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
Designed and built a WhatsApp AI agent system in n8n that acts as a 24/7 AI receptionist for businesses, replying to customers instantly through conversational AI, understanding text and images, and managing real operations behind the scenes.
The system routes incoming WhatsApp messages through a core ai_automation agent powered by GPT models with persistent memory, then uses multi agent orchestration to delegate tasks: email management through Gmail, live research through web search tools, appointment_booking_automation through Google Calendar, and task tracking through Google Tasks. Customer memory and chat history are stored in a MongoDB vector database with RAG, so the AI maintains context across sessions instead of starting fresh each time.
Built for businesses that want to stop losing leads to slow response times, this workflow handles customer_support_automation, appointment booking, and routine questions automatically, even outside business hours, functioning as a true ai_agent_developer level solution.
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
RouteMind is a multi-tenant fleet management SaaS with live GPS tracking and an AI voice agent for operators. I built the full stack and the AI layer end to end.
The hardest part was the data architecture. Structured records like fleet profiles, driver data, and route history sit in MySQL. The high-frequency GPS event stream, which would choke a relational setup, runs through MongoDB instead. Vehicle positions render on a live map with latency low enough that movement feels real-time. That split is what kept the dashboard fast while thousands of GPS events landed every minute.
The AI layer is a voice agent built on a RAG pipeline and the OpenAI API. Operators call in, and the agent retrieves from a vector database of indexed fleet policies and route procedures before answering, never generic output. Questions outside its scope trigger a clean handoff to a human.
The platform is fully multi-tenant with strict data isolation between businesses. Roles and permissions are set from the dashboard, so onboarding a new operator needs no code change.
What the client gets: live fleet visibility, an AI agent that answers policy questions without tying up staff, and an architecture that holds up as the fleet grows.
Great work! my fyp was about Driver's behaviour analysis (dowsiness, distraction detection ) for fleet transportation system and generating alerts while danger is detected.
We built an AI agent that shipped 68 medical articles in 15 days. 1,998 runs, zero failures. And we still won't let it publish on its own. 🩺
It's for Sabai Health, a Thai health platform. The whole system runs from a single Telegram command. Claude handles the keyword clustering, the briefs, and the bilingual writing. Nine n8n workflows move everything from idea to a live page.
But the part we're actually proud of: it never publishes without a human. Medical content is one place you don't hand the last call to a machine, so we didn't. The agent does everything except the medical review on purpose.
That's the whole philosophy. Good automation isn't about removing people. It's knowing the one spot a human has to stay, and building everything else around it.
The full breakdown, stack, and numbers are all on our profile. Do take a look. 🙌
Where would you keep a human in the loop?
Nice 👏
Create Facebook posts, images, and captions on autopilot using an automa automation workflow. Stop doing manual social media tasks.
This tutorial shows how to build a no-code workflow directly in your browser using the free Automa extension. You will learn to connect tools so that a single form submission triggers an entire sequence of content creation. This process is perfect for anyone looking to save time on daily content tasks without needing complex design or copywriting skills.
By following this method, you can send prompts to Nanobrander for flash previews and generate images while simultaneously pushing that same context to GPT-4 for caption and hashtag creation. The system handles the heavy lifting so you can focus on strategy rather than repetitive manual entry. Using a browser extension automation setup ensures your tools work together seamlessly.
Subscribe for weekly automation breakdowns, and comment which platform you want to automate next.
I'd love to try this soon.
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
fifaworldcup2026
The World Cup is here and the whole world's watching. How are you designing for the world stage?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?