This workflow follows the Chainllm → Google Sheets 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 →
{
"name": "AI News Research Automation with n8n - Public Sanitized",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "ai-news-research-assignment-10",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-1280,
-240
],
"id": "f288b6c6-63d1-4027-bcff-1fde3f85b10a",
"name": "Webhook"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "ddfc71ab-7fcf-4f30-bbf3-26f9bc394302",
"name": "topic",
"value": "={{$json.body.topic}}",
"type": "string"
},
{
"id": "b8722b21-0e39-4cef-97d0-7c246f48dc5c",
"name": "articles",
"value": "={{$json.body.articles}}",
"type": "number"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-1104,
-240
],
"id": "9f48fcdc-d6c9-4a90-af7d-4f1ac4f19fdf",
"name": "Validate Input"
},
{
"parameters": {
"url": "https://gnews.io/api/v4/search",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "q",
"value": "={{$json.topic}}"
},
{
"name": "lang",
"value": "en"
},
{
"name": "max",
"value": "={{$json.articles}}"
},
{
"name": "apikey",
"value": "YOUR_GNEWS_API_KEY"
}
]
},
"options": {
"response": {
"response": {
"responseFormat": "json"
}
}
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
-928,
-240
],
"id": "feba2c8d-7ee6-4acf-b861-8c7291455984",
"name": "Fetch News",
"onError": "continueRegularOutput"
},
{
"parameters": {
"fieldToSplitOut": "articles",
"options": {}
},
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
-736,
-240
],
"id": "740d2e9d-b36d-4e0c-a46e-d8a0df804ca3",
"name": "Split Out Articles"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "47ca1bdb-7958-43df-b572-181db577c36b",
"name": "title",
"value": "={{$json.title}}",
"type": "string"
},
{
"id": "74e2d9e1-f895-437b-a60e-09df15ab6918",
"name": "source",
"value": "={{$json.source.name}}",
"type": "string"
},
{
"id": "ceade662-41b5-42e1-9584-3f29eefe1112",
"name": "published_date",
"value": "={{$json.publishedAt}}",
"type": "string"
},
{
"id": "9ed90f73-dfc5-4168-a8aa-e6628e8cd93f",
"name": "article_url",
"value": "={{$json.url}}",
"type": "string"
},
{
"id": "43e657e7-de6d-45d7-b744-a9daad686c9b",
"name": "description",
"value": "={{$json.description}}",
"type": "string"
},
{
"id": "c44260ac-c855-4305-964f-a2fd2e536f92",
"name": "content",
"value": "={{$json.content}}",
"type": "string"
},
{
"id": "369245d9-ae93-4478-a8cf-5e1def3c22c9",
"name": "topic",
"value": "={{ $('Validate Input').item.json.topic }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-544,
-240
],
"id": "8dcb8b4c-02d5-40aa-ba55-dca41efb63b6",
"name": "Normalize Article Data"
},
{
"parameters": {
"model": "anthropic/claude-3-haiku",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"typeVersion": 1,
"position": [
-432,
16
],
"id": "d3e03f6a-f286-439c-aed9-598d7c784ad3",
"name": "OpenRouter Chat Model"
},
{
"parameters": {
"promptType": "define",
"text": "=Analyze this AI news article.\n\nTopic:\n{{ $json.topic }}\n\nTitle:\n{{ $json.title }}\n\nSource:\n{{ $json.source }}\n\nPublished Date:\n{{ $json.published_date }}\n\nArticle URL:\n{{ $json.article_url }}\n\nDescription:\n{{ $json.description }}\n\nContent:\n{{ $json.content }}\n\nTasks:\n1. Generate a 2-3 sentence summary.\n2. Extract one clear key takeaway.\n3. Assign exactly one category:\nAI Product, AI Research, Funding, Open Source, Business.\n4. Give a LinkedIn Worthiness Score from 1 to 10.\n\nScoring guide:\n- 9-10: Highly relevant, timely, strong LinkedIn discussion potential.\n- 7-8: Useful and relevant for AI/business audience.\n- 5-6: Interesting but not very strong for LinkedIn.\n- 1-4: Low relevance or weak business value.",
"hasOutputParser": true,
"messages": {
"messageValues": [
{
"message": "=You are an expert AI news research analyst and LinkedIn content strategist.\n\nYour job is to analyze AI news articles for a startup founder who publishes daily LinkedIn posts about AI.\n\nYou must:\n- Summarize the article in 2\u20133 clear sentences.\n- Extract one practical key takeaway.\n- Classify the article into exactly one category:\n AI Product, AI Research, Funding, Open Source, or Business.\n- Give a LinkedIn Worthiness Score from 1 to 10.\n- Prefer business relevance, founder usefulness, novelty, timeliness, and discussion potential when scoring.\n- Return only valid JSON.\n- Do not use markdown.\n- Do not add explanations outside the JSON.\n- Do not invent facts that are not supported by the article."
