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
Built an AI-powered WhatsApp front desk in Respond.io to handle incoming customer conversations automatically. The AI agent can respond to customer questions, manage conversations, and hand the conversation over to a human team member when needed. This workflow demonstrates AI customer support, WhatsApp automation, human-agent handoff, and centralized conversation management.
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
Related posts
Dial: the AI front desk for one-person trades
The problem: one-person trades can't answer the phone from a roof or a crawlspace. Missed calls become lost jobs, and evenings go to quotes and follow-ups.
I built Dial and set it up for a demo HVAC shop, Dry Heat Air Co. in Mesa, AZ.
For customers
• An AI voice front desk that answers every call, asks the right questions and flags emergencies
• Online booking in plain words. Dial suggests the likely fault and offers real arrival windows from the owner's schedule. Booked in about a minute.
• A live job page, plus a My Visits account with every visit, quote and receipt
• One tap to confirm "I'll be home" or accept a quote
For the owner
• The whole day on one screen: what needs you, what the front desk handled, the route and time saved
• Hold to talk after a job. The voice note becomes the receipt, the quote and follow-ups on day 2, 7 and 14.
• Both sides update live, so there's no phone tag
Built with Lovable and Lovable Cloud, ElevenLabs for the voice agent and transcription, and Gemini to write up each job.
Try it: dial-frontdesk.lovable.app
The customer side has a shared demo account, so you can tap around and watch the owner's side update live.
Nino Nails is a booking app built in Lovable for a solo home nail studio in Old Batumi.
The problem: Nino can't answer calls while her hands are busy, and many clients don't like calling anyway.
Client side: an AI assistant that answers questions, suggests free times from the real calendar and books the client with a confirm button, plus classic step-by-step booking with add-ons, in English and Ukrainian.
Owner side: a dashboard with weekly stats, a time-grid calendar, appointment statuses, questions the assistant passed on, and working hours.
Live app: https://nino-nails.lovable.app
Owner dashboard demo, one click, no password: https://nino-nails.lovable.app/nino
Demo walkthrough: https://youtu.be/ep7BVX3J-tg
Process video: https://youtu.be/-6Vp8XADDU4
The result: clients go from "can I book?" to "you're booked" without a call, and Nino just checks her calendar between appointments.:
AI-Powered Email Classification Workflow | n8n Automation
Built an intelligent email automation system using n8n that automatically reads incoming emails, classifies them by department using AI, and forwards them to the right team without any human input.
The workflow connects directly to Gmail and triggers the moment a new email arrives. A JavaScript node extracts the key email details, including sender, subject, body, and date, before passing them to an AI Agent powered by GPT-4o-mini. The AI reads the email content and classifies it into one of six departments: Sales, Customer Service, HR, Finance, Operations, or Other.
A Switch node then routes the email down the correct branch, and a Gmail node automatically forwards it to the right department inbox with a clear label in the subject line.
What it does:
Monitors a Gmail inbox in real time
Extracts and cleans email data automatically
Uses AI to classify emails by department
Routes and forwards emails to the correct team
Fully automated with zero manual sorting required
Result:
Emails that would normally sit unread or require manual sorting now reach the right department within seconds of arriving.
Nice implementation. The production question is what happens to ambiguous emails. I usually add a confidence threshold, an “unclassified” review queue, and retention of the original message so a routing mistake can be corrected without losing context.