Answer patient enquiries for a clinic by chat
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
An agency owner built a WhatsApp agent for a tutoring company that books calendar appointments, shipped in two days for a $5K fee.
An agency owner built a WhatsApp agent for a tutoring company that books calendar appointments, shipped in two days for a $5K fee.
MarcoKueks, who runs a small AI agency and is not an engineer, built a WhatsApp agent for a tutoring company that books calendar appointments. He used Struere, a platform he built to handle the recurring WhatsApp-to-calendar-to-database plumbing. That let him spend most of the two days on the client's booking logic.
It shipped in two days for a $5K fee. Six months earlier, the same job took a week and a half, including days fixing messages that arrived but never triggered a booking.
The speedup came from reusing a platform he had already built after repeatedly paying developers for the same stack, not from starting fresh.
Build a workflow that takes incoming WhatsApp messages for [business name], asks the customer which [service] and what time they want, checks [Google Calendar name] for openings, and books the slot. Send a confirmation back to the customer. Test it with a few fake bookings and show me the results before turning it on for real customers.
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
An n8n workflow has AI classify web-form jobs by type, urgency and summary, create an Airtable record, reply instantly and flag uncertain cases.
Lindy agents summarized meeting notes, sent action items to teammates, suggested knowledge-base replies on support tickets, and handled follow-up emails and calendar updates.