This workflow follows the Gmail → Gmail Trigger 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": "Coffee & Peppers - Email AI",
"nodes": [
{
"parameters": {
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"filters": {
"readStatus": "unread",
"sender": ""
},
"options": {
"downloadAttachments": false
}
},
"type": "n8n-nodes-base.gmailTrigger",
"typeVersion": 1,
"position": [
-200,
0
],
"id": "gmail-trigger",
"name": "Gmail - New Email",
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const body = $input.first().json.text || $input.first().json.snippet || '';\nconst subject = $input.first().json.subject || '';\nconst from = $input.first().json.from || '';\nconst threadId = $input.first().json.threadId || '';\nconst messageId = $input.first().json.id || '';\n\n// Extract order number patterns like #12345, order 12345, order #12345\nconst orderMatch = (body + ' ' + subject).match(/#?(\\d{4,6})|order\\s*#?(\\d{4,6})/i);\nconst orderNumber = orderMatch ? orderMatch[1] || orderMatch[2] : null;\n\n// Extract customer email from the From field\nconst emailMatch = from.match(/<(.+?)>/) || [null, from];\nconst customerEmail = emailMatch[1];\n\nreturn [{\n json: {\n body,\n subject,\n from,\n threadId,\n messageId,\n orderNumber,\n customerEmail\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
20,
0
],
"id": "parse-email",
"name": "Parse Email & Extract Order #"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": false
},
"conditions": [
{
"leftValue": "={{ $json.orderNumber }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "isNotEmpty"
}
}
]
}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
240,
0
],
"id": "has-order-number",
"name": "Has Order Number?"
},
{
"parameters": {
"method": "GET",
"url": "=https://coffeeandpeppers.com/wp-json/wc/v3/orders/{{ $json.orderNumber }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpBasicAuth",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
460,
-120
],
"id": "get-order",
"name": "Get WooCommerce Order",
"credentials": {
"httpBasicAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Build order summary for AI context\nconst order = $input.first().json;\nconst emailData = $('Parse Email & Extract Order #').first().json;\n\nlet orderSummary = 'No order data available.';\nif (order && order.id) {\n const items = (order.line_items || []).map(i => `${i.quantity}x ${i.name}`).join(', ');\n const shipping = order.shipping_lines?.[0]?.method_title || 'standard';\n const trackingNumber = order.meta_data?.find(m => m.key === '_wc_shipment_tracking_items')?.value?.[0]?.tracking_number || 'not available';\n orderSummary = `Order #${order.id} | Status: ${order.status} | Items: ${items} | Shipping: ${shipping} | Tracking: ${trackingNumber} | Total: $${order.total}`;\n}\n\nreturn [{\n json: {\n ...emailData,\n orderSummary\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
680,
-120
],
"id": "format-order",
"name": "Format Order Data"
},
{
"parameters": {
"jsCode": "const emailData = $input.first().json;\nreturn [{\n json: {\n ...emailData,\n orderSummary: 'No order number found in email.'\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
460,
120
],
"id": "no-order",
"name": "No Order - Pass Through"
},
{
"parameters": {
"mode": "combine",
"combinationMode": "mergeByPosition",
"options": {}
},
"type": "n8n-nodes-base.merge",
"typeVersion": 3,
"position": [
900,
0
],
"id": "merge",
"name": "Merge"
},
{
"parameters": {
"model": "gpt-4o",
"messages": {
"values": [
{
"role": "system",
"content": "You are a friendly, casual customer service AI for Coffee & Peppers (coffeeandpeppers.com), a peptide and supplement company. Your job is to:\n\n1. CLASSIFY the email into one of these categories:\n - order_status (asking where their order is)\n - missing_items (received incomplete kit or wrong items)\n - wrong_address (address error on order)\n - dosing_medical (ANY dosing, medical, or health advice questions)\n - product_question (general product info, availability, batch tests)\n - refund_return (requesting refund or return)\n - other (anything that doesn't fit above)\n\n2. Determine a CONFIDENCE score (0.0 to 1.0) - how confident are you that your response is complete and correct without human review?\n - High confidence (0.8+): Simple factual replies, dosing deflections, order status with full data\n - Low confidence (below 0.8): Missing items, refunds, complaints, anything requiring a business decision\n\n3. Draft a RESPONSE that is casual and friendly in tone. Sign off as 'The C&P Team'.\n\nSpecial rules:\n- For dosing_medical: Always respond with exactly: \"Hey [name]! We totally get the curiosity, but we're not able to give medical or dosing advice - that's something to chat with your healthcare provider about! Is there anything else we can help you with? - The C&P Team\"\n- For missing_items or wrong_address: Draft a response but keep confidence LOW (0.4) since a human needs to verify and decide on reship/refund\n- For refund_return: Draft empathetically, keep confidence LOW (0.3)\n- Never promise specific outcomes (refund, reship) without human approval\n\nReturn ONLY valid JSON with this exact structure:\n{\n \"category\": \"<category>\",\n \"confidence\": <number>,\n \"response\": \"<full email response>\",\n \"summary\": \"<one sentence summary for the team>\"\n}"
},
{
"role": "user",
"content": "=Customer Email:\nFrom: {{ $json.from }}\nSubject: {{ $json.subject }}\nMessage: {{ $json.body }}\n\nOrder Data: {{ $json.orderSummary }}\n\nPlease classify and draft a response."
