This workflow follows the Google Sheets → 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 →
{
"name": "03 \u00b7 RSS \u2192 GPT \u2192 Post Draft (human approval)",
"nodes": [
{
"parameters": {
"content": "## 03 \u00b7 RSS \u2192 GPT \u2192 post draft\n**Schedule \u2192 RSS \u2192 dedupe \u2192 GPT draft \u2192 Sheets + Telegram approval**\n\nDeduplication uses `$getWorkflowStaticData`, so restarting the workflow\ndoes not re-post old articles. Max 3 drafts per run keeps the cost flat.\n\nNothing is published automatically: the draft goes to Telegram for review.",
"height": 280,
"width": 560,
"color": 7
},
"id": "00000003-0000-4000-8000-000000000000",
"name": "Overview",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-280,
-220
]
},
{
"parameters": {
"rule": {
"interval": [
{
"field": "hours",
"hoursInterval": 3
}
]
}
},
"id": "00000003-0000-4000-8000-000000000001",
"name": "Every 3 Hours",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
-260,
140
]
},
{
"parameters": {
"url": "https://openai.com/blog/rss.xml",
"options": {
"ignoreSSL": false
}
},
"id": "00000003-0000-4000-8000-000000000002",
"name": "Read RSS Feed",
"type": "n8n-nodes-base.rssFeedRead",
"typeVersion": 1.1,
"position": [
-40,
140
],
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 5000
},
{
"parameters": {
"jsCode": "// Workflow static data survives between executions, so the same article is\n// never drafted twice. Keep the seen-list bounded or it grows forever.\nconst state = $getWorkflowStaticData('global');\nstate.seen = Array.isArray(state.seen) ? state.seen : [];\n\nconst seen = new Set(state.seen);\nconst fresh = [];\n\nfor (const item of $input.all()) {\n const guid = item.json.guid ?? item.json.link;\n if (!guid || seen.has(guid)) continue;\n\n seen.add(guid);\n fresh.push({\n json: {\n guid,\n title: item.json.title ?? '',\n link: item.json.link ?? '',\n published_at: item.json.isoDate ?? item.json.pubDate ?? new Date().toISOString(),\n excerpt: String(item.json.contentSnippet ?? item.json.content ?? '').slice(0, 3000),\n },\n });\n\n if (fresh.length >= 3) break; // cap the per-run cost\n}\n\nstate.seen = Array.from(seen).slice(-500);\nreturn fresh;"
},
"id": "00000003-0000-4000-8000-000000000003",
"name": "Filter New Articles",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
180,
140
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.openai.com/v1/chat/completions",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"model\": \"gpt-4o-mini\",\n \"temperature\": 0.6,\n \"response_format\": { \"type\": \"json_object\" },\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You ghost-write LinkedIn posts for an AI engineer. Reply with JSON only, using exactly these keys: hook (one scroll-stopping sentence, no emoji), body (120-180 words, first person, concrete, no buzzwords, no hashtags inside), takeaway (one actionable sentence), hashtags (array of 3-5 lowercase tags without the # sign), skip (true when the article is not worth posting about). Never invent statistics that are not in the source.\"\n },\n {\n \"role\": \"user\",\n \"content\": {{ JSON.stringify(`Title: ${$json.title}\\nLink: ${$json.link}\\n\\n${$json.excerpt}`) }}\n }\n ]\n}",
"options": {
"timeout": 60000
}
},
"id": "00000003-0000-4000-8000-000000000004",
"name": "Draft Post",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
400,
140
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 2000
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "// Paired-item lookup, with a positional fallback if the pairing is lost.\nlet article = {};\ntry {\n article = $('Filter New Articles').item.json;\n} catch (error) {\n article = $('Filter New Articles').all()[$itemIndex]?.json ?? {};\n}\n\nconst raw = $json.choices?.[0]?.message?.content ?? '{}';\n\nlet draft;\ntry {\n draft = JSON.parse(raw);\n} catch (error) {\n draft = { skip: true, hook: '', body: String(raw).slice(0, 500), takeaway: '', hashtags: [] };\n}\n\nconst hashtags = Array.isArray(draft.hashtags) ? draft.hashtags : [];\nconst post = [draft.hook, '', draft.body, '', draft.takeaway, '', hashtags.map((t) => `#${t}`).join(' ')]\n .join('\\n')\n .trim();\n\nreturn {\n json: {\n ...article,\n skip: Boolean(draft.skip),\n post,\n hook: draft.hook ?? '',\n hashtags: hashtags.join(', '),\n drafted_at: new Date().toISOString(),\n },\n};"
