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 bookkeeping assistant for freelancers and small businesses reads receipt photos sent through Telegram or Discord and extracts vendor, amount, tax, category and date.
A bookkeeping assistant for freelancers and small businesses reads receipt photos sent through Telegram or Discord and extracts vendor, amount, tax, category and date.
The builder made AICountant for freelancers and small businesses as a Telegram or Discord bot. Users connect one of those accounts, send a receipt photo, and the AI pulls out vendor, amount, tax, category, and date, then adds the expense to a ledger for review before the user can export it as CSV.
The post says the product was already functional and the creator was recruiting beta testers to validate usage patterns. They specifically wanted real receipts from different countries, formats, and industries to find weak spots in extraction.
The main catch was coverage: they were still testing on varied real-world receipts to improve accuracy, so reliability across formats was not yet proven.
Build a workflow that triggers when I send a receipt photo to my [Telegram/Discord] bot. It should extract vendor, amount, tax, category, and date, then append a row to my [Google Sheet name]. Test it with [3] sample receipts and show me the rows it created. Flag any receipt it cannot read clearly instead of guessing.
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.