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 Pulse \u2014 Deep Analysis (Pass 2)",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "hours",
"hoursInterval": 4
}
]
}
},
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.3,
"position": [
0,
-32
],
"id": "9accff48-f95c-479c-a3fa-9cfcd7c174df",
"name": "Schedule Trigger"
},
{
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:11434/api/generate",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "{\"model\": \"mistral\", \"prompt\": \"\", \"stream\": false, \"keep_alive\": 0}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
224,
96
],
"id": "74d62c6d-70bf-4e32-9a99-6785478e316b",
"name": "Unload Mistral",
"onError": "continueRegularOutput"
},
{
"parameters": {
"language": "pythonNative",
"pythonCode": "import sqlite3\n\ndb_path = \"/data/ai-pulse/ai-pulse.db\"\nconn = sqlite3.connect(db_path)\nconn.row_factory = sqlite3.Row\ncursor = conn.cursor()\n\ncursor.execute(\"\"\"\n SELECT id, title, url, source_name, source_type, category, raw_content, relevance_score\n FROM articles\n WHERE relevance_score >= 60\n AND importance IS NULL\n ORDER BY relevance_score DESC\n LIMIT 100\n\"\"\")\nrows = cursor.fetchall()\nconn.close()\n\nreturn [{\"json\": dict(row)} for row in rows]"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
448,
96
],
"id": "f5ed13fc-0e76-432d-aa26-788085000208",
"name": "Fetch Promoted Articles"
},
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
672,
96
],
"id": "5d0df582-17e8-47d8-9305-47aa3a2a3b57",
"name": "Loop Promoted Articles"
},
{
"parameters": {
"language": "pythonNative",
"pythonCode": "import json as json_lib\n\nitems = _items\nresult = []\n\nfor item in items:\n data = item['json'] if 'json' in item else item\n\n title = str(data.get('title', 'Untitled'))[:300]\n source_name = str(data.get('source_name', 'Unknown'))\n category = str(data.get('category', 'general'))\n raw = str(data.get('raw_content', ''))[:3000]\n\n prompt = (\n \"You are an AI analyst writing for a Software Engineer who works on\\n\"\n \"AI-powered dev tooling, agentic workflows, context engineering,\\n\"\n \"prompt engineering, and workflow automation. He cares about practical,\\n\"\n \"engineering-focused insights he can apply immediately.\\n\\n\"\n f\"Analyze this article:\\nTitle: {title}\\nSource: {source_name}\\n\"\n f\"Category: {category}\\nContent: {raw}\\n\\n\"\n \"Return ONLY valid JSON, no other text:\\n\"\n \"{\\\"summary\\\": \\\"<2-3 sentence plain-language summary>\\\", \"\n \"\\\"importance\\\": <1-5>, \"\n \"\\\"importance_reasoning\\\": \\\"<why this rating>\\\", \"\n \"\\\"why_it_matters\\\": \\\"<one sentence connecting this to the reader's work>\\\", \"\n \"\\\"tags\\\": [\\\"<tag1>\\\", \\\"<tag2>\\\", \\\"<tag3>\\\"]}\"\n )\n\n body = json_lib.dumps({\n \"model\": \"llama3:8b\",\n \"prompt\": prompt,\n \"stream\": False,\n \"keep_alive\": \"10m\"\n })\n\n result.append({\"json\": {\n \"id\": data.get('id', 0),\n \"title\": title,\n \"source_name\": source_name,\n \"request_body\": body\n }})\n\nreturn result"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
896,
96
],
"id": "90d7e742-7721-4a9b-9ea8-7eeee4c3083d",
"name": "Prepare Pass 2 Prompt"
},
{
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:11434/api/generate",
"sendBody": true,
"contentType": "raw",
"rawContentType": "application/json",
"body": "={{ $json.request_body }}",
"options": {
"timeout": 300000
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
1120,
96
],
"id": "f6b5c175-e50f-44f8-b061-5a6ad22e1e9a",
"name": "Ollama Deep Analysis",
"onError": "continueRegularOutput"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "56c1f084-fc18-4100-9d55-d47d0a8f94d1",
"name": "article_id",
"value": "={{ $('Prepare Pass 2 Prompt').item.json.id }}",
"type": "string"
}
]
},
"includeOtherFields": true,
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1344,
96
],
"id": "8541caef-7577-4170-b250-f1e0793f24de",
"name": "Add Article ID"
},
{
"parameters": {
"language": "pythonNative",
"pythonCode": "import sqlite3\n\ndb_path = \"/data/ai-pulse/ai-pulse.db\"\nconn = sqlite3.connect(db_path)\ncursor = conn.cursor()\n\ncursor.execute(\"SELECT COUNT(*) FROM articles WHERE relevance_score >= 60 AND importance IS NULL\")\nremaining = cursor.fetchone()[0]\n\ncursor.execute(\"SELECT COUNT(*) FROM articles WHERE importance IS NOT NULL\")\nenriched = cursor.fetchone()[0]\n\ncursor.execute(\"SELECT importance, COUNT(*) FROM articles WHERE importance IS NOT NULL GROUP BY importance ORDER BY importance DESC\")\nratings = cursor.fetchall()\n\nconn.close()\n\nrating_summary = \", \".join([f\"{row[0]} stars: {row[1]}\" for row in ratings])\n\nreturn [{\"json\": {\"enriched_total\": enriched, \"remaining_to_enrich\": remaining, \"importance_distribution\": rating_summary}}]"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
