Order & returns AI agent on WhatsApp (Arabic)
Answers "where's my order?", gives delivery updates and logs returns and exchanges — in the customer's dialect.
How it works
Trigger: WhatsApp — a customer sends a message
- A customer asks about their order on WhatsApp.
- The agent finds the order by number or by their phone number.
- It shares the status and tracking, or logs a return or exchange after confirming the details.
- It alerts your team on Telegram for returns and anything it can't solve.
What it can do
Unlike a fixed flow, an agent decides which of its tools to use, in what order — and remembers the conversation.
- Finds orders by order number — or automatically by the customer's phone
- Shares status, courier and tracking number
- Logs return and exchange requests with item, reason and refund/exchange choice
- Explains your return policy
- Alerts your team for returns, damaged items and hand-overs
System prompt
The instructions that shape the agent. It's already inside the n8n template — copy it into Make or Zapier, and adjust the YOUR_… parts.
You are the after-sales assistant for YOUR_STORE on WhatsApp. Reply in the customer's language and dialect (Egyptian Arabic, Gulf Arabic, Modern Standard Arabic or English). Be warm and brief.
You handle: "where is my order?", delivery updates, returns and exchanges.
Tools:
- "Look up order": finds orders by order number or by the customer's phone. Returns status, items, total, courier and tracking number.
- "Create return request": logs a return or exchange request. Use only after the customer confirms which item, the reason, and whether they want a refund or an exchange.
- "Notify team": alerts our team for every return request, damaged item, or anything you can't solve.
Our policy: YOUR_RETURN_POLICY (e.g. returns within 14 days, unused, with tags).
Rules:
- The customer's phone is {{ $('Get question').item.json.from }} — try it first if they don't give an order number.
- Never promise refunds, dates or compensation. Say the team will confirm.
- Never invent order details; if you can't find the order, ask for the order number.Safety rules
Built into the prompt and the tools:
- Never promises refunds, dates or compensation — the team confirms
- Never invents order details
- Confirms return details before logging them
Uses your own AI key (Claude, OpenAI or another model). Cost depends on the model and conversation length — a small, fast model keeps most conversations to a fraction of a cent.
Diagram
Trigger App Code AI Agent tool
Code
JavaScript used in the Code step — already included in the template below.
// Keeps only text messages and pulls out who sent it and what they asked.
const msg = $input.first().json.messages?.[0];
if (!msg || msg.type !== "text") return [];
return [{ json: { from: msg.from, question: msg.text.body } }];Build it
Pick your tool — same automation, step by step.
Copy and paste straight into an n8n canvas (Ctrl+V), or download and use Import from File. Then connect your own credentials and replace every YOUR_… placeholder. AI steps use a Claude model node — swap it for OpenAI, Gemini or Ollama if you prefer.
Show code (304 lines)
{
"name": "Order & returns AI agent on WhatsApp (Arabic) (Flowngn)",
"nodes": [
{
"parameters": {
"content": "## Order & returns AI agent on WhatsApp (Arabic)\nAnswers \"where's my order?\", gives delivery updates and logs returns and exchanges — in the customer's dialect.\n\n**Setup**\n1. Open each node and connect your own credentials.\n2. Replace every YOUR_… placeholder.\n3. Test once, then activate.\n\nFree template from Flowngn",
"height": 260,
"width": 340
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Setup notes",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-420,
-60
]
},
{
"parameters": {
"updates": [
"messages"
]
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Incoming message",
"type": "n8n-nodes-base.whatsAppTrigger",
"typeVersion": 1,
"position": [
0,
0
],
"webhookId": "329e2b17-62e3-40d1-a6e5-e475fee4c948"
},
{
"parameters": {
"jsCode": "// Keeps only text messages and pulls out who sent it and what they asked.\nconst msg = $input.first().json.messages?.[0];\nif (!msg || msg.type !== \"text\") return [];\n\nreturn [{ json: { from: msg.from, question: msg.text.body } }];"
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Get question",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
300,
0
]
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.question }}",
"options": {
"systemMessage": "=You are the after-sales assistant for YOUR_STORE on WhatsApp. Reply in the customer's language and dialect (Egyptian Arabic, Gulf Arabic, Modern Standard Arabic or English). Be warm and brief.\n\nYou handle: \"where is my order?\", delivery updates, returns and exchanges.\n\nTools:\n- \"Look up order\": finds orders by order number or by the customer's phone. Returns status, items, total, courier and tracking number.\n- \"Create return request\": logs a return or exchange request. Use only after the customer confirms which item, the reason, and whether they want a refund or an exchange.\n- \"Notify team\": alerts our team for every return request, damaged item, or anything you can't solve.\n\nOur policy: YOUR_RETURN_POLICY (e.g. returns within 14 days, unused, with tags).\n\nRules:\n- The customer's phone is {{ $('Get question').item.json.from }} — try it first if they don't give an order number.\n- Never promise refunds, dates or compensation. Say the team will confirm.\n- Never invent order details; if you can't find the order, ask for the order number."
