Automate With Marc This workflow corresponds to n8n.io template #5825 — we link there as the canonical source.
This workflow follows the Chainllm → Chat Trigger 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": "",
"name": "Start-up Ideas Generator",
"tags": [],
"nodes": [
{
"id": "76a873cb-d035-4ca4-8ca9-ca9d2b1d3aa1",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-280,
-60
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "75de6535-e334-4d64-a57f-7260df401a9d",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
380,
120
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-20250514",
"cachedResultName": "Claude 4 Sonnet"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "ce9f1ce5-2e12-4acc-ad9c-f92ba13ca246",
"name": "Executive Summary",
"type": "n8n-nodes-base.googleDocs",
"position": [
740,
-60
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "={{ $json.text }}",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "Redacted"
},
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "7932ae33-d1e4-4bb8-b38e-91b74435cb5f",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-340,
-180
],
"parameters": {
"width": 220,
"height": 500,
"content": "Chat Input Trigger"
},
"typeVersion": 1
},
{
"id": "0a490125-3a86-43cf-83c5-1b436e54e7ff",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-100,
-180
],
"parameters": {
"color": 4,
"width": 300,
"height": 500,
"content": "Define Research Scope"
},
"typeVersion": 1
},
{
"id": "09e33798-af03-45bf-b0a0-a01aa654d8e3",
"name": "Research Scope Definer Agent",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-80,
-60
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1",
"cachedResultName": "GPT-4.1"
},
"options": {},
"messages": {
"values": [
{
"content": "={{ $json.chatInput }}"
},
{
"role": "system",
"content": "You are a deep\u2011research AI agent with access to the Perplexity Sonar Deep Research tool. Your task is to take the user\u2019s query (e.g. \u201cGive me a few start\u2011up ideas in AI tech\u201d) and:\n\n1. Conduct thorough market research:\n \u2022 Identify 3\u20135 high\u2011potential start\u2011up opportunities aligned with the user\u2019s topic.\n \u2022 For each opportunity, include:\n \u2013 A concise description of the idea.\n \u2013 Target market size and growth trends.\n \u2013 Key customer pain points you\u2019ll solve.\n \u2013 Competitive landscape (top 2\u20133 players and gaps).\n \u2013 High\u2011level feasibility and differentiation angles.\n\n2. Structure your output as a JSON array named \u201copportunities\u201d, where each element contains the fields:\n {\n \"title\": string,\n \"description\": string,\n \"market_size\": string,\n \"customer_pain_points\": string[],\n \"competition\": { \"name\": string, \"notes\": string }[],\n \"differentiation\": string\n }\n\n3. Do not include any extraneous explanation\u2014only return valid JSON.\n\nOnce complete, pass this JSON to the next AI Agent node, which will convert it into a full business plan.\n"
}
]
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "16ca83ec-c18d-4196-8122-0ca4dfeb0871",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
220,
-180
],
"parameters": {
"color": 5,
"width": 420,
"height": 500,
"content": "Business Plan Proposal Builder"
},
"typeVersion": 1
},
{
"id": "2de9f3f6-5e61-47c1-842d-c7bf996d4a1b",
"name": "Claude Business Case Writer",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
320,
-60
],
"parameters": {
"text": "={{ $json.message.content }}",
"batching": {},
"messages": {
"messageValues": [
{
"message": "You are a business\u2010plan AI agent. You will receive a JSON object named `opportunities` from the previous research node, structured as an array of:\n{\n \"title\": string,\n \"description\": string,\n \"market_size\": string,\n \"customer_pain_points\": string[],\n \"competition\": { \"name\": string, \"notes\": string }[],\n \"differentiation\": string\n}\n\nYour task is to transform each opportunity into a complete, polished business plan and output it as plain text ready to populate a Google Doc. For each opportunity, produce these sections with clear headings:\n\n1. **Title** \n2. **Executive Summary** \n \u2013 One\u2011paragraph overview of the opportunity and value proposition. \n3. **Market Analysis** \n \u2013 Market size and growth trends. \n \u2013 Key customer segments and pain points. \n4. **Product or Service Description** \n \u2013 Detailed description of the offering. \n \u2013 How it solves the pain points. \n5. **Competitive Analysis** \n \u2013 Summary of top competitors and market gaps. \n \u2013 Your differentiation strategy. \n6. **Business Model** \n \u2013 Revenue streams, pricing model, and unit economics. \n7. **Go\u2011to\u2011Market Strategy** \n \u2013 Marketing channels, sales approach, and partnerships. \n8. **Financial Projections (Year\u202f1\u20133)** \n \u2013 High\u2011level revenue, cost assumptions, and breakeven outlook. \n9. **Team & Roadmap** \n \u2013 Key roles required and a 6\u2011month roadmap of milestones. \n\n\u2013 Use professional, concise language. \n\u2013 Format headings using Markdown\u2011style (e.g., `## Executive Summary`) so the Google Doc node will render them as section titles. \n\u2013 Do not include any JSON or explanatory text\u2014only the formatted business plan content. \n"
