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.
Authors use Cowork or Claude Code to schedule invites, triage email, book flights and hotels, pull Airtable data and scrape exhibitor lists.
Authors use Cowork or Claude Code to schedule invites, triage email, book flights and hotels, pull Airtable data and scrape exhibitor lists.
The authors run Claude in Cowork or Claude Code and link Gmail, calendar, Airtable and other apps through Rube, a free connector service. They teach it routines as saved Skills and keep notes in markdown files. It then finds open calendar slots and sends invites, triages and archives email, books travel through a booking tool, and scrapes exhibitor lists with Firecrawl.
The authors call the agent useful across daily workflows, data pulls and research. They give no metrics. They say Claude sometimes skips a Skill unless told to use it, and that it can make mistakes.
Needs a paid Claude plan (Pro is $20/mo). Start with drafts rather than sending, watch for prompt injection, and consider giving the agent its own limited email account.
Act as my work assistant for this week's tasks: [list tasks such as schedule a meeting with X, triage my inbox, find flights and hotels to [city] for [dates]]. For each task, finish the prep and show me the result. Pause and show me details before sending any invite or email, or booking or paying for anything.
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.