Ranjan Dailata This workflow corresponds to n8n.io template #9924 — we link there as the canonical source.
This workflow follows the Chainllm → Informationextractor 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": "in11m3CofWPWeo7h",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Summarize & Extract Glassdoor Company Info with Google Gemini and Decode",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
},
{
"id": "rKOa98eAi3IETrLu",
"name": "HR",
"createdAt": "2025-04-13T04:59:30.580Z",
"updatedAt": "2025-04-13T04:59:30.580Z"
}
],
"nodes": [
{
"id": "e17438ec-00e7-4f0a-b57b-9597ffbae1ad",
"name": "When clicking \u2018Execute workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-560,
128
],
"parameters": {},
"typeVersion": 1
},
{
"id": "ad1c0eee-3b2d-4e15-8d4c-7756adea4fc2",
"name": "Set the Input Fields",
"type": "n8n-nodes-base.set",
"position": [
-336,
128
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "0bd5c0c2-dc62-466a-941c-98fdb0404d6c",
"name": "company_url",
"type": "string",
"value": "https://www.glassdoor.co.in/Overview/Working-at-Decode-Technologies-EI_IE4772827.11,30.htm"
},
{
"id": "31a57370-3210-4ece-b329-c10a0afc53af",
"name": "geo",
"type": "string",
"value": "India"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "db9ecca5-7fcb-4c0d-b80b-f6675ade9d34",
"name": "Decodo",
"type": "@decodo/n8n-nodes-decodo.decodo",
"position": [
-112,
128
],
"parameters": {
"geo": "={{ $('Set the Input Fields').item.json.geo }}",
"url": "={{ $('Set the Input Fields').item.json.company_url }}"
},
"credentials": {
"decodoApi": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "a80fabf3-d506-4896-8efa-71abc8f8fdd3",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
352,
48
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\",\n \"description\": \"Full summarized text including company overview, ratings, and insights\"\n },\n \"overview\": {\n \"type\": \"object\",\n \"properties\": {\n \"companyName\": { \"type\": \"string\" },\n \"rating\": { \"type\": \"number\" },\n \"location\": { \"type\": \"string\" },\n \"size\": { \"type\": \"string\" },\n \"type\": { \"type\": \"string\" },\n \"website\": { \"type\": \"string\" }\n }\n },\n \"keyTakeaways\": {\n \"type\": \"array\",\n \"items\": { \"type\": \"string\" }\n },\n \"ratingsBreakdown\": {\n \"type\": \"object\",\n \"properties\": {\n \"cultureAndValues\": { \"type\": \"number\" },\n \"diversityAndInclusion\": { \"type\": \"number\" },\n \"workLifeBalance\": { \"type\": \"number\" },\n \"seniorManagement\": { \"type\": \"number\" },\n \"compensationAndBenefits\": { \"type\": \"number\" },\n \"careerOpportunities\": { \"type\": \"number\" }\n }\n },\n \"reviewSnippets\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"role\": { \"type\": \"string\" },\n \"pros\": { \"type\": \"array\", \"items\": { \"type\": \"string\" } },\n \"cons\": { \"type\": \"array\", \"items\": { \"type\": \"string\" } }\n }\n }\n },\n \"faq\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"question\": { \"type\": \"string\" },\n \"answer\": { \"type\": \"string\" }\n }\n }\n },\n \"callToAction\": { \"type\": \"string\" }\n },\n \"required\": [\"text\"]\n }\n}\n"
},
"typeVersion": 1.3
},
{
"id": "97034fba-e1f5-43c4-8357-c5300033662c",
"name": "Structured Data Extractor",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
208,
-176
],
"parameters": {
"text": "=Analyze and extract structured data\n\n{{ $json.data.results[0].content }}",
"batching": {},
"promptType": "define",
"hasOutputParser": true
},
"executeOnce": false,
"retryOnFail": true,
"typeVersion": 1.7
},
{
"id": "ca125524-bf97-44b2-a3d1-30cc4ab9d865",
"name": "Summarizer",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
208,
328
],
"parameters": {
"text": "=Summarize the following content {{ $json.data.results[0].content }}",
"options": {},
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"detailed_summary\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.2
},
{
"id": "95bdc9dd-c788-4650-a87c-5ebd79cfa07a",
"name": "Google Gemini Chat Model for Summarization",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
280,
552
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "24837733-309c-4078-9197-36b4de71f330",
"name": "Google Gemini Chat Model for Structured Data Extract",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
192,
48
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "2917a190-f43a-4d7b-9a6a-36222e6f39ad",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
672,
96
],
"parameters": {},
"typeVersion": 3.2
},
{
"id": "574fbde4-7dc1-4996-b7a7-50138b589b68",
"name": "Read/Write Files from Disk",
"type": "n8n-nodes-base.readWriteFile",
"position": [
1344,
96
],
"parameters": {
"options": {},
"fileName": "=C:\\\\{{ $json.overview.companyName }}.json",
"operation": "write",
"dataPropertyName": "=data"
},
