The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I built a WhatsApp and Telegram automation system using n8n and AI to handle customer conversations, FAQs, and appointment bookings.
The workflow:
→ Receives WhatsApp messages
→ Understands customer intent with AI
→ Handles FAQs and customer inquiries
→ Collects service, preferred date, and time for bookings
→ Saves appointments to Google Sheets
→ Sends booking confirmations automatically
→ Routes customers who need a human to Telegram
→ Keeps the conversation flowing between WhatsApp and Telegram
The goal was simple: automate repetitive customer communication while keeping a human team involved when needed.
#n8n #WhatsAppAutomation #TelegramAutomation #AIAutomation #WorkflowAutomation #CustomerSupport #AIChatbot
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Saved 30 mins per chat with AI Store Manager
I was tired of juggling Telegram messages, product photos, and a sprawling Google Sheet for every lead. Using n8n I wired a Telegram Trigger to Groq Vision for image recognition, then an IF/Switch combo decides whether the user is a customer or the shop owner. All the data lands in Google Sheets, and the bot can pull promotions or order status from CJ Dropshipping on the fly. The result? About half an hour saved per conversation and a much cleaner workflow.
#n8n #automation #TelegramTrigger #HTTPRequest
Follow for more: https://go.phonezait.de/
A workflow can finish successfully and still be wrong.
That is the reliability problem with production AI agents. A green execution only tells you the workflow ran; it does not tell you whether the model had the right context, chose the right tool, or returned a useful answer.
A practical n8n reliability loop:
• constrain inputs, tools, schemas and routing
• tag executions and inspect full agent logs
• run evals whenever prompts, tools or models change
• add real production failures to the test set
• monitor execution, quality, efficiency and safety separately
The best metric is not the one you can collect. It is the one that changes a decision.
Which failure would your current monitoring miss?
Building an Autonomous WhatsApp AI Sales Agent for E-Commerce — My Descript Workflow.
In this demo, I share my engineering workflow using Next.js & Supabase to build an AI that understands local Arabic dialects and automates customer orders in real-time.
I used Descript to edit this video quickly, leveraging 'Studio Sound' to isolate background noise and adding dynamic automated captions in seconds.
Nice blend of product engineering and clear demo storytelling here. The local-dialect handling plus real-time order flow is a compelling use case, and the clean dashboard framing makes the workflow easy to follow.