Set up a chat agent for clinic questions

An n8n workflow used Gemini and Google Sheets to reply to patient chat enquiries with context kept across messages.

Done with n8nGemini· Intermediate· Oct 2026

What they did
Patients wrote in through a chat interface connected to an n8n flow. A Gemini agent, paired with Simple Memory, handled the ongoing conversation and looked up clinic details stored in Google Sheets before drafting replies.
How it went
The setup was meant to make clinic communication smoother and cut down on manual replies. No performance numbers or other results were reported.
Tips
Use the sheet as the single source of truth for clinic details, and check a few sample conversations before letting it answer patients directly. For anything medical or uncertain, have the workflow route the message to staff instead of trying to resolve it alone.

Try it yourself with n8n

Create an n8n workflow for a [clinic type] chat assistant. Connect incoming messages from [chat tool] to a Gemini agent with memory so it can follow the conversation across multiple turns. Pull up-to-date answers from a Google Sheet that includes [services], [hours], [pricing], and [location]. Draft responses in a calm, helpful tone, but if a message is medical, sensitive, or unclear, do not answer it directly; pause and ask for staff review, then notify [staff email] before anything is sent. Test the workflow with sample patient questions and show me the replies before I use it with real patients.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on x.com ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.