}
]
},
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.9,
"position": [
-352,
-240
],
"id": "1ca347b4-590a-4aca-afa4-d495e5d82a5e",
"name": "AI News Research",
"onError": "continueRegularOutput"
},
{
"parameters": {
"schemaType": "manual",
"inputSchema": "={\n \"type\": \"object\",\n \"properties\": {\n \"summary\": {\n \"type\": \"string\",\n \"description\": \"A 2-3 sentence summary of the article\"\n },\n \"key_takeaway\": {\n \"type\": \"string\",\n \"description\": \"One clear practical takeaway from the article\"\n },\n \"category\": {\n \"type\": \"string\",\n \"enum\": [\n \"AI Product\",\n \"AI Research\",\n \"Funding\",\n \"Open Source\",\n \"Business\"\n ],\n \"description\": \"The category that best fits the article\"\n },\n \"linkedin_worthiness_score\": {\n \"type\": \"number\",\n \"minimum\": 1,\n \"maximum\": 10,\n \"description\": \"A score from 1 to 10 showing how suitable this article is for a LinkedIn post\"\n }\n },\n \"required\": [\n \"summary\",\n \"key_takeaway\",\n \"category\",\n \"linkedin_worthiness_score\"\n ]\n}"
},
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"typeVersion": 1.3,
"position": [
-160,
16
],
"id": "e8dd6270-3525-4bac-872e-e7ff177f24c0",
"name": "Structured Output Parser"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "c241293c-357c-463c-81d4-a621ea96a19f",
"name": "Title",
"value": "={{ $('Normalize Article Data').item.json.title }}",
"type": "string"
},
{
"id": "4ec39262-5e5d-4542-93bf-c07cc5f3de07",
"name": "Source",
"value": "={{ $('Normalize Article Data').item.json.source }}",
"type": "string"
},
{
"id": "9c9204f5-829e-40b0-989f-ec61aa9afee8",
"name": "Published Date",
"value": "={{ $('Normalize Article Data').item.json.published_date }}",
"type": "string"
},
{
"id": "3cb78ebd-328d-4bcd-b92e-fb4717aa56b1",
"name": "Summary",
"value": "={{ $json.output.summary }}",
"type": "string"
},
{
"id": "3a28d2e2-eee3-46da-81b8-d7e31a37b468",
"name": "Key Takeaway",
"value": "={{ $json.output.key_takeaway }}",
"type": "string"
},
{
"id": "f775e6e4-c758-452b-a472-fa2c438b22ba",
"name": "Category",
"value": "={{ $json.output.category }}",
"type": "string"
},
{
"id": "d29a3144-45c2-42d3-bddb-7857ba44661c",
"name": "LinkedIn Worthiness Score",
"value": "={{ $json.output.linkedin_worthiness_score }}",
"type": "number"
},
{
"id": "0873e064-a826-4443-806f-bd94effe64bc",
"name": "Article URL",
"value": "={{ $('Normalize Article Data').item.json.article_url }}",
"type": "string"
},
{
"id": "6233f8b2-c22e-4dae-8903-16eaa9851a3f",
"name": "Topic",
"value": "={{ $('Normalize Article Data').item.json.topic }}",
"type": "string"
},
{
"id": "fcfa7d81-b6bd-4688-9b52-239da735c945",
"name": "Processed At",
"value": "={{ $now }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
-32,
-240
],
"id": "f33e3d3e-a5bb-460f-8259-817dab84f7b6",
"name": "Prepare Sheet Row"
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "YOUR_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "News Results",
"mode": "name"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"Title": "={{ $json.Title }}",
"Source": "={{ $json.Source }}",
"Published Date": "={{ $json['Published Date'] }}",
"Summary": "={{ $json.Summary }}",
"Key Takeaway": "={{ $json['Key Takeaway'] }}",
"Category": "={{ $json.Category }}",
"LinkedIn Worthiness Score": "={{ $json['LinkedIn Worthiness Score'] }}",
"Article URL": "={{ $json['Article URL'] }}",
"Topic": "={{ $json.Topic }}",
"Processed At": "={{ $json['Processed At'] }}"
},
"matchingColumns": [],
"schema": [
{
"id": "Title",
"displayName": "Title",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Source",
"displayName": "Source",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Published Date",
"displayName": "Published Date",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Summary",
"displayName": "Summary",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Key Takeaway",
"displayName": "Key Takeaway",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Category",
"displayName": "Category",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "LinkedIn Worthiness Score",
"displayName": "LinkedIn Worthiness Score",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Article URL",
"displayName": "Article URL",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Topic",
"displayName": "Topic",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
},
{
"id": "Processed At",
"displayName": "Processed At",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.7,
"position": [
192,
-240
],
"id": "db897334-605b-4d44-9eb2-e7d28c6bc154",
"name": "Save to Google Sheets",
"onError": "continueRegularOutput"
},
{
"parameters": {
