{ "name": "Case 83 - Academic Researcher - Thought Leadership Tracker", "nodes": [ { "parameters": { "rule": { "interval": [ { "field": "cronExpression", "expression": "0 9 * * 1" } ] } }, "type": "n8n-nodes-base.scheduleTrigger", "typeVersion": 1.2, "position": [ -1040, -144 ], "id": "e0885daf-b3a3-4671-9ecc-5646c16b5ac5", "name": "Weekly Schedule - Monday 9 AM" }, { "parameters": { "actorId": { "__rl": true, "value": "buIWk2uOUzTmcLsuB", "mode": "list", "cachedResultName": "Linkedin Post Search Scraper (No Cookies) (harvestapi/linkedin-post-search)", "cachedResultUrl": "https://console.apify.com/actors/buIWk2uOUzTmcLsuB/input" }, "customBody": "{\n \"authorUrls\": [\n \"https://www.linkedin.com/school/stanford-university\",\n \"https://www.linkedin.com/school/massachusetts-institute-of-technology\",\n \"https://www.linkedin.com/school/harvard-university\",\n \"https://www.linkedin.com/school/university-of-california-berkeley\",\n \"https://www.linkedin.com/school/university-of-oxford\",\n \"https://www.linkedin.com/school/university-of-cambridge\"\n ],\n \"searchQueries\": [\n \"research\",\n \"published\",\n \"paper\",\n \"findings\",\n \"conference\",\n \"study\"\n ],\n \"maxPosts\": 50,\n \"scrapeComments\": false,\n \"scrapeReactions\": false\n}" }, "type": "@apify/n8n-nodes-apify.apify", "typeVersion": 1, "position": [ -864, -144 ], "id": "fbdd054c-2f86-4120-b762-c79913013fae", "name": "Scrape LinkedIn Research Posts", "credentials": { "apifyApi": { "id": "w5S6YBbbyUddEfQA", "name": "Apify account" } } }, { "parameters": { "resource": "Datasets", "datasetId": "={{ $json.defaultDatasetId }}" }, "type": "@apify/n8n-nodes-apify.apify", "typeVersion": 1, "position": [ -688, -144 ], "id": "b2f1fbd5-f946-4c27-bccb-75eaeecdfdf2", "name": "Get Dataset Items", "credentials": { "apifyApi": { "id": "w5S6YBbbyUddEfQA", "name": "Apify account" } } }, { "parameters": { "modelId": { "__rl": true, "value": "gpt-4o-mini", "mode": "list", "cachedResultName": "GPT-4o-mini" }, "responses": { "values": [ { "role": "system", "content": "=You are an Academic Thought Leadership Validation Expert.\n\nAnalyze LinkedIn posts to determine if they are genuine academic thought leadership content.\n\nReturn ONLY valid JSON in this exact format:\n{\n \"is_thought_leadership\": \"yes|no\",\n \"confidence\": 0.95,\n \"reason\": \"brief explanation\"\n}\n\nCriteria for \"yes\" (genuine thought leadership):\n✅ Shares original research findings or publications\n✅ Presents conference paper or keynote insights\n✅ Offers expert analysis on emerging trends/topics\n✅ Discusses research methodology or innovations\n✅ Announces research collaborations or grants\n✅ Reviews or critiques existing literature\n✅ Proposes new theoretical frameworks\n✅ Shares data-driven insights from studies\n✅ Discusses academic partnerships or initiatives\n\nCriteria for \"no\" (NOT thought leadership):\n❌ Personal opinions without research backing\n❌ Promotional content for courses/programs\n❌ Student achievement announcements\n❌ Administrative or event logistics posts\n❌ Casual sharing of others' content without analysis\n❌ Job postings or hiring announcements\n❌ Generic inspirational quotes or advice\n❌ Social/networking events without research focus\n\nRules:\n1. confidence: 0-1 scale (0.9+ for very clear thought leadership)\n2. reason: 1 sentence explaining the decision\n3. Be strict - require substantive academic/research content\n4. Return ONLY the JSON object, no explanations" }, { "content": "=Analyze this LinkedIn post to determine if it's genuine thought leadership:\n\nAuthor: {{ $json.author.name }}\nAuthor Info: {{ $json.author.info }}\nPost Date: {{ $json.postedAt.date }}\nPost Content: {{ $json.content }}\n\nReturn only JSON." } ] }, "builtInTools": {}, "options": {} }, "type": "@n8n/n8n-nodes-langchain.openAi", "typeVersion": 