Avkash Kakdiya This workflow corresponds to n8n.io template #12674 — we link there as the canonical source.
This workflow follows the Agent → Gmail 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": "8ac7bc5d-c409-44b2-8176-24ecbd2ae969",
"name": "Groq Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGroq",
"position": [
18496,
6112
],
"parameters": {
"model": "llama-3.3-70b-versatile",
"options": {}
},
"typeVersion": 1
},
{
"id": "f6b4adc7-0709-4058-8ff6-9107ccfbef6b",
"name": "Send a message2",
"type": "n8n-nodes-base.gmail",
"position": [
19088,
5856
],
"parameters": {
"sendTo": "your-email",
"message": "={{ $json.email_data.full_report }}",
"options": {},
"subject": "Revenue Forecast Summary Data"
},
"typeVersion": 2.2
},
{
"id": "911581aa-7453-44ca-b5c6-db1a6ce8efd7",
"name": "Send a message3",
"type": "n8n-nodes-base.slack",
"position": [
19088,
6064
],
"parameters": {
"text": "={{ $json.email_data.full_report }}",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "gmail-id",
"cachedResultName": "all-n8ntest"
},
"otherOptions": {},
"authentication": "oAuth2"
},
"typeVersion": 2.4
},
{
"id": "5bcf9c46-80b9-4c46-999e-ab02c2743f9b",
"name": "Loop Over Items1",
"type": "n8n-nodes-base.splitInBatches",
"position": [
18352,
5936
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "08c06ca5-dfaf-4b10-ae33-df0fb3e2cc6d",
"name": "Wait1",
"type": "n8n-nodes-base.wait",
"position": [
19472,
6048
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "ed54b5d9-678f-4a17-8b56-d96cc7dda6f8",
"name": "Format AI response1",
"type": "n8n-nodes-base.code",
"position": [
18864,
5952
],
"parameters": {
"jsCode": "// Extract AI response text\nconst aiOutput = $input.first().json.output;\n\n// Helper function to extract section content\nfunction extractSection(text, sectionTitle) {\n const regex = new RegExp(`## ${sectionTitle}([\\\\s\\\\S]*?)(?=##|$)`, 'i');\n const match = text.match(regex);\n return match ? match[1].trim() : 'Not available';\n}\n\n// Helper function to extract bullet points\nfunction extractBullets(text) {\n const bullets = text.match(/[\\*\\+\\-]\\s+\\*\\*(.+?)\\*\\*/g) || [];\n return bullets.map(b => b.replace(/[\\*\\+\\-]\\s+\\*\\*(.+?)\\*\\*/, '$1')).join(', ');\n}\n\n// Helper function to clean markdown formatting\nfunction cleanText(text) {\n return text\n .replace(/\\*\\*/g, '') // Remove bold markers\n .replace(/\\*/g, '') // Remove italic markers\n .replace(/\\t/g, '') // Remove tabs\n .replace(/\\n\\n+/g, '\\n') // Remove multiple newlines\n .trim();\n}\n\n// Extract revenue figures\nfunction extractRevenue(text) {\n const bestCase = text.match(/Best Case:\\s*\u20b9?([\\d,]+)/i);\n const likelyCase = text.match(/Likely Case:\\s*\u20b9?([\\d,]+)/i);\n const worstCase = text.match(/Worst Case:\\s*\u20b9?([\\d,]+)/i);\n const weighted = text.match(/Weighted Pipeline Value:\\s*\u20b9?([\\d,]+)/i);\n \n return {\n best_case: bestCase ? `\u20b9${bestCase[1]}` : '\u20b90',\n likely_case: likelyCase ? `\u20b9${likelyCase[1]}` : '\u20b90',\n worst_case: worstCase ? `\u20b9${worstCase[1]}` : '\u20b90',\n weighted_value: weighted ? `\u20b9${weighted[1]}` : '\u20b90'\n };\n}\n\n// Extract high-risk deals\nfunction extractHighRiskDeals(text) {\n const dealName = text.match(/\\*\\*Deal Name:\\*\\*\\s*(.+)/);\n const dealAmount = text.match(/\\*\\*Deal Amount:\\*\\*\\s*\u20b9?([\\d,]+)/);\n const riskFactors = text.match(/\\*\\*Risk Factors:\\*\\*([\\s\\S]*?)(?=\\*\\*Recommended|$)/);\n \n let riskText = '';\n if (dealName && dealAmount) {\n riskText = `${dealName[1]} (\u20b9${dealAmount[1]})`;\n if (riskFactors) {\n const factors = riskFactors[1].match(/\\+\\s+(.