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 n8n AI workflow reads labeled payment emails in Gmail, pulls the top three takeaways from each and sends a Sunday digest.
An n8n AI workflow reads labeled payment emails in Gmail, pulls the top three takeaways from each and sends a Sunday digest.
The author labels payment emails in Gmail, then builds an n8n workflow that runs Sunday at 8 AM. It fetches the past week's labeled messages, aggregates them, and truncates the text to 100K characters. An AI Agent node running gpt-4o-mini through OpenRouter writes the digest from a system-message template. A code node converts the markdown to HTML, and Gmail sends it.
The author gets about 15 payment notifications a week, and the workflow turns them into one weekly digest email. The post gives no measured results beyond a successful test run.
Truncating to 100K characters keeps the combined email text within what OpenAI can handle. Without the formatting code node, the email shows raw markdown symbols.
Build an n8n workflow that every Sunday reads emails under Gmail label [payment notifications] from the past week, has AI pull the top three takeaways from each, and compiles them into one digest. Send the digest to [my email]. It's finished when a test run produces a digest from the last week's labeled emails.
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
Score every demo request against your ICP, update HubSpot and ping the right rep in Slack within a minute of the form submit.
Every new Zendesk ticket gets a category, priority and sentiment tag plus a draft reply in an internal note before an agent opens it.