},
"id": "00000003-0000-4000-8000-000000000005",
"name": "Format Draft",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
620,
140
]
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose",
"version": 2
},
"conditions": [
{
"id": "c1",
"leftValue": "={{ $json.skip }}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "00000003-0000-4000-8000-000000000006",
"name": "Worth Posting?",
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
840,
140
]
},
{
"parameters": {
"operation": "append",
"documentId": {
"__rl": true,
"value": "REPLACE_WITH_GOOGLE_SHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Content Drafts",
"mode": "name"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"Drafted At": "={{ $json.drafted_at }}",
"Source Title": "={{ $json.title }}",
"Source Link": "={{ $json.link }}",
"Published At": "={{ $json.published_at }}",
"Hook": "={{ $json.hook }}",
"Post": "={{ $json.post }}",
"Hashtags": "={{ $json.hashtags }}",
"Status": "draft"
},
"matchingColumns": [],
"schema": []
},
"options": {}
},
"id": "00000003-0000-4000-8000-000000000007",
"name": "Save Draft to Sheet",
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.5,
"position": [
1080,
40
],
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 2000
},
{
"parameters": {
"chatId": "REPLACE_WITH_TELEGRAM_CHAT_ID",
"text": "=\ud83d\udcdd <b>New post draft</b>\n\n{{ $json.post }}\n\n\u2014\u2014\u2014\nSource: {{ $json.title }}\n{{ $json.link }}",
"additionalFields": {
"parse_mode": "HTML",
"disable_web_page_preview": true
}
},
"id": "00000003-0000-4000-8000-000000000008",
"name": "Send Draft for Review",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
1300,
40
],
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"onError": "continueRegularOutput"
},
{
"parameters": {},
"id": "00000003-0000-4000-8000-000000000009",
"name": "Skipped",
"type": "n8n-nodes-base.noOp",
"typeVersion": 1,
"position": [
1080,
260
]
}
],
"connections": {
"Every 3 Hours": {
"main": [
[
{
"node": "Read RSS Feed",
"type": "main",
"index": 0
}
]
]
},
"Read RSS Feed": {
"main": [
[
{
"node": "Filter New Articles",
"type": "main",
"index": 0
}
]
]
},
"Filter New Articles": {
"main": [
[
{
"node": "Draft Post",
"type": "main",
"index": 0
}
]
]
},
"Draft Post": {
"main": [
[
{
"node": "Format Draft",
"type": "main",
"index": 0
}
]
]
},
"Format Draft": {
"main": [
[
{
"node": "Worth Posting?",
"type": "main",
"index": 0
}
]
]
},
"Worth Posting?": {
"main": [
[
{
"node": "Save Draft to Sheet",
"type": "main",
"index": 0
}
],
[
{
"node": "Skipped",
"type": "main",
"index": 0
}
]
]
},
"Save Draft to Sheet": {
"main": [
[
{
"node": "Send Draft for Review",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true
},
"tags": []
}
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.
googleSheetsOAuth2ApihttpHeaderAuthtelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
03 · RSS → GPT → Post Draft (human approval). Uses rssFeedRead, httpRequest, googleSheets, telegram. Scheduled trigger; 10 nodes.
Source: https://github.com/wanderfool95/n8n-ai-workflows/blob/main/workflows/03-rss-content-pipeline.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.
Auto Hunt. Uses httpRequest, googleSheets, rssFeedRead, telegram. Scheduled trigger; 78 nodes.
HTTP Request, Google Sheets, RSS Feed Read +1
Auto-Hunt. Uses httpRequest, googleSheets, rssFeedRead, telegram. Scheduled trigger; 78 nodes.
HTTP Request, Google Sheets, RSS Feed Read +1
Competitor Feature-Parity Watcher. Uses rssFeedRead, httpRequest, googleSheets, telegram. Scheduled trigger; 24 nodes.
RSS Feed Read, HTTP Request, Google Sheets +1
FireReach — Always-On SDR Workflow. Uses rssFeedRead, httpRequest, telegram, googleSheets. Scheduled trigger; 11 nodes.
RSS Feed Read, HTTP Request, Telegram +1
. Uses googleSheets, telegram, httpRequest, wise. Scheduled trigger; 36 nodes.
Google Sheets, Telegram, HTTP Request +2