concise research notes: 5-8 key points, any important numbers, and 2-3 common misconceptions to correct. Do not write the article yet - just the notes.",
"options": {
"systemMessage": "You are a diligent research assistant. Verify facts with Wikipedia before stating them."
},
"promptType": "define"
},
"typeVersion": 3.1
},
{
"id": "6bc9a69e-3fa2-4057-8b37-29cc73454950",
"name": "Research Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
224,
224
],
"parameters": {
"options": {
"temperature": 0.2
},
"modelName": "models/gemini-3.1-flash-lite"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "c3d58078-8ba5-4520-96f8-ffe571b29eed",
"name": "Wikipedia",
"type": "@n8n/n8n-nodes-langchain.toolWikipedia",
"position": [
416,
224
],
"parameters": {},
"typeVersion": 1
},
{
"id": "66ace249-be70-405b-9147-30c73abb57de",
"name": "Write Draft with Gemini",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
576,
48
],
"parameters": {
"text": "=You are a writer. Using ONLY the research notes below, write a friendly, well-structured article of about 500 words for an audience of {{ $('Article Brief Form').item.json.Audience }} on \"{{ $('Article Brief Form').item.json.Topic }}\". Use short paragraphs and a clear intro and conclusion. Do not invent facts beyond the notes.\n\nResearch notes:\n{{ $json.output }}",
"batching": {},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "609fadc2-8b2c-48fd-9866-4df8a7386b5d",
"name": "Writer Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
576,
224
],
"parameters": {
"options": {
"temperature": 0.7
},
"modelName": "models/gemini-3.1-flash-lite"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "c2425e2a-8df7-46ce-b514-e3310bfc9537",
"name": "Edit and Optimise with Gemini",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
880,
48
],
"parameters": {
"text": "=You are an SEO editor. Improve the draft below: tighten the writing, fix any awkward phrasing, and naturally work in the keyword \"{{ $('Article Brief Form').item.json.Keyword }}\" where it fits. Then output the finished article, a compelling 55-60 character SEO title on a line starting \"TITLE:\", and a 150-character meta description on a line starting \"META:\".\n\nDraft:\n{{ $json.text }}",
"batching": {},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "ec48d034-4efc-4f96-9784-13c2c6efd230",
"name": "Editor Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
880,
224
],
"parameters": {
"options": {
"temperature": 0.4
},
"modelName": "models/gemini-3.1-flash-lite"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "fc2a4e5f-e9d7-45bc-b7c9-76fde8336f6a",
"name": "Split Article, Title and Meta",
"type": "n8n-nodes-base.code",
"position": [
1232,
48
],
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const out = String($json.text || '');\nconst t = out.match(/TITLE:\\s*(.*)$/im);\nconst m = out.match(/META:\\s*(.*)$/im);\nconst title = t ? t[1].trim() : '';\nconst meta = m ? m[1].trim() : '';\nconst body = out.replace(/TITLE:\\s*.*$/im, '').replace(/META:\\s*.*$/im, '').trim();\nconst f = $('Article Brief Form').item.json;\nreturn { email: f['Your email'], topic: f.Topic, title: title, meta: meta, article: body };"
},
"typeVersion": 2
},
{
"id": "91d9085e-3de4-4c8e-ba72-9d7c19499cca",
"name": "Log Article",
"type": "n8n-nodes-base.googleSheets",
"position": [
1456,
48
],
"parameters": {
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultName": "Articles"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultName": "Select your spreadsheet"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.7
},
{
"id": "f5bba6ea-a981-4cc9-80e3-d183fed50e0b",
"name": "Email the Article",
"type": "n8n-nodes-base.gmail",
"position": [
1664,
48
],
"parameters": {
"sendTo": "={{ $(\"Split Article, Title and Meta\").item.json.email }}",
"message": "={{ \"TITLE: \" + $(\"Split Article, Title and Meta\").item.json.title + \"\\nMETA: \" + $(\"Split Article, Title and Meta\").item.json.meta + \"\\n\\n\" + $(\"Split Article, Title and Meta\").item.json.article }}",
"options": {},
"subject": "={{ \"Your article: \" + $(\"Split Article, Title and Meta\").item.json.title }}",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.2
},
{
"id": "c5ab5e55-aa3b-42f2-a93d-38da3918610b",
"name": "Overview Sticky",
"type": "n8n-nodes-base.stickyNote",
"position": [
-624,
-160
],
"parameters": {
"width": 552,
"height": 664,
"content": "## Turn a topic into a research-backed article with a multi-agent AI pipeline\n\n### How it works\nInstead of one prompt doing everything, this template splits the job across three specialised AI steps, like a real editorial team. Submit a topic and audience in the built-in form. First an AI Agent researches the topic, using the Wikipedia tool to gather and verify facts, and produces structured notes. Then a Basic LLM Chain (the writer) turns only those notes into a friendly 500-word draft, so it cannot invent facts. Finally a second Basic LLM Chain (the SEO editor) tightens the draft, works in your keyword, and adds an SEO title and meta description. The finished piece is logged to Google Sheets and emailed to you.\n\n### Setup\n1. Connect Google Gemini (PaLM) API, Google Sheets and Gmail.\n2. Point the Log Article node at your spreadsheet (tab: Articles).\n3. Open the form URL and submit a topic.\n\n### Customization tips\nAdd a fact-check agent, or publish straight to WordPress or a Google Doc."
