Built an AI-powered triage bot (WeSki Bot) for a ski travel company using n8n, Slack, HubSpot, Jira, and GPT-4.
Agents trigger the bot in Slack with a booking ID. It verifies trip details in HubSpot in real-time, then walks through a structured triage flow via threaded replies: collecting issue description, urgency, OPS needs, actions taken, and refund details.
GPT-4 processes inputs and auto-creates a Jira ticket with booking details, triage notes, SLAs, and refund amounts. A Slack notification posts with links to the Jira ticket and HubSpot deal.
Results:
✅ 60% faster response times
✅ Zero manual data entry
✅ 100% lead capture
✅ 24/7 automated triage
Tech: n8n, Slack, HubSpot, Jira, GPT-4, Google Sheets
🚀 Turning Manual E-commerce Order Processing into an Automated Workflow with n8n
Manual order management may seem simple, but copying customer details, checking information, preventing duplicate orders, and sending confirmation emails can quickly become repetitive and error-prone.
I recently built an end-to-end order processing automation using n8n to solve these challenges for a handmade products store.
Here's what I implemented:
🔹 Automated Order Capture: Receive new orders through a webhook.
🔹 Data Validation & Cleaning: Validate required fields, email formats, quantities, and prices before processing.
🔹 Duplicate Prevention: Detect existing Order IDs to prevent duplicate records.
🔹 Google Sheets Integration: Automatically store valid orders and calculate order totals.
🔹 Email Notifications: Send order updates to the store owner and confirmation emails to customers.
🔹 Error Monitoring: Capture failed executions, log error details in a dedicated Google Sheets tab, and send email alerts.
The goal was simple: reduce repetitive administrative work, improve data accuracy, and make order operations more reliable.
This is what I enjoy about building with n8n — turning complex, repetitive business processes into practical automation systems.
Have a repetitive workflow in your business that could be automated? Let's connect!
An AI customer support chatbot for a fictional Nigerian food delivery business, Lagos Fresh Kitchen. It runs on n8n Cloud and uses Claude Haiku 5.5 as the AI model. The workflow is three nodes: a chat trigger receives the customer’s message, an AI Agent processes it, and the Anthropic Chat Model writes the answer.
How it behaves
The AI Agent has a system message that sets the rules. It must answer only from the business information, never invent prices, areas, hours or policies, and use a fixed fallback line when the answer isn’t there: “I don’t have enough information to answer that accurately. Please contact our support team.”
The business information it knows
Open Monday to Saturday, 9 AM to 8 PM, closed Sundays
Delivers to Lagos Mainland (Ikeja, Yaba, Surulere, Maryland, Ojota, Gbagada) and Island areas (Victoria Island, Ikoyi, Lekki), not outside Lagos
Delivery takes 30 to 60 minutes, with fees from ₦1,000
Menu of jollof rice, fried rice, rice and stew, pounded yam with egusi, grilled chicken, suya and soft drinks
Payments by card, transfer and cash on delivery
Cancellation allowed before cooking starts
No Sunday orders or Sunday delivery, and no event catering
Refunds, complaints and order status go to support