"typeVersion": 1
},
{
"id": "9140952a-0ba9-4d1e-b89a-5bd2b0a4dc16",
"name": "Format the Response",
"type": "n8n-nodes-base.code",
"position": [
896,
96
],
"parameters": {
"jsCode": "\nreturn $input.first().json.output[0];"
},
"typeVersion": 2
},
{
"id": "fa3f7f87-d789-4404-a0ed-684035ee3931",
"name": "Create a Binary Response",
"type": "n8n-nodes-base.function",
"position": [
1120,
96
],
"parameters": {
"functionCode": "\n\nitems[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "4e19fb55-a7b8-4ecf-b35c-857eb02f4cfc",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-560,
-128
],
"parameters": {
"color": 7,
"width": 384,
"height": 208,
"content": "\n\nGoogle Gemini LLM for the Structured Data Extraction and Summarization Purposes"
},
"typeVersion": 1
},
{
"id": "96511f0b-a610-4b2d-b73e-9f67f3ee121d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
48,
-240
],
"parameters": {
"color": 6,
"width": 592,
"height": 928,
"content": "## Google Gemini LLM Data Extract"
},
"typeVersion": 1
},
{
"id": "312bdbbb-6073-4891-bac4-d13e02390853",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-576,
304
],
"parameters": {
"width": 592,
"height": 624,
"content": "### **Purpose**\n\nAutomate **Glassdoor company intelligence extraction** \u2014 transforming raw company data from Glassdoor into **structured insights and summaries** using **Decodo API** + **Google Gemini**.\n\nGenerates a clean JSON report of the provided Glassdoor Company URL.\n\n\n### **Flow Summary**\n\n1. **Trigger** \u2013 Manually start workflow (`Execute Workflow`).\n2. **Set Input** \u2013 Enter `company_url` + `geo`.\n3. **Extract Raw Data** \u2013 Use **Decodo API** to pull Glassdoor overview, ratings, reviews, and FAQs.\n4. **Structure Data (Gemini + Parser)** \u2013 Gemini organizes data into:\n\n * Company details (name, size, type, website)\n * Ratings + reviews (pros/cons, job roles)\n * FAQs + key takeaways\n5. **Summarize Insights (Gemini)** \u2013 AI-driven summary on:\n\n * Company reputation & culture\n * Employee sentiment trends\n * Strengths, weaknesses, hiring notes\n6. **Merge & Format** \u2013 Combine structured + summarized data.\n7. **Export JSON** \u2013 Save to `C:\\{{CompanyName}}.json`.\n8. **Encode File (Base64)** \u2013 Prepare for API uploads or report downloads.\n\n"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "4cdc168b-a6bc-4012-b49f-b61531f33e36",
"connections": {
"Merge": {
"main": [
[
{
"node": "Format the Response",
"type": "main",
"index": 0
}
]
]
},
"Decodo": {
"main": [
[
{
"node": "Structured Data Extractor",
"type": "main",
"index": 0
},
{
"node": "Summarizer",
"type": "main",
"index": 0
}
]
]
},
"Summarizer": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Format the Response": {
"main": [
[
{
"node": "Create a Binary Response",
"type": "main",
"index": 0
}
]
]
},
"Set the Input Fields": {
"main": [
[
{
"node": "Decodo",
"type": "main",
"index": 0
}
]
]
},
"Create a Binary Response": {
"main": [
[
{
"node": "Read/Write Files from Disk",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Structured Data Extractor",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Structured Data Extractor": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Set the Input Fields",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model for Summarization": {
"ai_languageModel": [
[
{
"node": "Summarizer",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model for Structured Data Extract": {
"ai_languageModel": [
[
{
"node": "Structured Data Extractor",
"type": "ai_languageModel",
"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.
decodoApigooglePalmApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow automates company research and intelligence extraction from Glassdoor using Decode API for data retrieval and Google Gemini for AI-powered summarization.
Source: https://n8n.io/workflows/9924/ — 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.
Content - Newsletter Agent. Uses formTrigger, chainLlm, outputParserStructured, httpRequest. Event-driven trigger; 87 nodes.
Form Trigger, Chain Llm, Output Parser Structured +7
This n8n template automates complaint mining from unstructured text sources and turns raw user feedback into clear, actionable insights. It uses AI to identify recurring complaints, pain points, and t
Output Parser Structured, Chain Llm, Google Gemini Chat +5
Community nodes can only be installed on self-hosted instances of n8n.
HTTP Request, Google Gemini Chat, Chain Llm +4
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Telegram Trigger, Google Gemini Chat, Chain Llm +5
The Scrape and Analyze Amazon Product Info with Decodo + OpenAI workflow automates the process of extracting product information from an Amazon product page and transforming it into meaningful insight
@Decodo/N8N Nodes Decodo, OpenAI Chat, Output Parser Structured +3