Ai-powered Linkedin Connection Recommender

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 →

{
  "id": "fnSWZ5XCdbq6snzS",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "AI-Powered LinkedIn Connection Recommender",
  "tags": [],
  "nodes": [
    {
      "id": "ef9e2f3b-c06a-484a-8903-2f37b35728f3",
      "name": "Search LinkedIn Profiles",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -600,
        4.76293103448279
      ],
      "parameters": {
        "url": "https://serpapi.com/search.json",
        "options": {},
        "sendQuery": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpBasicAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "engine",
              "value": "google"
            },
            {
              "name": "q",
              "value": "=site:linkedin.com/in \"{{ $json.Position }}\" \"{{ $json.Location }}\" {{ $json.Skills.split(',')[0] }}"
            },
            {
              "name": "api_key",
              "value": "="
            },
            {
              "name": "num",
              "value": "200"
            },
            {
              "name": "start",
              "value": "0"
            }
          ]
        }
      },
      "credentials": {
        "httpBasicAuth": {
          "name": "<your credential>"
        },
        "httpQueryAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4
    },
    {
      "id": "34999f59-ae4b-4ef6-9603-bc5f6b2798d0",
      "name": "AI Profile Analysis",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        -160,
        4.76293103448279
      ],
      "parameters": {
        "text": "=You are a LinkedIn networking expert. Analyze the following user profile and potential connections to provide intelligent networking recommendations.\n\nUser Profile:\n- Name: {{ $json.userProfile.name }}\n- Position: {{ $json.userProfile.current_position }}\n- Industry: {{ $json.userProfile.industry }}\n- Location: {{ $json.userProfile.location }}\n- Skills: {{ $json.userProfile.skills }}\n- Interests: {{ $json.userProfile.interests }}\n- Target Roles: {{ $json.userProfile.target_roles }}\n- Preferred Companies: {{ $json.userProfile.company_types }}\n\nPotential Connections Found:\n{{ $json.foundProfiles.map(p => `- ${p.name}: ${p.headline}`).join('\\n') }}\n\nPlease provide a JSON response with the following structure:\n{\n  \"scored_profiles\": [\n    {\n      \"name\": \"Profile Name\",\n      \"score\": 8.5,\n      \"reasons\": [\"Similar role\", \"Same industry\", \"Skill overlap\"]\n    }\n  ],\n  \"top_connections\": [\n    // Top 10 recommended profiles with full details\n  ],\n  \"connection_strategies\": [\n    \"Personalized connection message suggestion for each top profile\"\n  ],\n  \"networking_insights\": \"Key insights about networking opportunities and industry trends\"\n}\n\nScore profiles from 1-10 based on:\n- Role alignment with user's target positions\n- Industry relevance\n- Skill complementarity\n- Networking value\n- Career growth potential\n\nFocus on quality connections that could provide mutual value.",
        "batching": {},
        "promptType": "define"
      },
      "typeVersion": 1.7
    },
    {
      "id": "d8205e9b-e176-477c-a8e7-2f1eb94bc3cb",
      "name": "Ollama Model1",
      "type": "@n8n/n8n-nodes-langchain.lmOllama",
      "position": [
        -72,
        224.7629310344828
      ],
      "parameters": {
        "model": "llama3.2-16000:latest",
        "options": {
          "topP": 0.9,
          "temperature": 0.7
        }
      },
      "credentials": {
        "ollamaApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "482f65e9-4075-4d60-8bc8-3c078f8c7acc",
      "name": "Send email",
      "type": "n8n-nodes-base.emailSend",
      "position": [
        656,
        4.76293103448279
      ],
      "parameters": {
        "text": "={{ $json.body }}",
        "options": {},
        "subject": "={{ $json.subject }}",
        "toEmail": "{{ $json.from }}",
