Automating a task and understanding it are not the same skill, and skipping straight to the first...Automating a task and understanding it are not the same skill, and skipping straight to the first...
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
Automating a task and understanding it are not the same skill, and skipping straight to the first one usually backfires.
I've watched people automate a report before ever manually building it once and the automation just encodes whatever mistake was already baked into the process. The manual version is where you find the edge cases. The automated version is where you scale them.
Do it by hand once before you let a script do it forever.
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.
A client shouldn’t have to learn Webflow just to publish their next case study.
On a recent build, I spent a lot of time on the CMS: setting up reusable blocks and the logic that lets the team update content without rebuilding pages.
The tricky part is deciding how much control to give them. Too little, and every update becomes a request. Too much, and they’re suddenly responsible for the layout.
I want them to open the CMS, know what to do, and get on with their day. There’s a fair amount of work behind making that feel simple.
Built AI-powered automation workflows using n8n, MCP, Firecrawl, APIs, Google Sheets, Email, Telegram, Slack, and ElevenLabs to automate lead generation, data enrichment, notifications, and business workflows.
n8n · AI Automation · API Integration · MCP · AI Agents