+)/g);\n if (factors) {\n riskText += ' - ' + factors.map(f => f.replace(/\\+\\s+/, '')).join('; ');\n }\n }\n }\n return riskText || 'No high-risk deals identified';\n}\n\n// Extract top recommendations\nfunction extractRecommendations(text) {\n const recommendations = text.match(/\\*\\*Top 3 Actions.*?:\\*\\*([\\s\\S]*?)(?=\\*\\*Deals Requiring|$)/);\n if (recommendations) {\n const actions = recommendations[1].match(/\\d+\\.\\s+\\*\\*(.+?)\\*\\*/g);\n if (actions) {\n return actions.map((a, i) => {\n const title = a.match(/\\*\\*(.+?)\\*\\*/)[1];\n const desc = recommendations[1].match(new RegExp(`${i + 1}\\\\.\\\\s+\\\\*\\\\*${title}\\\\*\\\\*:?\\\\s*(.+?)(?=\\\\n\\\\s*\\\\d+\\\\.|$)`, 's'));\n return `${i + 1}. ${title}${desc ? ': ' + cleanText(desc[1]) : ''}`;\n }).join('\\n');\n }\n }\n return 'No specific recommendations';\n}\n\n// Extract revenue drivers\nfunction extractRevenueDrivers(text) {\n const section = extractSection(aiOutput, 'Revenue Drivers Analysis');\n const keyDeals = section.match(/\\*\\*Key Deals:\\*\\*\\s*(.+)/);\n const trends = section.match(/\\*\\*Revenue Trends:\\*\\*\\s*(.+)/);\n \n let drivers = '';\n if (trends) drivers += cleanText(trends[1]) + '. ';\n if (keyDeals) drivers += 'Key deals: ' + cleanText(keyDeals[1]);\n \n return drivers || 'Insufficient data for analysis';\n}\n\n// Parse all sections\nconst revenue = extractRevenue(aiOutput);\nconst highRiskDeals = extractHighRiskDeals(extractSection(aiOutput, 'High-Risk Deals'));\nconst revenueDrivers = extractRevenueDrivers(aiOutput);\nconst recommendations = extractRecommendations(aiOutput);\n\n// Format for Google Sheets\nconst formattedData = {\n timestamp: new Date().toLocaleString('en-IN', { timeZone: 'Asia/Kolkata' }),\n forecast_period: new Date().toLocaleString('en-IN', { month: 'long', year: 'numeric' }),\n expected_revenue: revenue.likely_case,\n best_case: revenue.best_case,\n worst_case: revenue.worst_case,\n weighted_pipeline: revenue.weighted_value,\n high_risk_deals: highRiskDeals,\n revenue_drivers: revenueDrivers,\n recommendations: recommendations,\n full_ai_response: cleanText(aiOutput),\n report_sent_to: 'user@example.com, user@example.com'\n};\n\n// Format for Email HTML (clean sections)\nconst emailData = {\n timestamp: formattedData.timestamp,\n forecast_summary: `\n <p><strong>Expected Revenue:</strong> ${revenue.likely_case}</p>\n <p><strong>Best Case:</strong> ${revenue.best_case}</p>\n <p><strong>Worst Case:</strong> ${revenue.worst_case}</p>\n <p><strong>Weighted Pipeline:</strong> ${revenue.weighted_value}</p>\n `,\n high_risk_section: `\n <p>${highRiskDeals}</p>\n `,\n revenue_drivers_section: `\n <p>${revenueDrivers}</p>\n `,\n recommendations_section: `\n <pre style=\"background-color: #f4f4f4; padding: 15px; border-radius: 5px; white-space: pre-wrap;\">${recommendations}</pre>\n `,\n full_report: aiOutput.replace(/\\n/g, '<br>').replace(/\\*\\*(.+?)\\*\\*/g, '<strong>$1</strong>')\n};\n\n// Return both formats\nreturn [\n {\n json: {\n // For Google Sheets\n sheets_data: formattedData,\n \n // For Email\n email_data: emailData,\n \n // Raw data for debugging\n raw_output: aiOutput\n }\n }\n];"
},
"typeVersion": 2
},
{
"id": "75c2b1e5-d2c2-4867-93e7-41d81f3db16a",
"name": "Append row in sheet",
"type": "n8n-nodes-base.googleSheets",
"position": [
19248,
5952
],
"parameters": {
"columns": {
"value": {
"Status": "Email Sent",
"Best_Case": "={{ $json.sheets_data.best_case }}",
"Time Stamp": "={{ $json.sheets_data.timestamp }}",
"Worst_Case": "={{ $json.sheets_data.worst_case }}",
"Report_Sent_To": "={{ $json.sheets_data.report_sent_to }}",
"Forecast_Period": "={{ $json.sheets_data.forecast_period }}",
