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 developer built an email intelligence product using agents and MCP, running on open-source models, that lets LLMs query Gmail and Outlook mailboxes; in private beta.
A developer built an email intelligence product using agents and MCP, running on open-source models, that lets LLMs query Gmail and Outlook mailboxes; in private beta.
The developer spent six months writing the codebase with help from Cursor, Codex and Claude Code. The system runs in the cloud and connects to Gmail and Outlook mailboxes. Agents powered by open-source models process email content transiently without storing it. They derive intelligence that ChatGPT, Claude and other LLMs can query through MCP. It launches first as a ChatGPT app.
The codebase is largely done and running in private beta. Public launch is held up waiting on approvals from Google, Microsoft and OpenAI, which the author calls tedious. IMAP and other providers are planned for later.
Budget time for the provider approvals from Google, Microsoft and OpenAI; the author found them a slow, tedious gate even after the code was finished.
Help me build a small email intelligence tool that lets an LLM query a mailbox through an MCP server. Start with [Gmail or Outlook] read-only access and add tools for [search, summarize a thread, find attachments]. Use OAuth with the minimum scopes needed. Stop when I can ask a natural-language question about my mailbox and get an answer with the source emails cited, and ask before enabling any send or delete permissions.
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.