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 a Conversational AI Cinema Booking Agent with n8n
I built this as a hands-on project to explore how AI agents, tool calling, and workflow automation can work together in a real-world booking process.
The agent can:
• Browse movies, showtimes, prices, and trailers
• Check seat availability
• Validate customer emails
• Generate unique Booking IDs
• Update movie inventory in Google Sheets
• Store booking records
• Send confirmation emails
• Retrieve bookings using Booking IDs
Tech stack: n8n, Google Gemini, Google Sheets, email automation, and an email verification API.
It’s still a demo with some limitations, but getting the entire process working end-to-end was the biggest takeaway.
Projects like this are helping me move beyond simply learning automation tools and focus on building practical AI-powered workflows that can solve real business problems.
Currently exploring more ways to combine AI agents with automation, APIs, and business workflows.
#n8n #AIAgents #AIAutomation #Automation #GoogleGemini #WorkflowAutomation #Contra #BuildInPublic
@Umaiir Wazir Using Google Sheets for inventory and Booking IDs for retrieval makes the demo feel grounded. How are you handling two customers trying to reserve the same seat at once?
In the current demo, I’m not fully handling concurrent bookings yet, Google Sheets works well for demonstrating the workflow, but it isn’t ideal for true real-time seat locking.
For a production version, I’d introduce a proper transactional database with atomic seat reservations...
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
I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant access to the company’s own knowledge and product information so it can give useful, context-aware responses instead of just generating random answers.
The interesting part isn’t just connecting an LLM.
It’s making sure the AI can:
→ Find the right information
→ Understand the user’s question
→ Retrieve relevant context
→ Give an accurate response
→ Actually be useful in a real business workflow
Still working on it, but I’m excited about where it’s going.
This is the kind of AI automation I enjoy building, systems that solve actual business problems, not just AI demos.
Building something similar? Let’s talk.
I’ve built something similar for Purchaser, an e-commerce marketplace for automotive and industrial products.
I built a RAG-powered AI agent inside Slack that gives the team access to Purchaser’s product and spare-parts database. Instead of opening Excel and manually searching...
🚀 New case study — Relay: AI Operations Platform
I designed and built Relay, a self-initiated SaaS concept focused on automating repetitive business workflows with AI.
The experience is built around a simple narrative:
Signal → Decision → Action
I focused on:
— Premium SaaS UI/UX
— Product-focused visual storytelling
— Clear information architecture
— Responsive Framer development
— Workflow automation concepts
The goal was to make a complex AI operations product feel simple, clear, and launch-ready.
Designed & built in Framer.
🔗 Explore the full case study
#Framer #UIUX #ProductDesign #SaaS #AI #WebDesign
🚀 I built an AI-powered morning news automation with n8n.
Instead of manually checking multiple news websites every morning, I built a workflow that does it all automatically.
Here’s what it does:
📥 Pulls fresh headlines from Dawn News + BBC World
🕐 Filters out articles older than 24 hours
🤖 Uses Groq + Llama 3.3 70B to identify relevant stories and summarize them
✍️ Creates a clean daily news digest
📧 Sends the final digest directly to my inbox
The entire system runs hands-free.
The workflow contains 9 n8n nodes, covering:
→ RSS ingestion
→ Data merging
→ Date filtering
→ AI processing
→ Response parsing
→ Content formatting
→ Email delivery
One of the interesting parts was using a raw HTTP request to the AI API instead of relying on a pre-built AI node. This gave me more control over the prompt and output structure.
The challenging part wasn’t connecting the AI.
It was making the whole workflow reliable, especially handling messy article content, building valid JSON, and getting consistently structured responses from the LLM.
This is the kind of automation I love building: simple on the surface, but thoughtfully engineered underneath.
🎥 I recorded the full build so you can see exactly how it works.
#n8n #AIAutomation #Automation #AI #NoCode #WorkflowAutomation #BuildInPublic