}
]
},
"options": {
"temperature": 0.3
}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.7,
"position": [
1120,
0
],
"id": "ai-classify",
"name": "AI - Classify & Draft Response",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const raw = $input.first().json.message?.content || $input.first().json.choices?.[0]?.message?.content || '{}';\nlet parsed;\ntry {\n // Strip markdown code fences if present\n const cleaned = raw.replace(/```json\\n?/g, '').replace(/```\\n?/g, '').trim();\n parsed = JSON.parse(cleaned);\n} catch(e) {\n parsed = { category: 'other', confidence: 0.1, response: raw, summary: 'Parse error - review manually' };\n}\n\nconst emailData = $('Merge').first().json;\n\nreturn [{\n json: {\n ...emailData,\n category: parsed.category,\n confidence: parsed.confidence,\n aiResponse: parsed.response,\n summary: parsed.summary,\n needsReview: parsed.confidence < 0.75\n }\n}];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1340,
0
],
"id": "parse-ai",
"name": "Parse AI Response"
},
{
"parameters": {
"sendTo": "={{ $json.customerEmail }}",
"subject": "=Re: {{ $json.subject }}",
"emailType": "text",
"message": "={{ $json.aiResponse }}",
"options": {
"threadId": "={{ $json.threadId }}",
"appendAttribution": false
}
},
"type": "n8n-nodes-base.gmail",
"typeVersion": 2.1,
"position": [
1560,
-160
],
"id": "create-draft",
"name": "Create Gmail Draft",
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"conditions": [
{
"leftValue": "={{ $json.needsReview }}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "equal"
}
}
]
}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1560,
160
],
"id": "needs-review",
"name": "Needs Human Review?"
},
{
"parameters": {
"sendTo": "coffeepepp@gmail.com, coltonteefy@gmail.com",
"subject": "=[REVIEW NEEDED] {{ $json.category }} - {{ $json.subject }}",
"emailType": "text",
"message": "=A customer email needs your review:\n\nFrom: {{ $json.from }}\nSubject: {{ $json.subject }}\nCategory: {{ $json.category }}\nAI Summary: {{ $json.summary }}\n\n---\nDraft reply is ready in Gmail drafts. Review and send when ready.\n\nOriginal message:\n{{ $json.body }}",
"options": {}
},
"type": "n8n-nodes-base.gmail",
"typeVersion": 2.1,
"position": [
1780,
80
],
"id": "notify-team",
"name": "Notify Dan & Colton",
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Gmail - New Email": {
"main": [
[
{
"node": "Parse Email & Extract Order #",
"type": "main",
"index": 0
}
]
]
},
"Parse Email & Extract Order #": {
"main": [
[
{
"node": "Has Order Number?",
"type": "main",
"index": 0
}
]
]
},
"Has Order Number?": {
"main": [
[
{
"node": "Get WooCommerce Order",
"type": "main",
"index": 0
}
],
[
{
"node": "No Order - Pass Through",
"type": "main",
"index": 0
}
]
]
},
"Get WooCommerce Order": {
"main": [
[
{
"node": "Format Order Data",
"type": "main",
"index": 0
}
]
]
},
"Format Order Data": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"No Order - Pass Through": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Merge": {
"main": [
[
{
"node": "AI - Classify & Draft Response",
"type": "main",
"index": 0
}
]
]
},
"AI - Classify & Draft Response": {
"main": [
[
{
"node": "Parse AI Response",
"type": "main",
"index": 0
}
]
]
},
"Parse AI Response": {
"main": [
[
{
"node": "Create Gmail Draft",
"type": "main",
"index": 0
},
{
"node": "Needs Human Review?",
"type": "main",
"index": 0
}
]
]
},
"Needs Human Review?": {
"main": [
[
{
"node": "Notify Dan & Colton",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
}
}
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.
gmailOAuth2httpBasicAuthopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Coffee & Peppers - Email AI. Uses gmailTrigger, httpRequest, openAi, gmail. Event-driven trigger; 12 nodes.
Source: https://gist.github.com/aidanvalero/7c8bcf567f8acc47686e26d41f61d3f1 — 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.
This n8n workflow — HRMate — streamlines your entire recruitment process by automatically parsing incoming job applications, evaluating candidate fit using AI, and sending personalized acceptance or r
Overview
Turn email overload into audio insights — automatically.
Automate your entire invoice processing pipeline with AI-powered OCR, validation, and approval workflows 📄🤖. This n8n automation monitors incoming Gmail invoices, extracts structured data using OCR an
Small teams, solo operators, and security-conscious individuals who receive email attachments from external senders. Useful for freelancers, agencies, HR teams, and anyone handling CVs, invoices, or d