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 an AI-powered email automation using n8n that reads incoming emails, processes the code inside them and sends back a fully documented response automatically.
Here’s what happens under the hood:
→ Gmail Trigger detects a new email containing code
→ Two LLM chains (Groq Model) run in parallel one adds inline comments to the code, the other generates a plain English summary
→ The outputs are merged and aggregated into a single structured response
→ Edit Fields formats everything cleanly
→ A final LLM pass polishes the content
→ Gmail sends the documented code + summary back as a reply
No manual review. No copy-pasting. Just structured, AI-generated documentation delivered straight to your inbox.
Built with: n8n · Groq · LLMs · Gmail API
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
Just wrapped up building flux/, an interactive UI with real-time WebGL rendering, custom GLSL shaders, and scroll-driven animation, built entirely from scratch with vanilla JS, what do you think?
It's been a super fun shift for me, most of my background is Python automation, AI integration, and data pipelines, but diving into frontend/UI work like this has been genuinely rewarding.
Link's in my portfolio if you want to see it in action. Always open to talk automation, AI integration, or interactive web work.
The vanilla JS route is the part I would defend - straight to GLSL instead of inheriting a scene graph you never needed. The one that caught me on scroll-driven work was portrait: visible width is 2*z*tan(fov/2)*aspect, so at 0.75 aspect you see less than half of what you...
I built an AI-powered Telegram assistant that handles incoming messages, understands requests, and responds automatically.
Using n8n, Google Gemini, and memory, the workflow helps reduce repetitive manual responses and keeps communication moving without constant intervention.
Designing Bledga with a clear, intuitive interface—from profile and settings to support and upgrades—so every interaction feels simple, purposeful, and easy to navigate.
Looking really clean and usable!