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
AI Maintenance Dispatch Agent | n8n, AI & Airtable
I built an AI-powered maintenance dispatch workflow designed to help property management teams handle tenant maintenance requests more reliably.
The system handles incoming requests, collects missing information through conversations, stores conversation state, and routes requests through the appropriate workflow.
What it does
Tenant request processing: Validates incoming maintenance requests before processing them.
Conversation memory: Uses Airtable to maintain conversation state across multiple messages.
AI classification: Separates in-scope requests, requests needing human review, and out-of-scope requests.
Duplicate prevention: Helps prevent repeated events from creating duplicate work.
Maintenance tracking: Creates or updates maintenance records in Airtable.
Human-in-the-loop review: Flags uncertain or sensitive requests for human attention.
Vendor coordination: Supports matching maintenance issues with suitable vendors and notifying the team.
Logging and monitoring: Records important workflow events to improve traceability and troubleshooting.
Tech stack
n8n · AI · Airtable · WhatsApp integration
The goal
The goal is to reduce manual coordination, keep maintenance requests organized, and make sure requests requiring human attention are not silently ignored.
I focused on building a workflow that accounts for real-world issues such as incomplete information, repeated events, and requests that should not be handled automatically.
Open to projects involving n8n, AI agents, CRM automation, API integrations, and custom business workflows.
Duplicate prevention and human-in-the-loop are what make this credible — most dispatch demos skip both and then break in the real world. Curious how you set the threshold for flagging a request for human review vs letting the classification run on its own?
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
🚨 A dental clinic was losing patients every single day.
Not because of bad service. Not because of high prices.
Because nobody was replying to messages.
Patients messaged on WhatsApp, Messenger, SMS… And waited. And waited. And left.
The clinic owner contacted me with one simple ask:
“I can’t hire someone to reply 24/7. Can you help?”
So, I built them an AI receptionist that never sleeps. 👇
Here’s exactly what it does:
✅ Omnichannel Support: Instantly replies to patients on WhatsApp, Facebook Messenger & SMS — all from one system.
✅ Human-like AI: Google Gemini AI understands the message, detects intent, and replies naturally.
✅ Smart FAQ Handler: Answers questions about services, pricing & clinic hours by pulling live data from Google Sheets.
✅ Automated Booking: Checks availability, blocks double-bookings, and confirms only after saving to the sheet.
✅ Instant Alerts: Notifies the clinic owner instantly via Gmail + Telegram on every new booking.
✅ Smart Reminders: Sends automated email reminders — 2 hours and 1 hour before the appointment.
✅ No-Show Recovery: Detects missed appointments and automatically sends a polite rescheduling email after 12 hours.
The Tech Stack 🛠️:
⚙️ Make.com — Automation backbone
🧠 Google Gemini 2.0 Flash — AI brain
📊 Google Sheets — Live clinic database
💬 Green API — WhatsApp integration
📱 Facebook Messenger API & Twilio — Chat & SMS
✉️ Brevo — Email reminders
📢 Telegram Bot — Owner notifications
💾 Make.com DataStore — Conversation memory per patient
The Result? 📈
Every patient gets an instant, intelligent reply — 24/7. No missed bookings. No forgotten appointments. No manual follow-ups.
The clinic owner now wakes up to confirmed appointments already in the sheet with zero manual effort.
This is what I build for businesses. If you’re still replying manually and losing leads while you sleep — DM me. Let’s fix that. 👇
#MakeAutomation #AIAutomation #NoCode #Makecom #GeminiAI #WhatsAppAutomation #BusinessAutomation #AIReceptionist #FreelanceAutomation #Upwork #Fiverr
Nice build, and very close to a WhatsApp assistant I just built for a dental-clinic use case on the WhatsApp Cloud API. Two things mattered a lot in testing: when a patient asks for a person, the bot has to go completely quiet for that chat until the owner hands it back, and the...
I’ve built an entire Kajabi business system, website and all, with AI in hours.
Now I’m turning that process into a workflow other people can use.
It brings together the steps, instructions, and checks that guide AI from your initial idea through the build and launch. You use your own AI tools, with a clear process to follow.
This is for anyone starting a business on Kajabi, improving an existing one, or building for clients.
I’ve already done the build. What I’m developing now is the way to put that process in your hands. I’ll be sharing more soon. Who wants first dibs on access?
Turning your own AI build process into a reusable workflow is the natural next step, Kraig. Steps, instructions and checks from idea through launch is exactly the structure people need to trust AI with a real business. Count me curious for first dibs.
MASTER START — Lead Automation System
Independent product demo of a lead-processing workflow that connects website forms with Kommo, sends manager alerts in Telegram, and handles automated email follow-up with CRM status-based stop logic.
Built and tested with synthetic data.
The CRM status based stop logic is crucial because it prevents sending duplicate emails to leads who already converted. Without that guard, your automation risks annoying customers and cluttering the inbox with unnecessary follow ups.