}
]
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "dbc5fc4a-3f45-45f6-a34c-c302900dedd0",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
660,
-180
],
"parameters": {
"color": 3,
"width": 300,
"height": 500,
"content": "Business Case Output on Google Docs"
},
"typeVersion": 1
},
{
"id": "756b169a-3f46-4671-a8fe-62d7732a3911",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1420,
-280
],
"parameters": {
"color": 6,
"width": 1060,
"height": 1220,
"content": "\ud83d\ude80 Start-up Ideas Generator \u2013 From Idea to Business Plan in Minutes\nDescription:\nThis AI-powered n8n workflow helps you brainstorm and validate start-up ideas, perform market research using Perplexity Sonar, and automatically generate a professional business plan \u2014 all within minutes.\n\nIt\u2019s designed for entrepreneurs, accelerators, venture studios, and ideation teams looking to go from a single prompt to a detailed proposal ready to pitch or develop.\n\nWatch step-by-step build video of n8n workflows like this:\nhttps://www.youtube.com/@Automatewithmarc\n\n\ud83d\udd0d How It Works:\n\ud83d\udcac Chat Trigger\n\u2003Start the process by typing a simple request like \u201cGive me a few start-up ideas in AI tech.\u201d\n\n\ud83e\udde0 AI Research Agent (OpenAI + Perplexity Sonar)\n\u2003The system defines the research scope, taps into Perplexity AI for deep market scans, and outputs high-potential business opportunities including:\n\nMarket size\n\nCustomer pain points\n\nCompetition overview\n\nDifferentiation strategy\n\n\ud83d\udcc4 Business Case Generator (Claude)\n\u2003Each opportunity is expanded into a complete business plan using Claude Sonnet, covering:\n\nExecutive summary\n\nMarket analysis\n\nProduct description\n\nCompetitor gap\n\nBusiness model & GTM\n\nFinancials & roadmap\n\n\ud83d\udcc3 Google Docs Export\n\u2003The full business plan is automatically inserted into a connected Google Doc for easy sharing, editing, or pitching.\n\n\ud83d\udee0\ufe0f Tools & Models Used:\nLangChain Chat Trigger\n\nOpenAI GPT-4.1 (Research Prompt Structuring)\n\nPerplexity Sonar Deep Research (Market Research)\n\nAnthropic Claude Sonnet (Business Plan Writing)\n\nGoogle Docs Node (Formatted Output)\n\n\ud83d\udca1 Use Cases:\nRapid ideation for venture building or incubators\n\nValidating start-up ideas before prototyping\n\nAutomating market research + proposal writing\n\nGenerating investor-ready pitch materials\n\n"
},
"typeVersion": 1
},
{
"id": "b5500023-acb8-43e3-8620-a0a52d432c79",
"name": "Perplexity Sonar Deep Research",
"type": "n8n-nodes-base.perplexityTool",
"position": [
20,
160
],
"parameters": {
"model": "sonar-deep-research",
"options": {},
"messages": {
"message": [
{
"content": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('message0_Text', ``, 'string') }}"
}
]
},
"requestOptions": {}
},
"credentials": {
"perplexityApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "Claude Business Case Writer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Research Scope Definer Agent",
"type": "main",
"index": 0
}
]
]
},
"Claude Business Case Writer": {
"main": [
[
{
"node": "Google Docs",
"type": "main",
"index": 0
}
]
]
},
"Research Scope Definer Agent": {
"main": [
[
{
"node": "Claude Business Case Writer",
"type": "main",
"index": 0
}
]
]
},
"Perplexity Sonar Deep Research": {
"ai_tool": [
[
{
"node": "Research Scope Definer Agent",
"type": "ai_tool",
"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.
anthropicApigoogleDocsOAuth2ApiopenAiApiperplexityApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Source: https://n8n.io/workflows/5825/ — 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.
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Chat Trigger, Anthropic Chat, Google Docs +3
✨ Intro This workflow shows how to go beyond a “plain” AI chatbot by:
Telegram, OpenAI, OpenAI Chat +13
This workflow turns a simple chat interface into a powerful personal expense tracker. Just describe your spending in plain language — the AI understands it, categorizes it, and saves it to Google Shee
Chat Trigger, Google Sheets, Chain Llm +1
This workflow implements an AI-powered design and prototyping assistant that integrates Telegram, Google Gemini, and Google Stitch (MCP) to enable conversational UI generation and project management.
Chat Trigger, Google Gemini Chat, Memory Buffer Window +6
This template automates stock analysis by combining technical analysis, news sentiment, and real-time market data to generate actionable trading recommendations with confidence scores, risk management
Chat Trigger, HTTP Request, OpenAI +6