},
"typeVersion": 1
},
{
"id": "a788c244-dd3a-4e54-8792-6951c990f95f",
"name": "S1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-48,
-160
],
"parameters": {
"color": 7,
"width": 564,
"height": 652,
"content": "## 1. Research Agent\nAn AI Agent gathers and verifies facts with the Wikipedia tool and writes structured notes."
},
"typeVersion": 1
},
{
"id": "16a64a47-c0d6-45cf-b385-829ec9833008",
"name": "S2",
"type": "n8n-nodes-base.stickyNote",
"position": [
528,
-160
],
"parameters": {
"color": 7,
"width": 616,
"height": 652,
"content": "## 2. Writer & SEO editor (Basic LLM Chains)\nOne chain writes the draft from the notes only; a second chain edits it and adds an SEO title and meta."
},
"typeVersion": 1
},
{
"id": "c5fe3ba5-8f73-4f32-92a1-135e1a0279f7",
"name": "S3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1168,
-160
],
"parameters": {
"color": 7,
"width": 660,
"height": 652,
"content": "## 3. Log & deliver\nSplit out the title and meta, log the article to Sheets and email the finished piece."
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"availableInMCP": true,
"executionOrder": "v1"
},
"versionId": "59fa85a1-f322-40f1-b64e-8b3b31ef249a",
"nodeGroups": [],
"connections": {
"Wikipedia": {
"ai_tool": [
[
{
"node": "Research Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Log Article": {
"main": [
[
{
"node": "Email the Article",
"type": "main",
"index": 0
}
]
]
},
"Editor Model": {
"ai_languageModel": [
[
{
"node": "Edit and Optimise with Gemini",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Writer Model": {
"ai_languageModel": [
[
{
"node": "Write Draft with Gemini",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Research Agent": {
"main": [
[
{
"node": "Write Draft with Gemini",
"type": "main",
"index": 0
}
]
]
},
"Research Model": {
"ai_languageModel": [
[
{
"node": "Research Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Article Brief Form": {
"main": [
[
{
"node": "Research Agent",
"type": "main",
"index": 0
}
]
]
},
"Write Draft with Gemini": {
"main": [
[
{
"node": "Edit and Optimise with Gemini",
"type": "main",
"index": 0
}
]
]
},
"Edit and Optimise with Gemini": {
"main": [
[
{
"node": "Split Article, Title and Meta",
"type": "main",
"index": 0
}
]
]
},
"Split Article, Title and Meta": {
"main": [
[
{
"node": "Log Article",
"type": "main",
"index": 0
}
]
]
}
}
}
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.
gmailOAuth2googlePalmApigoogleSheetsOAuth2Api
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow collects a topic, audience, and keyword in an n8n form, researches the topic with Wikipedia, writes and SEO-edits a ~500-word article using Google Gemini, then logs the result to Google Sheets and emails the finished article via Gmail. Receives an article request…
Source: https://n8n.io/workflows/17692/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
HTTP Request, Google Sheets, OpenRouter Chat +5
The workflow runs every hour with a randomized delay of 5–20 minutes to help distribute load. It records the exact date and time a lead is emailed so you can track outreach. Follow-ups are automatical
Google Sheets, Agent, OpenAI Chat +5
This workflow collects candidate applications via an n8n form, extracts resume text with Mistral AI, matches the candidate to an open role stored in Google Sheets and Google Docs, scores the fit using
Form, Form Trigger, Google Sheets +7
Automate your lead intake, scoring, and outreach pipeline. This workflow collects leads from forms, enriches and scores them using Relevance AI, routes them by quality, and triggers the right follow-u
Form Trigger, HTTP Request, Chain Llm +6