Gleb D This workflow corresponds to n8n.io template #4565 — we link there as the canonical source.
This workflow follows the Chainllm → Form 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 →
{
"nodes": [
{
"id": "03a69683-ae41-4457-a067-f8eb3070e6cc",
"name": "Snapshot Progress",
"type": "n8n-nodes-base.httpRequest",
"position": [
-120,
-220
],
"parameters": {
"url": "=https://api.brightdata.com/datasets/v3/progress/{{ $('HTTP Request- Post API call to Bright Data').item.json.snapshot_id }}",
"options": {},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer YOUR_TOKEN_HERE"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "042743bc-4a3a-4be7-87d2-5a0d7327b2aa",
"name": "HTTP Request- Post API call to Bright Data",
"type": "n8n-nodes-base.httpRequest",
"position": [
-620,
40
],
"parameters": {
"url": "https://api.brightdata.com/datasets/v3/trigger",
"method": "POST",
"options": {},
"sendBody": true,
"sendQuery": true,
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "keyword",
"value": "={{ $json[\"Keyword\"] }}"
}
]
},
"queryParameters": {
"parameters": [
{
"name": "dataset_id",
"value": "gd_l1vijqt9jfj7olije"
},
{
"name": "type",
"value": "discover_new"
},
{
"name": "discover_by",
"value": "keyword"
},
{
"name": "include_errors",
"value": "true"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer YOUR_TOKEN_HERE"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "4ae4d5a0-b266-4620-ae74-1230a1622437",
"name": "Wait - Polling Bright Data",
"type": "n8n-nodes-base.wait",
"position": [
-340,
-220
],
"parameters": {
"amount": 15
},
"executeOnce": false,
"typeVersion": 1.1
},
{
"id": "fdd36a29-ee46-4737-892c-a8095db01233",
"name": "If - Checking status of Snapshot - if data is ready or not",
"type": "n8n-nodes-base.if",
"position": [
100,
-220
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7932282b-71bb-4bbb-ab73-4978e554de7e",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "running"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "6ef4e903-ef2d-4b0d-921b-30e848ad7590",
"name": "HTTP Request - Getting data from Bright Data",
"type": "n8n-nodes-base.httpRequest",
"position": [
320,
-220
],
"parameters": {
"url": "=https://api.brightdata.com/datasets/v3/snapshot/{{ $json.snapshot_id }}",
"options": {},
"sendQuery": true,
"sendHeaders": true,
"queryParameters": {
"parameters": [
{
"name": "format",
"value": "json"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer YOUR_TOKEN_HERE"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "5686b066-2f14-4aa9-bfd0-834f02e514c7",
"name": "Code - Parse and Clean JSON Data",
"type": "n8n-nodes-base.code",
"position": [
540,
-220
],
"parameters": {
"language": "python",
"pythonCode": "from datetime import datetime\n\nall_companies = _input.all()\n\nvalid_companies = []\nfor item in all_companies:\n company = item.json\n date_str = company.get(\"founded_date\")\n try:\n date = datetime.strptime(date_str, \"%Y-%m-%d\")\n valid_companies.append((date, company))\n except (TypeError, ValueError):\n continue\n\nsorted_companies = sorted(valid_companies, key=lambda x: x[0], reverse=True)\n\ncleaned = []\nfor _, c in sorted_companies[:10]:\n founders = c.get(\"founders\") or []\n products = c.get(\"products_and_services\") or []\n financials = c.get(\"financials_highlights\") or {}\n\n cleaned.append({\n \"name\": c.get(\"name\"),\n \"founded\": c.get(\"founded_date\"),\n \"about\": c.get(\"about\"),\n \"num_employees\": c.get(\"num_employees\"),\n \"type\": c.get(\"type\"),\n \"ipo_status\": c.get(\"ipo_status\"),\n \"full_description\": c.get(\"full_description\", \"\"),\n \"monthly_visits\": c.get(\"monthly_visits\"),\n \"social_media_links\": c.get(\"social_media_links\", []),\n \"website\": c.get(\"website\"),\n \"address\": c.get(\"address\"),\n \"funding_total\": financials.get(\"funding_total\"),\n \"num_investors\": c.get(\"num_investors\") or financials.get(\"num_investors\"),\n \"lead_investors\": financials.get(\"num_lead_investors\"),\n \"founders\": \", \".join([p.get(\"value\") for p in founders if p.get(\"value\")]),\n \"products_and_services\": \", \".join([p.get(\"product_name\") for p in products if p.get(\"product_name\")]),\n \"crunchbase_link\": c.get(\"url\"),\n \"ai_analysis\": \"\"\n })\n\nreturn [{\n \"json\": {\n \"companies\": cleaned\n }\n}]\n"
},
"typeVersion": 2,
"alwaysOutputData": true
},
{
"id": "29f39c43-e688-43de-b249-5407abd3ff50",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
-400
],
"parameters": {
"content": "## Note \nModify the JSON keys in the code to include only the fields you want. The current structure is a sample template"
},
"typeVersion": 1
},
{
"id": "29b00dad-9e5d-45fd-87ad-0c1a6659bfcd",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
340,
220
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash"
},
"typeVersion": 1
},
{
"id": "92076574-6e30-4436-81b0-a016c47d707e",
"name": "Google Gemini - Comparative Analisys",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
340,
40
],
"parameters": {
"text": "={{$json}}",
"messages": {
"messageValues": [
{
"message": "=You will be provided with data for companies from Crunchbase, operating in the sector (or field of interests) that user requested by [keyword].\n\nPlease perform a comparative analysis of these companies. Highlight key similarities, differences, perspectives, and any notable outliers. The [keyword] user requested initially: {{ $('When User Completes Form').first().json['Keyword']}}.\nDon't start your answer with 'Okay'."