        "fromEmail": "user@example.com",
        "emailFormat": "text"
      },
      "credentials": {
        "smtp": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "c759dfb7-9935-41e0-9d38-e41ff48c8b0b",
      "name": "Create Email",
      "type": "n8n-nodes-base.code",
      "position": [
        436,
        4.76293103448279
      ],
      "parameters": {
        "jsCode": "// Get the input data (your JSON)\nconst data = items[0].json;\n\n// Build the email text\nlet emailText = `\ud83d\udcca Networking Report for ${data.user_profile.name}\\n`;\nemailText += `\\nInterests: ${data.user_profile.interests}`;\nemailText += `\\nTarget Industry: ${data.user_profile.target_industry}\\n`;\n\nemailText += `\\nSummary:\\n`;\nemailText += `- Total Profiles Found: ${data.summary.total_profiles_found}\\n`;\nemailText += `- Analyzed Connections: ${data.summary.analyzed_connections}\\n`;\nemailText += `- High Priority: ${data.summary.high_priority}\\n`;\nemailText += `- Medium Priority: ${data.summary.medium_priority}\\n`;\nemailText += `- Average Score: ${data.summary.average_score}\\n`;\n\nemailText += `\\nTop Connection Recommendations:\\n`;\ndata.connection_recommendations.forEach((rec, index) => {\n    emailText += `\\n${index + 1}. ${rec.name} (${rec.priority} Priority, Score: ${rec.aiScore})`;\n    emailText += `\\n   ${rec.description}`;\n    emailText += `\\n   Mutual Connections: ${rec.mutual_connections}`;\n    emailText += `\\n   Reason: ${rec.connectionReason}`;\n    emailText += `\\n   Suggested Message: \"${rec.suggestedMessage}\"\\n`;\n});\n\nemailText += `\\nNext Steps:\\n`;\ndata.next_steps.forEach((step, i) => {\n    emailText += `- ${step}\\n`;\n});\n\nemailText += `\\nAI Insights:\\n${data.ai_insights}\\n`;\n\nemailText += `\\nBest Networking Times:\\nDays: ${data.networking_strategy.best_days.join(\", \")}\\nTimes: ${data.networking_strategy.best_times.join(\", \")}\\n`;\n\nreturn [{\n    json: {\n        subject: `Networking Report - ${data.user_profile.name}`,\n        body: emailText\n    }\n}];\n"
      },
      "typeVersion": 2
    },
    {
      "id": "7e27272d-1c4e-4e15-b7be-f0ef85937c13",
      "name": "Your Profile Information",
      "type": "n8n-nodes-base.set",
      "position": [
        -820,
        4.76293103448279
      ],
      "parameters": {
        "fields": {
          "values": [
            {
              "name": "Name"
            },
            {
              "name": "Position"
            },
            {
              "name": "Industry"
            },
            {
              "name": "Location"
            },
            {
              "name": "Skills"
            },
            {
              "name": "Interests"
            },
            {
              "name": "Target Roles"
            },
            {
              "name": "Company Types"
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "a9d1762a-aaf2-45a5-a5fc-381ec2d174c5",
      "name": "Process LinkedIn Search Results",
      "type": "n8n-nodes-base.code",
      "position": [
        -380,
        4.76293103448279
      ],
      "parameters": {
        "jsCode": "// Process search results and extract LinkedIn profiles\nconst results = $json.organic_results || [];\n\n// Get user profile from the previous node\nconst userProfile = $input.first().json || {};\n\n// Filter and process LinkedIn profiles\nconst linkedinProfiles = results\n  .filter(result => {\n    const link = result.link || '';\n    return link.includes('linkedin.com/in/') && \n           !link.includes('/posts/') && \n           !link.includes('/activity/');\n  })\n  .map(result => {\n    let name = result.title || 'Unknown';\n    // Clean up the title to extract just the name\n    name = name.replace(/\\s*[-|]\\s*LinkedIn.