2.1, "position": [ -528, -144 ], "id": "9353271d-8dd7-497e-a68c-79c16cb25d76", "name": "AI Validation Filter", "credentials": { "openAiApi": { "id": "ICwxUBbatsF2sDvy", "name": "OpenAi account" } } }, { "parameters": { "jsCode": "// UNIVERSAL AI RESPONSE PARSER - Same code for ALL cases\nconst items = [];\nconst input = $input.all();\n\nfunction extractJSON(text) {\n const jsonMatch = text.match(/\\{[\\s\\S]*\\}/);\n if (!jsonMatch) return null;\n return jsonMatch[0];\n}\n\ninput.forEach((item, index) => {\n try {\n let aiText = item.json.output[0].content[0].text || '';\n \n // Clean markdown code blocks\n aiText = aiText\n .replace(/```json/gi, '')\n .replace(/```/g, '')\n .trim();\n \n // Extract JSON object\n const jsonStr = extractJSON(aiText);\n \n if (!jsonStr) {\n throw new Error('No JSON found in AI response');\n }\n \n // Parse and return clean JSON\n const parsed = JSON.parse(jsonStr);\n items.push({ json: parsed });\n \n } catch (error) {\n console.error(`Parse error for item ${index}:`, error.message);\n // Return empty object on error - no case-specific fields\n items.push({ json: {} });\n }\n});\n\nreturn items;" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -256, -144 ], "id": "c313c32f-fb25-4d49-a0a3-2cf831605856", "name": "Parse AI Validation" }, { "parameters": { "assignments": { "assignments": [ { "id": "is_thought_leadership", "name": "is_thought_leadership", "value": "={{ $json.is_thought_leadership }}", "type": "string" }, { "id": "confidence", "name": "confidence", "value": "={{ $json.confidence }}", "type": "number" }, { "id": "reason", "name": "reason", "value": "={{ $json.reason }}", "type": "string" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ -80, -144 ], "id": "73f1d7c8-ae7e-42ac-a214-e9a90508a96f", "name": "Edit Fields - Validation" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 1 }, "conditions": [ { "id": "condition-001", "leftValue": "={{ $json.is_thought_leadership }}", "rightValue": "yes", "operator": { "type": "string", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.filter", "typeVersion": 2, "position": [ 96, -144 ], "id": "47bf9f24-2541-47ce-bfaf-935407466b13", "name": "Filter Only Thought Leadership" }, { "parameters": { "modelId": { "__rl": true, "value": "gpt-4o-mini", "mode": "list", "cachedResultName": "GPT-4o-mini" }, "responses": { "values": [ { "role": "system", "content": "=You are an Academic Research Intelligence Analyst.\n\nExtract structured thought leadership information from LinkedIn posts.\n\nReturn ONLY valid JSON in this exact format:\n{\n \"researcher_name\": \"Name of researcher/author\",\n \"institution\": \"University/Research center affiliation\",\n \"research_area\": \"Field/topic of research (e.g., 'Machine Learning', 'Climate Science')\",\n \"content_type\": \"Paper|Conference|Opinion|Partnership|Funding|Review|Dataset|Framework\",\n \"key_insight\": \"Main finding or contribution in 150 chars or less\",\n \"methodology\": \"Research method if mentioned (Experimental|Survey|Meta-analysis|Theoretical|Computational|Other)\",\n \"collaboration_potential\": \"Yes|No - does this indicate openness to collaboration?\",\n \"citation_worthy\": \"Yes|No - is this significant enough to cite?\",\n \"relevance_score\": \"High|Medium|Low - relevance to AI/ML field\",\n \"publication_venue\": \"Journal/Conference name if mentioned, otherwise 'Not specified'\"\n}\n\nExtraction Rules:\n1. researcher_name: Extract from author info\n2. institution: Extract university/organization affiliation\n3. research_area: Identify specific research domain\n4. content_type:\n - Paper = Published research paper\n - Conference = Conference presentation/proceedings\n - Opinion = Expert commentary/perspective\n - Partnership = Research collaboration announcement\n - Funding = Grant or