}
]
},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "10dacf61-006d-4821-aced-72beb4de1cf0",
"name": "When User Completes Form",
"type": "n8n-nodes-base.formTrigger",
"position": [
-840,
40
],
"parameters": {
"options": {
"ignoreBots": true
},
"formTitle": "Search from Crunchbase by keyword",
"formFields": {
"values": [
{
"fieldLabel": "Keyword",
"placeholder": "e.g. \"AI in healthcare\"",
"requiredField": true
}
]
},
"responseMode": "lastNode",
"formDescription": "Please provide a keyword to search and compare relevant startups"
},
"typeVersion": 2.2
},
{
"id": "28aa3e45-bbaa-40a1-b0ec-33c81e8a1a7a",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
780,
-80
],
"parameters": {},
"typeVersion": 3.1
},
{
"id": "e7da127a-864c-4957-8be9-a48229885c78",
"name": "Code - Combining JSON and AI outputs",
"type": "n8n-nodes-base.code",
"position": [
1000,
-80
],
"parameters": {
"language": "python",
"pythonCode": "input_0 = _input.all(0)\ninput_1 = _input.all(1) \n\nif not input_0 or not input_1:\n raise ValueError(\"Missing input data on one of the inputs.\")\n\ncompanies = input_0[0].json.get(\"companies\")\nanalysis_text = input_1[1].json.get(\"text\")\n\nif companies:\n companies[0][\"ai_analysis\"] = analysis_text\n\nreturn [{ \"json\": company } for company in companies]\n"
},
"typeVersion": 2
},
{
"id": "60268912-b8e8-4fd9-ac86-ad5e4494e013",
"name": "Google Sheets - Export Results",
"type": "n8n-nodes-base.googleSheets",
"position": [
1220,
-80
],
"parameters": {
"columns": {
"value": {
"name": "={{ $json.companies[0].name }}"
},
"schema": [
{
"id": "name",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "founded",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "founded",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "about",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "about",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "num_employees",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "num_employees",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "type",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "type",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "ipo_status",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "ipo_status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "full_description",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "full_description",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "social_media_links",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "social_media_links",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "website",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "website",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "funding_total",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "funding_total",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "num_investors",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "num_investors",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "lead_investors",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "lead_investors",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "founders",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "founders",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "products_and_services",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "products_and_services",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "crunchbase_link",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "crunchbase_link",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "text",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "text",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "companies",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "companies",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "autoMapInputData",
"matchingColumns": [
"name"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/134y4U1gc8DvM4bPhSfOUtZhjoBvx62dTsff2P8niGAg/edit#gid=0",
"cachedResultName": "results"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "134y4U1gc8DvM4bPhSfOUtZhjoBvx62dTsff2P8niGAg",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/134y4U1gc8DvM4bPhSfOUtZhjoBvx62dTsff2P8niGAg/edit?usp=drivesdk",
"cachedResultName": "Crunchbase Output"
}
},
"typeVersion": 4.3,
"alwaysOutputData": true
}
],
"connections": {
"Merge": {
"main": [
[
{
"node": "Code - Combining JSON and AI outputs",
"type": "main",
"index": 0
}
]
]
},
"Snapshot Progress": {
"main": [
[
{
"node": "If - Checking status of Snapshot - if data is ready or not",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Google Gemini - Comparative Analisys",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When User Completes Form": {
"main": [
[
{
"node": "HTTP Request- Post API call to Bright Data",
"type": "main",
"index": 0
}
]
]
},
"Wait - Polling Bright Data": {
"main": [
[
{
"node": "Snapshot Progress",
"type": "main",
"index": 0
}
]
]
},
"Google Sheets - Export Results": {
"main": [
[]
]
},
"Code - Parse and Clean JSON Data": {
"main": [
[
{
"node": "Google Gemini - Comparative Analisys",
"type": "main",
"index": 0
},
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Code - Combining JSON and AI outputs": {
"main": [
[
{
"node": "Google Sheets - Export Results",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini - Comparative Analisys": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"HTTP Request- Post API call to Bright Data": {
"main": [
[
{
"node": "Wait - Polling Bright Data",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request - Getting data from Bright Data": {
"main": [
[
{
"node": "Code - Parse and Clean JSON Data",
"type": "main",
"index": 0
}
]
]
},
"If - Checking status of Snapshot - if data is ready or not": {
"main": [
[
{
"node": "Wait - Polling Bright Data",
"type": "main",
"index": 0
}
],
[
{
"node": "HTTP Request - Getting data from Bright Data",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n workflow automates the discovery, enrichment, and comparative analysis of startups from the Crunchbase dataset via Bright Data, enhanced with AI, and exports structured results to Google Sheets.
Source: https://n8n.io/workflows/4565/ — 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.
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
Sales teams and B2B marketers who spend hours researching leads manually. If you've looked at Clay but didn't want the $149/month price tag, this workflow does the same job as a one-time n8n template.
Form Trigger, HTTP Request, Chain Llm +3
This workflow automates B2B lead research for Japanese companies. Submit a company name through a web form, and the workflow queries two free Japanese government APIs for corporate registry and busine
Form Trigger, HTTP Request, Chain Llm +3
> Transform your content ideas into viral Facebook posts with AI-powered automation in just 30 minutes!
Facebook Graph Api, Google Sheets, Chain Llm +4
It uses the power of Google Gemini's multimodal capabilities to read the document, identify key fields, and organize the data into a structured format, saving it directly to a Google Sheet. Healthcare
Google Drive, HTTP Request, Google Sheets +4