Problem: Customers struggled to choose the right perfume and frequently asked for order updates manually.
Solution: Built a Messenger automation using ManyChat + Make.com + Google Sheets + WooCommerce. Perfume finder quiz (gender, preference, occasion). FAQs automation Order tracking via Order ID. Data stored & synced automatically.
Results: Faster responses, reduced manual work, and improved customer experience.
@Figma to @Shopify with @Instant, feels like designing at light speed if you are fast enough, you can design each section while the next one gets built with
@Instant AI is the part I love the best while using AI, adding my human touch and personal taste
say NO to e-comm generic design flop
turn on sound 🔈
Built an AI-powered customer support automation workflow that can classify incoming emails, identify support requests, retrieve relevant information from a knowledge base, and assist with generating the right response.
The workflow combines AI agents, RAG, embeddings, Pinecone, Gmail, and automated notifications to reduce repetitive support work while keeping human review in the loop.
The flow includes:
📩 Incoming email detection
🤖 AI-based support request classification
📚 Knowledge base retrieval with Pinecone
🧠 Context-aware customer support agent
✍️ Automated response draft generation
🔔 Reviewer notification through Telegram
⚡ Separate handling for non-support emails
I’ve been exploring more ways to combine AI + automation + real-world business workflows, rather than using AI only as a chatbot.