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
Designed and deployed a secure, automated AI customer support workflow built in n8n using the Google Gemini API. The system parses customer inquiries, applies strict business compliance rules, and formats output as structured JSON to determine whether to resolve inquiries automatically or escalate them to a human agent.
Key Technical Details Shown:
Workflow Engine: n8n (Google Gemini Chat Model node)
AI Model: Google Gemini (gemini-3-flash-preview)
Structured Output: Enforced JSON schema containing intent classification (category), human escalation flags (needs_human), and pre-drafted responses (draft_reply).
Compliance Guardrails: Custom prompt guardrails instructing the AI never to handle sensitive inquiries (e.g., dosage, medical/health advice, safety claims) and automatically route them to human support.
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
Related posts
Just wrapped up an AI voice agent for a residential cleaning business 🎙️ It handles the full call end to end — checks service area, gives a live quote, checks real calendar availability, and books the appointment straight onto Google Calendar. Built with Vapi + n8n + Google Calendar API. Portfolio build, but fully working — swipe through the n8n workflow in the video 👀
#aiworkflow #automation #voiceai
Rope Street Tattoo, Brașov (fictional)
Problem solved: a solo tattoo artist loses tourist leads to midnight DM replies and a day's pay to every no-show. Now any message becomes a priced, deposit-paid booking in under a minute, and confirmations, reschedules and waitlist refills run on their own.
The client: Mara, one chair, around the corner from Strada Sforii. Gloves on 7 hours a day, so DMs wait until midnight. Every quote needs size, placement and colour: about 7 messages per booking. Tourists leave before she replies, and 1 client in 7 doesn't show up.
What I built in Lovable:
→ Front door: describe the idea in English, German or Romanian. AI reads it, but Mara's own rules set duration, price and deposit. Only times that fit the job and the customer's days in town. Stripe deposit, booked. Cover-ups and hands go to Mara instead.
→ Autopilot: confirm or move at 72 h, a second nudge at 48 h, unconfirmed slots released 24 h ahead and offered to the waitlist, prep reminders, online consent forms, aftercare and touch-ups.
→ Owner area: Today, Week, Needs you with drafted replies, paste-a-DM replies, and the numbers: in four weeks of demo data, 304 messages not written and 38 h 53 min saved.
→ A demo clock to fast-forward and watch it work.
Try it: https://rope-street-tattoo.lovable.app
Owner view: footer → Studio → Try the owner view → Demo clock
Case study: https://rope-street-tattoo.lovable.app/story
A tourist who books two days ahead lands inside the 72-hour confirmation step. Does that booking skip the confirm-or-move message, or does it get the 48-hour nudge straight away?
Built an automated lead enquiry workflow using n8n to handle incoming WhatsApp enquiries, process contact information, trigger automated responses and update customer data.
The workflow connects multiple steps into one system, reducing manual handling and making sure new enquiries are processed consistently.
Built with: n8n, WhatsApp, webhooks, APIs and custom logic.
The focus was simple: turn an incoming enquiry into an organized, automated workflow without requiring someone to manually process every step.