*$/i, '').trim();\n    \n    return {\n      name: name,\n      headline: result.snippet || result.title || '',\n      link: result.link,\n      description: result.snippet || '',\n      source: 'Google Search via SerpAPI'\n    };\n  })\n  .slice(0, 15); // Limit to top 15 results\n\n// Safely extract skills - handle undefined/null values\nconst getFirstSkill = (skills) => {\n  if (!skills || typeof skills !== 'string') {\n    return '';\n  }\n  const skillsArray = skills.split(',');\n  return skillsArray.length > 0 ? skillsArray[0].trim() : '';\n};\n\n// Build search query with safe property access\nconst buildSearchQuery = () => {\n  const position = userProfile.Position || '';\n  const location = userProfile.Location || '';\n  const firstSkill = getFirstSkill(userProfile.Skills);\n  \n  return `site:linkedin.com/in \"${position}\" \"${location}\" ${firstSkill}`.trim();\n};\n\n// Return structured data for AI analysis\nreturn {\n  json: {\n    userProfile: {\n      name: $('Your Profile Information').first().json.Name || '',\n      current_position: $('Your Profile Information').first().json.Position || '',\n      industry: $('Your Profile Information').first().json.Industry || '',\n      location:  $('Your Profile Information').first().json.Location|| '',\n      skills: $('Your Profile Information').first().json.Skills|| '',\n      interests: $('Your Profile Information').first().json.Interests || '',\n      target_roles: $('Your Profile Information').first().json['Target Roles']|| '',\n      company_types: $('Your Profile Information').first().json['Company Types'] || ''\n    },\n    foundProfiles: linkedinProfiles,\n    totalFound: linkedinProfiles.length,\n    searchQuery: buildSearchQuery()\n  }\n};"
      },
      "typeVersion": 2,
      "alwaysOutputData": true
    },
    {
      "id": "808cb1fa-9970-4d0e-8d34-37eea340fdb4",
      "name": "Create Final Recommendations",
      "type": "n8n-nodes-base.code",
      "position": [
        216,
        4.76293103448279
      ],
      "parameters": {
        "jsCode": "// Process AI recommendations and create final output\nconst inputData = $input.first();\nconst inputText = inputData.json?.text || inputData.json || inputData;\n\nlet aiRecommendations = {};\ntry {\n  // Extract JSON from the text content\n  const content = typeof inputText === 'string' ? inputText : JSON.stringify(inputText);\n  \n  // Try to parse JSON from the AI response\n  const jsonMatch = content.match(/```json\\n([\\s\\S]*?)\\n```/) || content.match(/\\{[\\s\\S]*\\}/);\n  if (jsonMatch) {\n    const jsonString = jsonMatch[1] || jsonMatch[0];\n    aiRecommendations = JSON.parse(jsonString);\n  } else {\n    throw new Error('No JSON found in response');\n  }\n} catch (error) {\n  console.log('Could not parse AI response:', error.message);\n  console.log('Input data:', inputData);\n  \n  // Create fallback recommendations if parsing fails\n  aiRecommendations = {\n    scored_profiles: [],\n    top_connections: [],\n    connection_strategies: [],\n    networking_insights: 'Focus on building meaningful professional relationships in your industry.'\n  };\n}\n\n// Helper function to safely split and get first element\nfunction safeGetFirst(str, delimiter = ',') {\n  if (!str || typeof str !== 'string') return '';\n  const parts = str.split(delimiter);\n  return parts.length > 0 ? parts[0].trim() : '';\n}\n\n// Helper function to safely split string\nfunction safeSplit(str, delimiter = ',') {\n  if (!str || typeof str !== 'string') return [];\n  return str.split(delimiter).map(item => item.trim()).filter(item => item);\n}\n\n// Helper function to generate connection message\nfunction generateConnectionMessage(profile, index) {\n  if (!profile || !profile.name) return 'Hi! I\\'d love to connect and share professional insights.';\n  \n  const firstName = safeGetFirst(profile.name, ' ');\n  const description = profile.description || '';\n  \n  // Create personalized messages based on profile\n  if (description.toLowerCase().includes('devops')) {\n    return `Hi ${firstName}, I'm interested in DevOps and cloud technologies. I'd love to connect and learn from your experience!