"High_Risk_Deals": "={{ $json.sheets_data.high_risk_deals }}",
"Recommendations": "={{ $json.sheets_data.recommendations }}",
"Revenue_Drivers": "={{ $json.sheets_data.revenue_drivers }}",
"Expected_Revenue": "={{ $json.sheets_data.expected_revenue }}",
"Full_AI_Response": "={{ $json.sheets_data.full_ai_response }}",
"Weighted_Pipeline": "={{ $json.sheets_data.weighted_pipeline }}"
},
"schema": [
{
"id": "Time Stamp",
"type": "string",
"display": true,
"required": false,
"displayName": "Time Stamp",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Forecast_Period",
"type": "string",
"display": true,
"required": false,
"displayName": "Forecast_Period",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Expected_Revenue",
"type": "string",
"display": true,
"required": false,
"displayName": "Expected_Revenue",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Best_Case",
"type": "string",
"display": true,
"required": false,
"displayName": "Best_Case",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Worst_Case",
"type": "string",
"display": true,
"required": false,
"displayName": "Worst_Case",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Weighted_Pipeline",
"type": "string",
"display": true,
"required": false,
"displayName": "Weighted_Pipeline",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "High_Risk_Deals",
"type": "string",
"display": true,
"required": false,
"displayName": "High_Risk_Deals",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Revenue_Drivers",
"type": "string",
"display": true,
"required": false,
"displayName": "Revenue_Drivers",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Recommendations",
"type": "string",
"display": true,
"required": false,
"displayName": "Recommendations",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Full_AI_Response",
"type": "string",
"display": true,
"required": false,
"displayName": "Full_AI_Response",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Report_Sent_To",
"type": "string",
"display": true,
"required": false,
"displayName": "Report_Sent_To",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "string",
"display": true,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1485545756,
"cachedResultUrl": "sheet-url",
"cachedResultName": "sheet-name"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "sheet-value",
"cachedResultUrl": "sheet-url",
"cachedResultName": "sheet-name"
}
},
"typeVersion": 4.7
},
{
"id": "ad3b35be-95a2-4fa5-813a-62910b68b002",
"name": "HubSpot Trigger1",
"type": "n8n-nodes-base.hubspotTrigger",
"position": [
17808,
5936
],
"parameters": {
"eventsUi": {
"eventValues": [
{
"name": "deal.creation"
}
]
},
"additionalFields": {}
},
"typeVersion": 1
},
{
"id": "9686ae09-74f9-4f99-b92a-457b83f1cfaa",
"name": "Get many deals1",
"type": "n8n-nodes-base.hubspot",
"position": [
17984,
5936
],
"parameters": {
"filters": {},
"resource": "deal",
"operation": "getAll"
},
"typeVersion": 2.2
},
{
"id": "fe6d16bc-d256-4c3f-9945-7be037564dda",
"name": "Format Hubspot Data1",
"type": "n8n-nodes-base.code",
"position": [
18160,
5936
],
"parameters": {
"jsCode": "// Helper: map region to currency\nfunction getCurrency(region) {\n const map = {\n \"India\": \"INR\",\n \"USA\": \"USD\",\n \"United States\": \"USD\",\n \"UK\": \"GBP\",\n \"United Kingdom\": \"GBP\",\n \"UAE\": \"AED\"\n };\n return map[region] || \"USD\"; // default\n}\n\nreturn items.map(item => {\n const deal = item.json.properties || {};\n\n // Extract values safely\n const dealName = deal.dealname || \"Unknown Deal\";\n const dealAmount = Number(deal.amount || 0);\n\n const stage = deal.dealstage || \"Unknown\";\n const closeDate = deal.closedate\n ? new