"jsCode": "const inputItems = $input.all();\n\nconst articles = [];\n\nfor (const item of inputItems) {\n const row = item.json;\n\n articles.push({\n title: row.Title || \"\",\n source: row.Source || \"\",\n published_date: row[\"Published Date\"] || \"\",\n summary: row.Summary || \"\",\n key_takeaway: row[\"Key Takeaway\"] || \"\",\n category: row.Category || \"\",\n linkedin_worthiness_score: Number(row[\"LinkedIn Worthiness Score\"] || 0),\n article_url: row[\"Article URL\"] || \"\",\n topic: row.Topic || \"\",\n processed_at: row[\"Processed At\"] || \"\"\n });\n}\n\n// Sort logic:\n// 1. Higher LinkedIn Worthiness Score first\n// 2. If scores are same, newer Published Date first\narticles.sort((a, b) => {\n const scoreDiff = b.linkedin_worthiness_score - a.linkedin_worthiness_score;\n\n if (scoreDiff !== 0) {\n return scoreDiff;\n }\n\n const dateA = new Date(a.published_date || 0).getTime();\n const dateB = new Date(b.published_date || 0).getTime();\n\n return dateB - dateA;\n});\n\nconst top3 = articles.slice(0, 3);\n\nreturn [\n {\n json: {\n success: true,\n message: \"AI news research completed successfully\",\n total_articles_processed: articles.length,\n sorting_logic: \"Sorted by LinkedIn Worthiness Score. If scores are tied, the most recent Published Date is prioritized.\",\n top_3_articles: top3\n }\n }\n];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
432,
-240
],
"id": "e821bb8b-fd22-4e05-b540-65c485b02c67",
"name": "Sort Top 3 Articles"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ $json }}",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.5,
"position": [
656,
-240
],
"id": "029a1a27-f892-4afe-9972-428614b59317",
"name": "Return Top 3 Articles"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "Validate Input",
"type": "main",
"index": 0
}
]
]
},
"Validate Input": {
"main": [
[
{
"node": "Fetch News",
"type": "main",
"index": 0
}
]
]
},
"Fetch News": {
"main": [
[
{
"node": "Split Out Articles",
"type": "main",
"index": 0
}
]
]
},
"Split Out Articles": {
"main": [
[
{
"node": "Normalize Article Data",
"type": "main",
"index": 0
}
]
]
},
"Normalize Article Data": {
"main": [
[
{
"node": "AI News Research",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI News Research",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI News Research": {
"main": [
[
{
"node": "Prepare Sheet Row",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "AI News Research",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Prepare Sheet Row": {
"main": [
[
{
"node": "Save to Google Sheets",
"type": "main",
"index": 0
}
]
]
},
"Save to Google Sheets": {
"main": [
[
{
"node": "Sort Top 3 Articles",
"type": "main",
"index": 0
}
]
]
},
"Sort Top 3 Articles": {
"main": [
[
{
"node": "Return Top 3 Articles",
"type": "main",
"index": 0
}
]
]
},
"Return Top 3 Articles": {
"main": [
[]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false,
"timeSavedMode": "fixed",
"timezone": "Asia/Dhaka",
"callerPolicy": "workflowsFromSameOwner"
},
"versionId": "65cbfe22-9d0b-4ea8-a3b1-ec1a10c46496",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "cOuM1uhxGHbK69qP",
"tags": [
{
"updatedAt": "2026-04-19T10:36:06.995Z",
"createdAt": "2026-04-19T10:36:06.995Z",
"id": "qINUxDoUTgKfZG2J",
"name": "OSTAD"
},
{
"updatedAt": "2026-07-06T18:46:13.942Z",
"createdAt": "2026-07-06T18:46:13.942Z",
"id": "z2sCe7JGfPfVJrD0",
"name": "Assignment-10 Module-10"
}
]
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI News Research Automation with n8n - Public Sanitized. Uses httpRequest, lmChatOpenRouter, chainLlm, outputParserStructured. Webhook trigger; 12 nodes.
Source: https://github.com/jamilur0101/ai-news-research-automation-n8n/blob/main/workflows/ai-news-research-automation.sanitized.json — 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.
The workflow loads a list of test cases from a Google Sheet (previous results stored from an LLM) For each test case, we execute a call to an LLM judge in parallel (using HTTP Request + Webhook nodes)
Output Parser Structured, Google Sheets, HTTP Request +2
This workflow demonstrates a simple way to run evals on a set of test cases stored in a Google Sheet.
Google Sheets, Output Parser Structured, Chain Llm +3
• Extract AI Overviews from Google Search - Receives data from browser extension via webhook • Convert HTML to Markdown - Automatically processes and cleans AI Overview content • Store in Google Sheet
Google Sheets, HTTP Request, OpenRouter Chat +1
Splitout Code. Uses lmChatOpenRouter, outputParserStructured, httpRequest, stickyNote. Event-driven trigger; 11 nodes.
OpenRouter Chat, Output Parser Structured, HTTP Request +2
This workflow automates web scraping of Amazon search result pages by retrieving raw HTML, cleaning it to retain only the relevant product elements, and then using an LLM to extract structured product
OpenRouter Chat, Output Parser Structured, HTTP Request +2