π Product Image Sourcing Automation | n8n + AI I recently completed my first paid client project...π Product Image Sourcing Automation | n8n + AI I recently completed my first paid client project...
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
I recently completed my first paid client project: an end-to-end n8n automation designed to eliminate the manual process of sourcing, verifying, downloading, and organizing product images for large catalogs.
The clientβs existing process required manually searching for product images and checking whether each image actually matched the correct product, variant, size, and brand.
I built an automated pipeline that handles the process from CSV upload to final ZIP delivery.
Workflow:
π CSV upload with product names
π§ AI-powered product detail extraction
π Automated search query generation
π Product and image discovery
β Source-page verification for image accuracy
π¦ Automated image organization and ZIP generation
The workflow combines n8n, AI, search, data extraction, verification logic, and file processing into a single automated system.
The goal was not simply to automate individual tasks, but to create a complete workflow that could reliably handle a repetitive e-commerce operation with minimal manual involvement.
This project gave me the opportunity to take an automation from concept β development β testing β client delivery.
Tech stack:
n8n β’ AI β’ APIs β’ Web Search β’ Data Extraction β’ File Automation
Iβm currently building more practical AI and workflow automation systems for e-commerce and other business processes.
An AI-powered phone receptionist built for real estate agencies that answers inbound calls, qualifies leads in real time, and books showings directly to Google Calendar β all within the call itself, with no manual follow-up required.
The problem: Real estate agencies routinely lose leads to missed calls β after-hours inquiries, calls during showings, or overflow during busy periods. A slow callback often means the lead has already moved on to a competitor.
What it does:
Answers every call instantly, 24/7
Naturally qualifies the caller (buy/sell intent, area of interest, showing vs. agent call)
Collects contact details and preferred timing conversationally
Checks real-time calendar availability before booking
Prevents double-bookings and duplicate entries automatically
Confirms the appointment out loud before ending the call
Built with: Retell AI (conversational voice layer), n8n (workflow automation and business logic), Google Calendar API (scheduling)
Available for: Custom builds for real estate agencies, brokerages, or property management companies looking to stop losing leads to missed calls
I built an AI-powered Instagram chatbot using n8n, connecting AI, automation, memory, APIs, and knowledge retrieval into one complete workflow.
The chatbot can:
Understand incoming Instagram messages
Maintain conversation context using memory
Retrieve relevant information from a knowledge base
Generate intelligent responses with OpenAI
Automatically respond through the Instagram API
Tech Stack
n8n
OpenAI Chat Model
AI Agent
Pinecone Vector Store
Simple Memory
Instagram API
Webhooks
Switch & If nodes
This project was a great hands-on experience in building an end-to-end AI automation workflow and connecting multiple services to create a practical conversational system.
For me, the key takeaway was that effective AI automation is more than just an AI model, it's about connecting the model with the right data, memory, APIs, and workflow logic.