`;\n  } else if (description.toLowerCase().includes('aws') || description.toLowerCase().includes('cloud')) {\n    return `Hi ${firstName}, I noticed your expertise in cloud computing. Would love to connect and share insights about the industry!`;\n  } else {\n    return `Hi ${firstName}, I'd love to connect with a fellow professional and learn from your experience in the industry.`;\n  }\n}\n\n// Helper function to extract tags from description\nfunction extractTags(description) {\n  if (!description) return ['Professional Contact'];\n  \n  const tags = [];\n  const descText = description.toLowerCase();\n  \n  // Add technology tags\n  const techs = ['aws', 'azure', 'gcp', 'devops', 'terraform', 'ansible', 'jenkins', 'kubernetes', 'docker'];\n  techs.forEach(tech => {\n    if (descText.includes(tech)) {\n      tags.push(tech.toUpperCase());\n    }\n  });\n  \n  // Add role tags\n  if (descText.includes('senior') || descText.includes('lead')) {\n    tags.push('Senior Level');\n  }\n  \n  if (descText.includes('mentor') || descText.includes('enthusiast')) {\n    tags.push('Mentor');\n  }\n  \n  return tags.length > 0 ? tags : ['Professional Contact'];\n}\n\n// Process the connections from AI recommendations\nconst connections = aiRecommendations.top_connections || [];\nconst scoredProfiles = aiRecommendations.scored_profiles || [];\n\nconst enhancedConnections = connections.map((profile, index) => {\n  // Find matching score data\n  const scoreData = scoredProfiles.find(p => \n    p.name && profile.name && \n    p.name.toLowerCase().trim() === profile.name.toLowerCase().trim()\n  );\n  \n  const score = scoreData?.score || (9.5 - index * 0.3); // Fallback scoring\n  \n  return {\n    name: profile.name || 'Unknown',\n    description: profile.description || '',\n    connections: profile.connections || 0,\n    mutual_connections: profile.mutual_connections || 0,\n    priority: score >= 8.5 ? 'High' : score >= 7.5 ? 'Medium' : 'Low',\n    aiScore: score,\n    connectionReason: scoreData?.reasons?.join(', ') || 'Professional networking opportunity',\n    suggestedMessage: generateConnectionMessage(profile, index),\n    tags: extractTags(profile.description),\n    estimatedResponseRate: score >= 8.5 ? 'High (70-90%)' : score >= 7.5 ? 'Medium (40-70%)' : 'Low (20-40%)',\n    link: profile.link || '#'\n  };\n}).sort((a, b) => b.aiScore - a.aiScore); // Sort by AI score\n\n// Create individual connection strategies\nconst connectionStrategies = enhancedConnections.map(conn => {\n  const firstName = safeGetFirst(conn.name, ' ');\n  return `${firstName}: ${conn.suggestedMessage.replace(`Hi ${firstName}, `, '')}`;\n});\n\nreturn {\n  json: {\n    summary: {\n      total_profiles_found: scoredProfiles.length,\n      analyzed_connections: enhancedConnections.length,\n      high_priority: enhancedConnections.filter(c => c.priority === 'High').length,\n      medium_priority: enhancedConnections.filter(c => c.priority === 'Medium').length,\n      low_priority: enhancedConnections.filter(c => c.priority === 'Low').length,\n      average_score: enhancedConnections.length > 0 ? \n        (enhancedConnections.reduce((sum, c) => sum + c.aiScore, 0) / enhancedConnections.length).toFixed(1) : 0\n    },\n    user_profile: {\n      name: \"Vrushti Sukhadiya\", // Extracted from the analysis text\n      interests: \"DevOps, Cloud Computing, Automation\",\n      target_industry: \"IT, Tech Startups, Cloud Companies\"\n    },\n    connection_recommendations: enhancedConnections,\n    connection_strategies: connectionStrategies,\n    ai_insights: aiRecommendations.networking_insights || 'Focus on building meaningful professional relationships in your industry.',\n    networking_strategy: {\n      weekly_goal: '5-10 new connections',\n      best_days: ['Tuesday', 'Wednesday', 'Thursday'],\n      best_times: ['9-11 AM', '2-4 PM'],\n      follow_up_schedule: 'Within 48 hours of connection acceptance',\n      focus_areas: ['DevOps professionals', 'Cloud Computing experts', 'AI/ML enthusiasts']\n    },\n    next_steps: [\n      'Start with highest-scored profiles (Mihir Suthar - 9.5, Muneeswaran M - 9.2)',\n      'Check for mutual connections before reaching out',\n      'Engage with their recent posts about DevOps/Cloud topics',\n      'Send personalized connection requests highlighting common interests',\n      'Follow up with thoughtful messages about industry trends',\n      'Consider attending DevOps/Cloud computing events where they might be present'\n    ],\n    top_recommendations: enhancedConnections.slice(0, 3).map(conn => ({\n      name: conn.name,\n      why_connect: conn.connectionReason,\n      action_item: `Connect with ${safeGetFirst(conn.name, ' ')} focusing on ${conn.tags.slice(0, 2).join(' and ')} expertise`\n    }))\n  }\n};"
      },
      "typeVersion": 2
    },
    {
      "id": "e1b30786-455f-414f-9577-36634a0c1cd9",
      "name": "Get User Data From Email ",
      "type": "n8n-nodes-base.emailReadImap",
      "position": [
        -1040,
        4.76293103448279
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "imap": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 2
    },
    {
      "id": "02259afc-6178-49f4-b08c-82dc7667bd06",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -940,
        -420
      ],
      "parameters": {
        "width": 680,
        "height": 340,
        "content": "## System Architecture\n- **Profile Analysis Pipeline**:\n  - **Get User Data from Email**: Initiates with manual user input.\n  - **Your Profile Information**: Provides initial data.\n  - **Search LinkedIn Profiles**: Fetches profile data via API.\n  - **Process LinkedIn Search Results**: Extracts relevant information.\n- **AI Recommendation Flow**:\n  - **AI Profile Analysis**: Analyzes data with AI.\n  - **Create Recommendations**: Generates initial connection list.\n  - **Create Final Recommendations**: Refines the list.\n- **Delivery Flow**:\n  - **Create Email**: Prepares the email content.\n  - **Send Email**: Sends the curated list to the user."
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "9073190a-946e-4f57-998d-365de4ec3ae8",
  "connections": {
    "Create Email": {
      "main": [
        [
          {
            "node": "Send email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Ollama Model1": {
      "ai_languageModel": [
        [
          {
            "node": "AI Profile Analysis",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Profile Analysis": {
      "main": [
        [
          {
            "node": "Create Final Recommendations",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Search LinkedIn Profiles": {
      "main": [
        [
          {
            "node": "Process LinkedIn Search Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Your Profile Information": {
      "main": [
        [
          {
            "node": "Search LinkedIn Profiles",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get User Data From Email ": {
      "main": [
        [
          {
            "node": "Your Profile Information",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create Final Recommendations": {
      "main": [
        [
          {
            "node": "Create Email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Process LinkedIn Search Results": {
      "main": [
        [
          {
            "node": "AI Profile Analysis",
            "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.

• httpBasicAuth
• httpQueryAuth
• imap
• ollamaApi
• smtp

About this workflow

The workflow is triggered manually with user input, searches LinkedIn profiles, processes the results using AI, generates connection recommendations, and delivers them via email. It leverages AI to enhance networking opportunities based on insights from profiles. Each email is…

Source: https://n8n.io/workflows/7174/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.