896,
-96
],
"id": "1f8581da-dc6d-4441-9cca-0ef8efcefbd2",
"name": "Batch Summary"
},
{
"parameters": {
"language": "pythonNative",
"pythonCode": "import sqlite3\nimport json as json_lib\n\ndb_path = \"/data/ai-pulse/ai-pulse.db\"\n\nitems = _items\narticle_id = 0\nimportance = 0\nsummary = \"\"\nwhy_it_matters = \"\"\ntags = \"\"\nstatus = \"failed\"\n\nfor item in items:\n data = item['json'] if 'json' in item else item\n article_id = int(data.get('article_id', 0))\n response_text = str(data.get('response', ''))\n\n try:\n clean = response_text.strip()\n start = clean.find('{')\n end = clean.rfind('}') + 1\n if start >= 0 and end > start:\n parsed = json_lib.loads(clean[start:end])\n importance = int(parsed.get('importance', 0))\n summary = str(parsed.get('summary', ''))\n why_it_matters = str(parsed.get('why_it_matters', ''))\n tags_list = parsed.get('tags', [])\n tags = json_lib.dumps(tags_list)\n status = \"success\"\n except:\n importance = 1\n summary = \"Parse error\"\n status = \"parse_error\"\n\n if article_id > 0:\n conn = sqlite3.connect(db_path)\n cursor = conn.cursor()\n cursor.execute(\"\"\"\n UPDATE articles \n SET importance = ?, summary = ?, why_it_matters = ?, tags = ?\n WHERE id = ?\n \"\"\", (importance, summary, why_it_matters, tags, article_id))\n conn.commit()\n conn.close()\n\nreturn [{\"json\": {\"article_id\": article_id, \"importance\": importance, \"summary\": summary, \"status\": status}}]"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1568,
176
],
"id": "ccdfc1ae-d8b7-4f6b-8415-ce0ed7ba2a84",
"name": "Update Deep Analysis",
"onError": "continueRegularOutput"
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
0,
176
],
"id": "7b9c01ef-5b07-4b8d-a9ff-93aaf257532a",
"name": "When clicking \u2018Execute workflow\u2019"
}
],
"connections": {
"Schedule Trigger": {
"main": [
[
{
"node": "Unload Mistral",
"type": "main",
"index": 0
}
]
]
},
"Unload Mistral": {
"main": [
[
{
"node": "Fetch Promoted Articles",
"type": "main",
"index": 0
}
]
]
},
"Fetch Promoted Articles": {
"main": [
[
{
"node": "Loop Promoted Articles",
"type": "main",
"index": 0
}
]
]
},
"Loop Promoted Articles": {
"main": [
[
{
"node": "Batch Summary",
"type": "main",
"index": 0
}
],
[
{
"node": "Prepare Pass 2 Prompt",
"type": "main",
"index": 0
}
]
]
},
"Prepare Pass 2 Prompt": {
"main": [
[
{
"node": "Ollama Deep Analysis",
"type": "main",
"index": 0
}
]
]
},
"Ollama Deep Analysis": {
"main": [
[
{
"node": "Add Article ID",
"type": "main",
"index": 0
}
]
]
},
"Add Article ID": {
"main": [
[
{
"node": "Update Deep Analysis",
"type": "main",
"index": 0
}
]
]
},
"Update Deep Analysis": {
"main": [
[
{
"node": "Loop Promoted Articles",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Unload Mistral",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "37bf3b51-d5d4-48b8-9ba4-eb2389cc43f1",
"id": "2A6T3P7q3W4GKhxA",
"tags": []
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Pulse — Deep Analysis (Pass 2). Uses httpRequest. Scheduled trigger; 10 nodes.
Source: https://github.com/sh3lan93/ai-pulse/blob/b616cb8446522055bc8679b9f6c03b08b07c1441/n8n-workflows/03-pass2-analysis.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.
Birthday Automation - Production (Fixed). Uses stopAndError, httpRequest, emailSend, bannerbear. Scheduled trigger; 86 nodes.
Stop And Error, HTTP Request, Email Send +1
This template runs two scheduled workflows to govern Microsoft Entra ID (Azure AD) guest accounts by detecting stale users via Microsoft Graph, staging deletions in SharePoint with a 72-hour window, n
Microsoft SharePoint, Microsoft Teams, Microsoft Entra +1
Jira-Allure-Auto-Qa. Uses httpRequest, jira. Scheduled trigger; 68 nodes.
HTTP Request, Jira
Spotify-Sync-Surrealdb-V1. Uses httpRequest, n8n-nodes-surrealdb, spotify. Scheduled trigger; 62 nodes.
HTTP Request, N8N Nodes Surrealdb, Spotify
As n8n instances scale, teams often lose track of sub-workflows—who uses them, where they are referenced, and whether they can be safely updated. This leads to inefficiencies like unnecessary copies o
HTTP Request, n8n, N8N Trigger +1