Date(Number(deal.closedate)).toISOString().split(\"T\")[0]\n : null;\n\n const probability = deal.hs_probability\n ? Math.round(Number(deal.hs_probability) * 100)\n : 0;\n\n const owner = deal.hubspot_owner_id || \"Unassigned\";\n\n const region =\n deal.country ||\n deal.region ||\n deal.hs_country_region ||\n \"Unknown\";\n\n const currency = getCurrency(region);\n\n return {\n json: {\n \"Deal Name\": dealName,\n \"Customer Name\": deal.associatedcompanyname || \"N/A\",\n \"Deal Amount\": dealAmount,\n \"Currency\": currency,\n \"Stage\": stage,\n \"Close Date\": closeDate,\n \"Probability (%)\": probability,\n \"Sales Owner\": owner,\n \"Region\": region\n }\n };\n});\n"
},
"typeVersion": 2
},
{
"id": "4da571ca-aae7-4c74-b2a4-b19bf50da20a",
"name": "AI Revenue Forecast & Risk Analysis1",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
18560,
5952
],
"parameters": {
"text": "=Analyze the following sales pipeline data and generate a revenue forecast report:\n\n**Current Date:** {{$now.format('YYYY-MM-DD')}}\n**Forecast Period:** Next 30 days\n\n**Sales Pipeline Data:**\n{{JSON.stringify($json)}}\n\nPlease provide:\n\n1. **Revenue Forecast Summary**\n - Expected revenue (best case, likely case, worst case)\n - Weighted pipeline value\n - Conversion rate trends\n\n2. **High-Risk Deals** (identify deals that may slip or not close)\n - Deal name, amount, and risk factors\n - Recommended actions to mitigate risks\n\n3. **Revenue Drivers Analysis**\n - Why is revenue increasing or decreasing compared to last period?\n - Which deals are moving the needle?\n - Pipeline health assessment\n\n4. **Key Recommendations**\n - Top 3 actions for sales leadership\n - Deals requiring immediate attention\n\nFormat your response in clear sections with bullet points for easy reading.",
"options": {
"systemMessage": "=You are an expert Revenue Forecasting AI specialized in sales pipeline analysis. Your role is to:\n\n1. Analyze sales deal data (amount, stage, close date, probability)\n2. Generate accurate revenue forecasts for the next month/quarter\n3. Identify high-risk deals that may not close\n4. Explain key revenue drivers (why revenue is increasing or decreasing)\n5. Provide actionable insights for sales leadership\n\n**Output Requirements:**\n- Be concise and executive-ready\n- Use clear, business-friendly language\n- Highlight critical risks and opportunities\n- Provide specific deal-level recommendations\n- Format responses in structured sections\n\n**Tone:** Professional, data-driven, and action-oriented"
},
"promptType": "define"
},
"typeVersion": 3
},
{
"id": "cdf2afe5-3f49-4c3f-a508-ee0570f81a18",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
17136,
5648
],
"parameters": {
"width": 640,
"height": 688,
"content": "## AI Revenue Forecast Generator\n\nThis workflow automatically generates an AI-powered revenue forecast whenever a new deal is created in HubSpot. It analyzes the entire sales pipeline to estimate expected revenue, identify high-risk deals, and highlight key revenue drivers. The goal is to give sales leaders a clear, executive-ready view of pipeline health and upcoming revenue.\n\n### How it works\n- Triggers when a deal is created in HubSpot \n- Fetches all active deals from the pipeline \n- Cleans and standardizes deal data (amount, stage, probability, region) \n- Sends structured data to an AI model for forecasting and risk analysis \n- Generates best, likely, and worst-case revenue scenarios \n- Shares the report via Slack and Email \n- Logs all insights in Google Sheets for tracking and audits \n\n### Setup steps\n1. Connect your HubSpot account and enable the Deal Created trigger \n2. Ensure required deal properties are available \n3. Connect your AI provider (Groq / LLM) \n4. Connect Slack and choose a channel \n5. Connect Gmail for email delivery \n6. Connect Google Sheets for data logging \n7. Turn the workflow ON and test by creating a deal "
