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
I recently built this workflow in n8n to automate the first stage of handling customer support requests.
The idea was to take an incoming ticket and let the system handle the repetitive work:
→ Receive the customer request through a webhook
→ Process and structure the incoming data
→ Use an AI Agent to understand the ticket
→ Classify it as Genuine, Spam, or Unclear
→ Route it based on the classification
→ Trigger the appropriate email action
→ Log the interaction in Google Sheets
I also added an Unclear path so that tickets the AI isn’t confident about don’t get blindly processed.
The goal isn’t to remove humans from customer support.
It’s to reduce the repetitive sorting and routing work, so the team can spend more time on the requests that actually need their attention.
Would you automate customer support differently? I’d love to hear how you’d approach it.
Really solid approach, especially adding the Unclear path instead of forcing the AI to make a decision every time.
Technical question: how are you handling AI confidence/scoring before routing a ticket? Are you using a structured JSON output with a confidence threshold, or...
Yeah, I’m handling it with a structured output rather than letting the AI make the routing decision completely on its own. The AI returns the category along with a confidence score, and I use a threshold to decide whether it should be routed automatically or sent to the Unclear...
The Unclear lane is exactly the right guardrail. I’d add two production checks: redact PII before sending ticket text to the model, and measure false-positive/false-negative rates by category rather than a single accuracy score. Logging resolutions and human overrides back into...
Yeah, definitely. I’m keeping the original ticket and the decision trace so there’s a record of what the AI decided and why. That way it’s easier to audit, debug, or replay when needed. And yeah, I like the idea of feeding the human overrides back into the dataset too.
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
Developed an AI-powered Marketing Campaign Automation platform that helps businesses create, manage, and optimize marketing campaigns across multiple channels with minimal manual effort. The solution leverages Generative AI and conversational AI to streamline campaign planning, content generation, audience targeting, and performance analysis. The platform enables marketing teams to launch campaigns faster while improving engagement and conversion rates. Inspired by modern AI-driven marketing approaches that automate campaign workflows and personalized customer interactions.
Interesting!
If you do it every day, automate it.
If you copy it - automate it.
If you send it repeatedly - automate it.
If you move it between apps - automate it.
If you spend hours processing it - definitely automate it.
I build AI-powered business workflows with n8n + APIs + AI to eliminate repetitive work.
Less boring work. More time for things that actually matter.
I help businesses build effective email marketing systems and automated workflows that capture leads, nurture prospects, and keep customers engaged without relying on repetitive manual tasks.
