Felix Kemeth This workflow corresponds to n8n.io template #11092 — we link there as the canonical source.
This workflow follows the Agent → HTTP Request 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "78c17a2b-6458-42e5-acb6-74b350d17e4a",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-592,
-32
],
"parameters": {
"rule": {
"interval": [
{
"field": "weeks",
"triggerAtHour": 9
}
]
}
},
"typeVersion": 1.2
},
{
"id": "41b2c6a0-7063-446e-9403-478e6c7b325b",
"name": "Call NewsAPI",
"type": "n8n-nodes-base.httpRequest",
"position": [
-80,
-32
],
"parameters": {
"url": "https://newsapi.org/v2/everything",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
}
},
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth",
"queryParameters": {
"parameters": [
{
"name": "from",
"value": "={{ DateTime.fromISO($json.timestamp).minus({ days: 7 }) }}"
},
{
"name": "q",
"value": "={{ $json.topics.replaceAll(\",\", \" OR \") }}"
},
{
"name": "sortBy",
"value": "relevancy"
}
]
}
},
"credentials": {
"httpQueryAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2,
"alwaysOutputData": false
},
{
"id": "81bdbf07-dc4a-4fef-9e69-eef731f4bb14",
"name": "Send a text message",
"type": "n8n-nodes-base.telegram",
"position": [
1376,
-32
],
"parameters": {
"text": "={{ \n $json.output.map(article => {\n const title = JSON.stringify(article.title).slice(1, -1);\n const content = JSON.stringify(article.content).slice(1, -1);\n const source = JSON.stringify(article.source).slice(1, -1);\n const url = JSON.stringify(article.url).slice(1, -1);\n\n return `*${title}*\\n${content}\\nSource: [${source}](${url})`;\n }).join('\\n\\n')\n}}",
"chatId": "89066090",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "a522827f-0470-452e-9b9a-1268dbc97ba2",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
528,
-32
],
"parameters": {
"options": {},
"fieldToSplitOut": "message.content.articles"
},
"typeVersion": 1
},
{
"id": "d34cda05-2f22-4358-8890-f53ec36600f9",
"name": "Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
944,
192
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"object\",\n\t\"properties\": {\n\t\t\"title\": {\n\t\t\t\"type\": \"string\"\n\t\t},\n\t\t\"content\": {\n\t\t\t\"type\": \"string\"\n\t\t},\n \"source\": {\n\t\t\t\"type\": \"string\"\n\t\t},\n \"url\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.3
},
{
"id": "d1fe8abe-76cf-4ce2-934d-5c78c4de8662",
"name": "Tavily",
"type": "@tavily/n8n-nodes-tavily.tavilyTool",
"position": [
816,
192
],
"parameters": {
"query": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Query', ``, 'string') }}",
"options": {}
},
"credentials": {
"tavilyApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "137623d3-5bd0-44a8-a915-36e9e0db1331",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"position": [
1152,
-32
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "output"
}
]
}
},
"typeVersion": 1
},
{
"id": "d9fdf9e3-b954-43cb-98f7-503f6015e2f3",
"name": "Set topics and language",
"type": "n8n-nodes-base.set",
"position": [
-368,
-32
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "2e1993fe-ae4d-46e0-be9f-6b02a18cc610",
"name": "topics",
"type": "string",
"value": "AI,n8n"
},
{
"id": "2c6e2dad-d54a-4387-9bf5-4751037f99d9",
"name": "language",
"type": "string",
"value": "English"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "f96519e3-2626-4651-9157-30ab40ffbf60",
"name": "Newsletter AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
752,
-32
],
"parameters": {
"text": "=You are a research writer that updates short news summaries into concise, factual articles.\n\n**Input:**\nTitle: {{ $json[\"title\"] }}\nSummary: {{ $json[\"summary\"] }}\nSource: {{ $json[\"source\"] }}\nOriginal URL: {{ $json[\"url\"] }}\nLanguage: {{ $('Set topics and language').item.json.language }}\n\n**Instructions:**\n\n1. Use **Tavily Search** to gather 2\u20133 reliable, recent, and relevant sources on this topic.\n2. Update the **title** if a more accurate or engaging one exists.\n3. Write **1\u20133 sentences** summarizing the topic, combining the original summary and information from the new sources.\n4. Return the original source name and url as well.\n\n**Output (JSON):**\n\n```json\n{\n \"title\": \"final article title\",\n \"content\": \"concise 1\u20133 sentence article content\",\n \"source\": \"the name of the original source\",\n \"url\": \"the url of the original source\"\n}\n```\n\n**Rules:**\n\n* Ensure the topic is relevant, informative, and timely.\n* Translate the article if necessary to comply with the desired language {{ $('Set topics and language').item.json.language }}.",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "699ff0a8-4412-45cb-b20d-ac4fa39c6077",
"name": "AI Topic Selector",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
176,
-32
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-5.1",
"cachedResultName": "GPT-5.1"
},
"options": {},
"messages": {
"values": [
{
"content": "=You are an assistant that selects the most relevant news articles for a user.\n\nInstructions: \n1. Choose the **5 most relevant non-overlapping articles** based on the user topics. \n2. For each article, provide: \n - title \n - short summary (1\u20132 sentences) \n - source name \n - url\n3. Output the results in the language specified by the user.\n\nOutput as a \"articles\" JSON array of objects, each with \"title\", \"summary\", \"source\" and \"url\".\n\nUser topics of interest: {{ $('Set topics and language').item.json.topics }}\nOutput language: {{ $('Set topics and language').item.json.language }}\n\nNewsAPI articles:\n\n{{ \n $json.articles.map(\n article => \n `Title: ${article.title}\nDescription: ${article.description}\nContent: ${article.content}\nSource: ${article.source.name}\nURL: ${article.url}`\n ).join('\\n---\\n')\n}}\n"