}
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "After-sales agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
600,
0
]
},
{
"parameters": {
"model": {
"__rl": true,
"value": "claude-sonnet-5",
"mode": "list"
},
"options": {}
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Claude model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.3,
"position": [
260,
220
]
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Get question').item.json.from }}",
"contextWindowLength": 10
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
430,
220
]
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "Finds orders by order number or phone. Returns status, items, total, courier and tracking number.",
"operation": "read",
"documentId": {
"__rl": true,
"value": "YOUR_SPREADSHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Orders",
"mode": "name"
},
"filtersUI": {
"values": [
{
"lookupColumn": "={{ $fromAI('column', \"Which column to search: order_id or phone\", 'string') }}",
"lookupValue": "={{ $fromAI('value', \"The order number or phone number\", 'string') }}"
}
]
},
"options": {}
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Look up order",
"type": "n8n-nodes-base.googleSheetsTool",
"typeVersion": 4.5,
"position": [
600,
220
]
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "Logs a confirmed return or exchange request.",
"operation": "append",
"documentId": {
"__rl": true,
"value": "YOUR_SPREADSHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Returns",
"mode": "name"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"date": "={{ $now.toISO() }}",
"phone": "={{ $('Get question').item.json.from }}",
"order_id": "={{ $fromAI('order_id', \"Order number\", 'string') }}",
"item": "={{ $fromAI('item', \"Which item\", 'string') }}",
"reason": "={{ $fromAI('reason', \"Why they want to return it\", 'string') }}",
"wants": "={{ $fromAI('wants', \"refund or exchange\", 'string') }}",
"status": "new"
}
},
"options": {}
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Create return request",
"type": "n8n-nodes-base.googleSheetsTool",
"typeVersion": 4.5,
"position": [
770,
220
]
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "Alerts our team: every return request, damaged or wrong items, and anything you can't solve.",
"chatId": "YOUR_TEAM_CHAT_ID",
"text": "={{ $fromAI('message', \"What the team needs to know, including the customer's phone\", 'string') }}",
"additionalFields": {
"appendAttribution": false
}
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Notify team",
"type": "n8n-nodes-base.telegramTool",
"typeVersion": 1.2,
"position": [
940,
220
]
},
{
"parameters": {
"operation": "send",
"phoneNumberId": "YOUR_PHONE_NUMBER_ID",
"recipientPhoneNumber": "={{ $('Get question').item.json.from }}",
"textBody": "={{ $json.output }}"
},
"id": "329e2b17-62e3-40d1-a6e5-e475fee4c948",
"name": "Reply on WhatsApp",
"type": "n8n-nodes-base.whatsApp",
"typeVersion": 1,
"position": [
900,
0
]
}
],
"connections": {
"Incoming message": {
"main": [
[
{
"node": "Get question",
"type": "main",
"index": 0
}
]
]
},
"Get question": {
"main": [
[
{
"node": "After-sales agent",
"type": "main",
"index": 0
}
]
]
},
"After-sales agent": {
"main": [
[
{
"node": "Reply on WhatsApp",
"type": "main",
"index": 0
}
]
]
},
"Claude model": {
"ai_languageModel": [
[
{
"node": "After-sales agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Memory": {
"ai_memory": [
[
{
"node": "After-sales agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Look up order": {
"ai_tool": [
[
{
"node": "After-sales agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Create return request": {
"ai_tool": [
[
{
"node": "After-sales agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Notify team": {
"ai_tool": [
[
{
"node": "After-sales agent",
"type": "ai_tool",
"index": 0
}
]
]
}
},
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"meta": {
"templateCredsSetupCompleted": false
},
"tags": []
}In Make, create a new scenario and add these modules in order:
- WhatsApp Business Cloud › Watch Events (messages)
- Tools › Set variable / Iterator + Array aggregator (same logic as the Code step)
- Make AI Agents › Run an agent — give it these tools: “Look up order” (Google Sheets), “Create return request” (Google Sheets), “Notify team” (Telegram Bot); paste the system prompt as the agent's instructions
- WhatsApp Business Cloud › Send a Message
- Every module run uses Make operations — the free plan includes a monthly quota.
- Make's built-in functions (map, sum, formatDate…) can replace most Code steps; for complex logic use a code module.
- Module and step names can differ slightly as Make and Zapier update their apps.
In Zapier, create a new Zap and add these steps in order:
- WhatsApp — New Message
- Code by Zapier — Run JavaScript (paste the code from the Code section)
- Zapier Agents — create an agent (or AI by Zapier for a single step) — give it these tools: “Look up order” (Google Sheets), “Create return request” (Google Sheets), “Notify team” (Telegram); paste the system prompt as the agent's instructions
- WhatsApp — Send Message
- Zaps with more than two steps need a paid Zapier plan.
- Webhooks, Filters/Paths and Code by Zapier are premium features on some Zapier plans.
- Code by Zapier runs JavaScript: reuse the code shown above, reading inputs from inputData instead of $json.
- Module and step names can differ slightly as Make and Zapier update their apps.
Tips
- Keep tracking numbers in the Orders sheet (the Bosta flows can fill them in automatically).
Related flows
AI AgentsAdvanced
WhatsApp sales AI agent (Arabic)
Sells on WhatsApp in the customer's own dialect: checks your catalog, answers questions and takes cash-on-delivery orders.
WhatsApp → AI model → Google Sheets → Telegram30h/mo
AI AgentsAdvanced
Real-estate AI agent on WhatsApp
Understands what clients want, suggests matching listings and books viewings — in Arabic or English.
WhatsApp → AI model → Google Sheets → Google Calendar → Telegram25h/mo
AI AgentsAdvanced
Restaurant ordering AI agent on WhatsApp
Takes delivery orders on WhatsApp from your menu, confirms the total and sends the order to the kitchen.
WhatsApp → AI model → Google Sheets → Telegram30h/mo