Client: Roschiat Perfumes Built with: n8n · AI Agents (Gemini) · Airtable · Slack · Gmail Project Value: $200 Ongoing Maintenance: $50/month Project Overview Roschiat Perfumes needed a smart, scalable way to capture customer feedback, categorize it intelligently, and respond professionally—without manual effort. To solve this, I designed and implemented an AI-driven feedback automation system that transforms raw customer inputs into structured insights and automated actions. This system ensures no feedback is missed, improves response time, and gives the brand a clear understanding of customer sentiment. Key Use Cases - E-commerce Feedback Management - Customer Support Automation - Brand Reputation Monitoring - Product Improvement Insights - Internal Team Notifications Business Impact ⚡ Zero manual sorting of feedback ⚡ Instant AI-driven responses ⚡ Centralized customer insights ⚡ Improved customer experience & trust ⚡ Scales effortlessly as the brand grows Please review my project and share your suggestions for future enhancements. I have attached the production URL for your reference.https://n8n.srv1187080.hstgr.cloud/form/349ac866-9e24-4f8e-a5f7-05e4207828c8

Biggest challenge for e-commerce stores: Raw product images don’t sell. Customers want to see products on models and in real-life settings. So I built a UGC Image & Recreation Workflow (n8n + AI): - Form Submission → Client uploads any product image. - AI Image Analyzer → Detects and understands the product. - AI Agent (Gemini + Think) → Creates a smart prompt for recreation. - Image Recreation (API/Stable Diffusion) → Generates a new professional model-shot image. - Record Storage (Airtable/DB) → Saves original + recreated images + captions. ⚡ Outcome: ✅ Clients upload once → instantly get model-ready images. ✅ Campaign-ready creatives for ads, websites & social. ✅ Saves hours of manual design work.

ChatGPT and most AI tools answer using public internet data. But what if you want answers only from your own business or personal data? That’s where ✨ RAG Agents (Retrieval-Augmented Generation) step in. Here’s how I built one with n8n: - Trigger (Chat Message Received) → Listens for customer queries. - AI Agent (Google Gemini) → Core brain of the agent. - Vector Database (Pinecone) → Stores and retrieves your private data. - Embeddings (Google Gemini) → Converts data into searchable vectors. - Memory → Keeps chat context for natural conversations. ⚡ Outcome: Customer asks a question. RAG Agent fetches the most relevant info from your data. AI generates a precise, context-aware answer. If no private data is needed → it works like a normal chatbot. 💡 In short: RAG = Your Data + AI Power

🔥 Sending candidate outreach emails daily is time-consuming—especially when personalization is missing. So I built this workflow: 1️⃣ A daily trigger kicks things off automatically 2️⃣ Candidate data is pulled from Google Sheets 3️⃣ AI writes a personalized outreach email for each candidate 4️⃣ Emails are sent instantly via SMTP 5️⃣ Results are logged back in Google Sheets ⚡ Now outreach is personalized, consistent, and fully automated.

🔥 Scheduling interviews manually is painful—lots of back-and-forth emails, delays, and even double bookings. So I built a workflow to automate it: 1️⃣ Candidate shares their available times via a form/webhook 2️⃣ The system checks the recruiter’s Google Calendar 3️⃣ AI finds the best overlap 4️⃣ Calendar event is created instantly 5️⃣ Both sides get a confirmation email ⚡ In less than a minute, the interview is scheduled. Want to try this ?