}
]
},
"jsonOutput": true
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "56bd39e6-6c7f-4357-898e-b5a85457e04a",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1296,
-256
],
"parameters": {
"width": 640,
"height": 608,
"content": "# AI Newsletter Workflow\n\n## How it works\nThis workflow runs weekly, fetches fresh news for your chosen topics, lets an AI pick the five most relevant articles, enriches each with additional research, and then sends a compact Markdown newsletter to Telegram. It combines NewsAPI for discovery, GPT\u20115 for reasoning and writing, and Tavily for fact-checked enrichment.\n\n## Setup steps\n1. Configure the schedule (weekly, Sunday 09:00 or your preferred time). \n2. Set `topics` (comma-separated) and `language` in `Set topics and language`. \n3. Add credentials: NewsAPI (query auth), OpenAI, Tavily, and Telegram bot/chat ID. \n\n## Customization\n- Tweak `topics` and `language` for different audiences or languages. \n- Adjust the schedule (day/time) to control when newsletters go out. \n- Change the number of selected articles or the AI prompts if you want shorter or more in\u2011depth summaries."
},
"typeVersion": 1
},
{
"id": "11b0c727-a68c-4849-a2a9-58cfaacc1e9a",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-640,
-256
],
"parameters": {
"color": 7,
"width": 432,
"height": 608,
"content": "## Schedule & Configuration\n\n\u2022 **Schedule Trigger**: Runs at 9am every Sunday per default.\n\u2022 **Set topics and language**: Configure your topics (comma-separated) and output language."
},
"typeVersion": 1
},
{
"id": "72a31337-843c-41a2-9e1e-19dee208cd01",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-192,
-256
],
"parameters": {
"color": 7,
"width": 848,
"height": 608,
"content": "## Fetch & Select articles\n\n- **Call NewsAPI**: Queries the last 7 days of news for your topics. \n- **AI Topic Selector**: Uses GPT\u20115.1 to select 5 non-overlapping, relevant articles. \n- **Split Out**: Turns the selected list into one item per article."
},
"typeVersion": 1
},
{
"id": "7a1c47b9-48cb-40bd-ad7e-81d36c0180bb",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
672,
-256
],
"parameters": {
"color": 7,
"width": 416,
"height": 608,
"content": "## Enrich Articles using AI\n\n- **Newsletter AI Agent**: Orchestrates GPT\u20115, Tavily and the parser per article. \n- **GPT-5.1**: Writes short, clear newsletter-style summaries. \n- **Tavily**: Adds fresh sources for grounding and factual checks. \n- **Parser**: Enforces JSON with `title`, `content`, `source`, `url`."
},
"typeVersion": 1
},
{
"id": "9b3ce9c9-34d5-419a-a53a-20b4c08ca57f",
"name": "GPT-5.1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
688,
192
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5.1",
"cachedResultName": "gpt-5.1"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "2fe6ee6c-9964-4bb0-be1d-30f9485637bf",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1104,
-256
],
"parameters": {
"color": 7,
"width": 496,
"height": 608,
"content": "## Aggregate & Send\n\n- **Aggregate**: Combines all enriched article objects into one list. \n- **Send a text message**: Formats the newsletter in Markdown and posts it to Telegram."
},
"typeVersion": 1
}
],
"connections": {
"Parser": {
"ai_outputParser": [
[
{
"node": "Newsletter AI Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Tavily": {
"ai_tool": [
[
{
"node": "Newsletter AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"GPT-5.1": {
"ai_languageModel": [
[
{
"node": "Newsletter AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Send a text message",
"type": "main",
"index": 0
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Newsletter AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Call NewsAPI": {
"main": [
[
{
"node": "AI Topic Selector",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Set topics and language",
"type": "main",
"index": 0
}
]
]
},
"AI Topic Selector": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"Newsletter AI Agent": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Send a text message": {
"main": [
[]
]
},
"Set topics and language": {
"main": [
[
{
"node": "Call NewsAPI",
"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.
httpQueryAuthopenAiApitavilyApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Staying up to date with fast-moving topics like AI, machine learning, research, or your specific industry can be tricky.
Source: https://n8n.io/workflows/11092/ — 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.
Who Is This For?
Telegram, Google Sheets Trigger, Lm Chat Mistral Cloud +17
Automatically generate professional-grade product photography and ready-to-use Instagram posts using the power of AI, delivered straight to your Telegram for approval.
Output Parser Structured, OpenAI Chat, Agent +3
Staying up to date with fast-moving topics like AI, machine learning, or your specific industry can be overwhelming. You either drown in daily noise or miss important developments between weekly diges
HTTP Request, Data Table, OpenAI Chat +5
Title: Create daily AI news digest and send to Telegram
HTTP Request, Agent, OpenAI Chat +5
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Mailgun, OpenAI, OpenAI Chat +8