},
"typeVersion": 1
},
{
"id": "d1c68d2b-7f47-4d6c-a8ce-81381ecd368b",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
17792,
5648
],
"parameters": {
"color": 7,
"width": 688,
"height": 688,
"content": "## Step 1 \u2013 Collect & prepare HubSpot deals \nTriggers on deal creation, fetches all active deals, and formats key fields for AI analysis.\n"
},
"typeVersion": 1
},
{
"id": "73e70ef7-057a-45dc-9ce1-27986c76a405",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
18496,
5648
],
"parameters": {
"color": 7,
"width": 1136,
"height": 688,
"content": "## Step 2 \u2013 Generate & distribute AI forecast \nAI generates revenue forecasts and risk insights, sends them to Slack and Email, and logs them in Google Sheets."
},
"typeVersion": 1
}
],
"connections": {
"Wait1": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"Get many deals1": {
"main": [
[
{
"node": "Format Hubspot Data1",
"type": "main",
"index": 0
}
]
]
},
"Groq Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Revenue Forecast & Risk Analysis1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"HubSpot Trigger1": {
"main": [
[
{
"node": "Get many deals1",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items1": {
"main": [
[],
[
{
"node": "AI Revenue Forecast & Risk Analysis1",
"type": "main",
"index": 0
}
]
]
},
"Append row in sheet": {
"main": [
[
{
"node": "Wait1",
"type": "main",
"index": 0
}
]
]
},
"Format AI response1": {
"main": [
[
{
"node": "Send a message2",
"type": "main",
"index": 0
},
{
"node": "Append row in sheet",
"type": "main",
"index": 0
},
{
"node": "Send a message3",
"type": "main",
"index": 0
}
]
]
},
"Format Hubspot Data1": {
"main": [
[
{
"node": "Loop Over Items1",
"type": "main",
"index": 0
}
]
]
},
"AI Revenue Forecast & Risk Analysis1": {
"main": [
[
{
"node": "Format AI response1",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow automatically generates an AI-powered revenue forecast whenever a new deal is created in HubSpot. It collects all active deals, standardizes key sales data, and sends it to an AI model for forecasting and risk analysis. The AI produces best, likely, and worst-case…
Source: https://n8n.io/workflows/12674/ — 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.
Streamline client onboarding and project setup from hours to minutes with AI-driven automation. This intelligent workflow eliminates manual coordination, builds proposals, creates projects in Asana, w
Agent, Asana, Slack +5
Automate Ai-powered Employee Onboarding Emails and Slack Updates with Groq, Gmail, and Google Sheets
Triggered every 4 hours (or manually) to check all active products in Google Sheets Each product is evaluated for stock level and urgency against its reorder threshold Products with sufficient stock a
Form Trigger, Groq Chat, Gmail +5
New hire submits an onboarding form with their details Groq AI generates personalised welcome content, Slack messages, and IT access request Welcome email sent to the new hire via Gmail Automated emai
Form Trigger, Groq Chat, Gmail +5
🧠 AI-Powered Lead Routing and Sales Team Distribution
HubSpot Trigger, HubSpot, Airtable +8
This template enables natural-language-driven automation using Bright Data's MCP tools, triggered directly by new leads in HubSpot. It dynamically extracts and executes the right tool based on lead co
Google Sheets Trigger, Output Parser Structured, Output Parser Autofixing +7