funding announcement\n - Review = Literature review or critique\n - Dataset = New dataset release\n - Framework = New theoretical framework\n5. key_insight: Summarize main contribution briefly\n6. methodology: Extract research method used\n7. collaboration_potential:\n - Yes = Mentions seeking collaborators, open research, or partnerships\n - No = Standalone announcement\n8. citation_worthy:\n - Yes = Novel finding, significant result, or major contribution\n - No = Incremental or preliminary work\n9. relevance_score: Assess relevance to AI/ML (adjust field as needed)\n10. publication_venue: Extract journal/conference name\n\nReturn ONLY the JSON object, no explanations." }, { "content": "=Extract thought leadership intelligence from this LinkedIn post:\n\nAuthor: {{ $('Get Dataset Items').item.json.author.name }}\nAuthor Info: {{ $('Get Dataset Items').item.json.author.info }}\nPost Date: {{ $('Get Dataset Items').item.json.postedAt.date }}\nPost Content: {{ $('Get Dataset Items').item.json.content }}\nEngagement: {{ $('Get Dataset Items').item.json.engagement.likes }} likes, {{ $('Get Dataset Items').item.json.engagement.comments }} comments\n\nReturn only JSON." } ] }, "builtInTools": {}, "options": {} }, "type": "@n8n/n8n-nodes-langchain.openAi", "typeVersion": 2.1, "position": [ 256, -144 ], "id": "c032171f-2492-4835-b320-f106fa787d9d", "name": "AI Extract Research Intelligence", "credentials": { "openAiApi": { "id": "ICwxUBbatsF2sDvy", "name": "OpenAi account" } } }, { "parameters": { "jsCode": "// UNIVERSAL AI RESPONSE PARSER - Same code for ALL cases\nconst items = [];\nconst input = $input.all();\n\nfunction extractJSON(text) {\n const jsonMatch = text.match(/\\{[\\s\\S]*\\}/);\n if (!jsonMatch) return null;\n return jsonMatch[0];\n}\n\ninput.forEach((item, index) => {\n try {\n let aiText = item.json.output[0].content[0].text || '';\n \n // Clean markdown code blocks\n aiText = aiText\n .replace(/```json/gi, '')\n .replace(/```/g, '')\n .trim();\n \n // Extract JSON object\n const jsonStr = extractJSON(aiText);\n \n if (!jsonStr) {\n throw new Error('No JSON found in AI response');\n }\n \n // Parse and return clean JSON\n const parsed = JSON.parse(jsonStr);\n items.push({ json: parsed });\n \n } catch (error) {\n console.error(`Parse error for item ${index}:`, error.message);\n // Return empty object on error - no case-specific fields\n items.push({ json: {} });\n }\n});\n\nreturn items;" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 528, -144 ], "id": "de68ad33-62a6-4c9a-9f8d-2339599acf36", "name": "Parse AI Response" }, { "parameters": { "assignments": { "assignments": [ { "id": "timestamp", "name": "analysis_timestamp", "value": "={{ new Date().toISOString() }}", "type": "string" }, { "id": "researcher_name", "name": "researcher_name", "value": "={{ $json.researcher_name }}", "type": "string" }, { "id": "institution", "name": "institution", "value": "={{ $json.institution }}", "type": "string" }, { "id": "research_area", "name": "research_area", "value": "={{ $json.research_area }}", "type": "string" }, { "id": "content_type", "name": "content_type", "value": "={{ $json.content_type }}", "type": "string" }, { "id": "key_insight", "name": "key_insight", "value": "={{ $json.key_insight }}", "type": "string" }, { "id": "methodology", "name": "methodology", "value": "={{ $json.methodology }}", "type": "string" }, { "id": "collaboration", "name": "collaboration_potential", "value": "={{ $json.collaboration_potential }}", "type": "string" }, { "id": "citation", "name": "citation_worthy", "value": "={{ $json.citation_worthy }}", "type": "string" }, { "id": "relevance", "name": "relevance_score", "value": "={{ $json.relevance_score }}", "type": "string" }, { "id": "publication", "name": "publication_venue", "value": "={{ $json.publication_venue }}", "type": "string" }, { "id": "author_profile", "name": "author_profile", "value": "={{ $('Get Dataset Items').item.json.author?.linkedinUrl || '' }}", "type": "string" }, { "id": "author_info", "name": "author_info", "value": "={{ $('Get Dataset Items').item.json.author?.info || '' }}", "type": "string" }, { "id": "post_content", "name": "post_content", "value": "={{ $('Get Dataset Items').item.json.content || '' }}", "type": "string" }, { "id": "post_date", "name": "post_date", "value": "={{ $('Get Dataset Items').item.json.postedAt?.date || '' }}", "type": "string" }, { "id": "post_url", "name": "post_url", "value": "={{ $('Get Dataset Items').item.json.linkedinUrl || '' }}", "type": "string" }, { "id": "likes", "name": "likes_count", "value": "={{ $('Get Dataset Items').item.json.engagement?.likes || 0 }}", "type": "number" }, { "id": "comments", "name": "comments_count", "value": "={{ $('Get Dataset Items').item.json.engagement?.comments || 0 }}", "type": "number" }, { "id": "shares", "name": "shares_count", "value": "={{ $('Get Dataset Items').item.json.engagement?.shares || 0 }}", "type": "number" }, { "id": "total_engagement", "name": "engagement_total", "value": "={{ ($('Get Dataset Items').item.json.engagement?.likes || 0) + ($('Get Dataset Items').item.json.engagement?.comments || 0) + ($('Get Dataset Items').item.json.engagement?.shares || 0) }}", "type": "number" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 688, -144 ], "id": "71370b45-e67c-43db-ad8f-b51d096cbce0", "name": "Edit Fields" }, { "parameters": { "operation": "append", "documentId": { "__rl": true, "value": "1tzpeRbCgcOJzZj-sORBbZaCuXZjE2A7cLvcEuuouM3Q", "mode": "list", "cachedResultName": "Case 83 - Academic Researcher Log", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1tzpeRbCgcOJzZj-sORBbZaCuXZjE2A7cLvcEuuouM3Q/edit?usp=drivesdk" }, "sheetName": { "__rl": true, "value": "gid=0", "mode": "list", "cachedResultName": "Sheet1", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1tzpeRbCgcOJzZj-sORBbZaCuXZjE2A7cLvcEuuouM3Q/edit#gid=0" }, "columns": { "mappingMode": "defineBelow", "value": { "Analysis_Date": "={{ $json.analysis_timestamp }}", "Researcher_Name": "={{ $json.researcher_name }}", "Institution": "={{ $json.institution }}", "Research_Area": "={{ $json.research_area }}", "Content_Type": "={{ $json.content_type }}", "Key_Insight": "={{ $json.key_insight }}", "Methodology": "={{ $json.methodology }}", "Collaboration_Potential": "={{ $json.collaboration_potential }}", "Citation_Worthy": "={{ $json.citation_worthy }}", "Relevance_Score": "={{ $json.relevance_score }}", "Publication_Venue": "={{ $json.publication_venue }}", "Author_Profile": "={{ $json.author_profile }}", "Post_Date": "={{ $json.post_date }}", "Likes": "={{ $json.likes_count }}", "Comments": "={{ $json.comments_count }}", "Shares": "={{ $json.shares_count }}", "Total_Engagement": "={{ $json.engagement_total }}", "Post_URL": "={{ $json.post_url }}", "Post_Content": "={{ $json.post_content }}" }, "matchingColumns": [], "schema": [ { "id": "Analysis_Date", "displayName": "Analysis_Date", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Researcher_Name", "displayName": "Researcher_Name", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Institution", "displayName": "Institution", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Research_Area", "displayName": "Research_Area", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Content_Type", "displayName": "Content_Type", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Key_Insight", "displayName": "Key_Insight", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Methodology", "displayName": "Methodology", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Collaboration_Potential", "displayName": "Collaboration_Potential", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Citation_Worthy", "displayName": "Citation_Worthy", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Relevance_Score", "displayName": "Relevance_Score", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Publication_Venue", "displayName": "Publication_Venue", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Author_Profile", "displayName": "Author_Profile", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Post_Date", "displayName": "Post_Date", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Likes", "displayName": "Likes", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Comments", "displayName": "Comments", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Shares", "displayName": "Shares", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Total_Engagement", "displayName": "Total_Engagement", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Post_URL", "displayName": "Post_URL", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true }, { "id": "Post_Content", "displayName": "Post_Content", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true } ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {} }, "type": "n8n-nodes-base.googleSheets", "typeVersion": 4.7, "position": [ 848, -144 ], "id": "466d60e9-b86a-4a74-a490-4e38c339e4bd", "name": "Log to Google Sheet", "credentials": { "googleSheetsOAuth2Api": { "id": "LOs2dbk9lby0NfDM", "name": "Google Sheets account" } } }, { "parameters": { "jsCode": "// Aggregate all items from Google Sheets into email-ready summary\nconst allItems = $input.all();\n\n// Count by research area\nconst areaCounts = {};\nallItems.forEach(item => {\n const area = item.json.Research_Area || 'Other';\n areaCounts[area] = (areaCounts[area] || 0) + 1;\n});\n\nconst topAreas = Object.entries(areaCounts)\n .sort((a, b) => b[1] - a[1])\n .slice(0, 10);\n\n// Count by content type\nconst contentTypeCounts = {};\nallItems.forEach(item => {\n const type = item.json.Content_Type || 'Other';\n contentTypeCounts[type] = (contentTypeCounts[type] || 0) + 1;\n});\n\n// Count by institution\nconst institutionCounts = {};\nallItems.forEach(item => {\n const institution = item.json.Institution || 'Unknown';\n institutionCounts[institution] = (institutionCounts[institution] || 0) + 1;\n});\n\nconst topInstitutions = Object.entries(institutionCounts)\n .sort((a, b) => b[1] - a[1])\n .slice(0, 10);\n\n// Citation-worthy research\nconst citationWorthy = allItems.filter(item => \n item.json.Citation_Worthy === 'Yes'\n);\n\n// Collaboration opportunities\nconst collaborationOps = allItems.filter(item => \n item.json.Collaboration_Potential === 'Yes'\n);\n\n// High relevance research\nconst highRelevance = allItems.filter(item => \n item.json.Relevance_Score === 'High'\n);\n\n// Count by methodology\nconst methodCounts = {};\nallItems.forEach(item => {\n const method = item.json.Methodology || 'Other';\n methodCounts[method] = (methodCounts[method] || 0) + 1;\n});\n\n// Build HTML table rows\nconst tableRows = allItems.map(item => {\n const data = item.json;\n const relevanceColor = data.Relevance_Score === 'High' ? '#28a745' : \n data.Relevance_Score === 'Medium' ? '#ffc107' : '#6c757d';\n \n return `\n \n ${data.Researcher_Name || 'N/A'}\n ${data.Institution || 'N/A'}\n ${data.Research_Area || 'N/A'}\n ${data.Content_Type || 'N/A'}\n ${data.Relevance_Score || 'N/A'}\n ${data.Citation_Worthy || 'N/A'}\n View\n \n `;\n}).join('');\n\n// Return single aggregated item\nreturn {\n json: {\n week_start: new Date(Date.now() - 7*24*60*60*1000).toISOString().split('T')[0],\n week_end: new Date().toISOString().split('T')[0],\n total_posts: allItems.length,\n top_research_areas: topAreas,\n content_type_breakdown: Object.entries(contentTypeCounts),\n top_institutions: topInstitutions,\n citation_worthy_count: citationWorthy.length,\n collaboration_opportunities_count: collaborationOps.length,\n high_relevance_count: highRelevance.length,\n methodology_breakdown: Object.entries(methodCounts),\n table_rows: tableRows,\n all_research: allItems.map(item => item.json)\n }\n};" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1024, -144 ], "id": "36727dd8-ef8e-487b-9b0e-8860b2260991", "name": "Aggregate Weekly Summary" }, { "parameters": { "sendTo": "researcher@university.edu", "subject": "=📊 Weekly Thought Leadership Report: {{ $json.week_start }} to {{ $json.week_end }}", "message": "=WEEKLY THOUGHT LEADERSHIP INTELLIGENCE REPORT\n================================================\nReport Period: {{ $json.week_start }} to {{ $json.week_end }}\n\nOVERVIEW:\nTotal Research Posts Tracked: {{ $json.total_posts }}\nCitation-Worthy Research: {{ $json.citation_worthy_count }}\nCollaboration Opportunities: {{ $json.collaboration_opportunities_count }}\nHigh Relevance Posts: {{ $json.high_relevance_count }}\n\nTOP RESEARCH AREAS:\n{{ $json.top_research_areas.map(([area, count], i) => (i+1) + '. ' + area + ' (' + count + ' posts)').join('\\n') }}\n\nCONTENT TYPE BREAKDOWN:\n{{ $json.content_type_breakdown.map(([type, count]) => type + ': ' + count).join('\\n') }}\n\nTOP INSTITUTIONS:\n{{ $json.top_institutions.map(([inst, count], i) => (i+1) + '. ' + inst + ' (' + count + ' posts)').join('\\n') }}\n\nMETHODOLOGY DISTRIBUTION:\n{{ $json.methodology_breakdown.map(([method, count]) => method + ': ' + count).join('\\n') }}\n\n🎯 ACTION ITEMS:\n📚 {{ $json.citation_worthy_count }} citation-worthy papers to review\n🤝 {{ $json.collaboration_opportunities_count }} collaboration opportunities to explore\n⭐ {{ $json.high_relevance_count }} highly relevant posts to your field\n\nFull thought leadership details in Google Sheets.\n\nGenerated: {{ new Date().toLocaleDateString() }}", "options": {} }, "type": "n8n-nodes-base.gmail", "typeVersion": 2.1, "position": [ 1200, -144 ], "id": "9e917f22-2062-4a5c-aab3-f2d951f65f85", "name": "Send Weekly Summary Email", "webhookId": "08ffa92c-adb0-4f91-90ce-dc0902dd03b4", "credentials": { "gmailOAuth2": { "id": "cyqCGWcggZNMcSOv", "name": "Gmail account" } } } ], "pinData": {}, "connections": { "Weekly Schedule - Monday 9 AM": { "main": [ [ { "node": "Scrape LinkedIn Research Posts", "type": "main", "index": 0 } ] ] }, "Scrape LinkedIn Research Posts": { "main": [ [ { "node": "Get Dataset Items", "type": "main", "index": 0 } ] ] }, "Get Dataset Items": { "main": [ [ { "node": "AI Validation Filter", "type": "main", "index": 0 } ] ] }, "AI Validation Filter": { "main": [ [ { "node": "Parse AI Validation", "type": "main", "index": 0 } ] ] }, "Parse AI Validation": { "main": [ [ { "node": "Edit Fields - Validation", "type": "main", "index": 0 } ] ] }, "Edit Fields - Validation": { "main": [ [ { "node": "Filter Only Thought Leadership", "type": "main", "index": 0 } ] ] }, "Filter Only Thought Leadership": { "main": [ [ { "node": "AI Extract Research Intelligence", "type": "main", "index": 0 } ] ] }, "AI Extract Research Intelligence": { "main": [ [ { "node": "Parse AI Response", "type": "main", "index": 0 } ] ] }, "Parse AI Response": { "main": [ [ { "node": "Edit Fields", "type": "main", "index": 0 } ] ] }, "Edit Fields": { "main": [ [ { "node": "Log to Google Sheet", "type": "main", "index": 0 } ] ] }, "Log to Google Sheet": { "main": [ [ { "node": "Aggregate Weekly Summary", "type": "main", "index": 0 } ] ] }, "Aggregate Weekly Summary": { "main": [ [ { "node": "Send Weekly Summary Email", "type": "main", "index": 0 } ] ] } }, "active": false, "settings": { "executionOrder": "v1" }, "versionId": "905e2692-4112-4488-9a3e-105433b279e2", "meta": { "instanceId": "3a43da28588548e21903e71cf1dc3ddd65c24bf0c62e7e4b77542ffe87ad79c6" }, "id": "aWcfVgPL4jkDAKpj", "tags": [] }