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.
A self-hosted desktop app runs background agents, with finished work in Unread and approvals in Action; it began as automating CRM activity logging and meeting prep.
A self-hosted desktop app runs background agents, with finished work in Unread and approvals in Action; it began as automating CRM activity logging and meeting prep.
You start or schedule a task in the desktop app (Electron, also available in a browser or CLI), then carry on with other work. Runs are checkpointed and continue after you navigate away. Finished work goes to Unread, and runs needing a decision go to Action. Cron or webhook triggers can start runs, and skills run as delegated workers. Local folders are only reachable if you grant them.
The README gives no results or metrics beyond saying more than 2,000 Amazon users tested earlier versions. It doesn't mention CRM logging or meeting prep, so that origin isn't confirmed here.
The api-server process has to stay running for agents to keep working. You also need Node.js 24 or newer and a model provider configured under Settings > Providers.
Set up a background agent that every [weekday morning] reviews my [calendar and CRM] and drafts meeting prep notes for each upcoming meeting, plus activity log entries for yesterday's calls. Put finished prep notes in an unread list, and put anything that would write to the CRM or send a message in a separate approval list. Do not make any changes or send anything until I approve it.
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.