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 planning agent that works across Google Calendar, Linear, Gmail, and Google Docs through MCP.
A planning agent that works across Google Calendar, Linear, Gmail, and Google Docs through MCP.
Kim Maida built a dashboard with a chat agent, Todaygent, backed by an MCP server. One tool fetches Calendar, Gmail, Linear, Drive and other sources in parallel, scores tasks, and caches them in a local JSON file. Access is read-only. Keycard swaps one login for short-lived, per-source tokens. The agent only dismisses or reprioritizes tasks locally, after asking.
She uses it daily. Token exchange adds about 150–250ms per dashboard load. Early on the agent re-fetched data, dropped links and falsely claimed actions it couldn't take; a detailed system prompt addressed this. She says reproducing her prioritizing is an ongoing effort.
Keycard is in Early Access, and the author works there. It's a personal local tool, and a commenter warned it isn't production-secure.
Plan my workday using my [Google Calendar], [ticket tracker, e.g. Linear], [Gmail], and [Google Docs]. Look at today's meetings, tickets due or assigned to me, and emails needing a reply, then propose a time-blocked schedule with priorities. Don't send, accept, or edit anything until I approve; stop once I have the plan and a list of suggested replies.
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.