Work & Operations
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.
n8n · Gemini
Run a company autonomously
Andon Labs on why they built Pion, an agent designed to run any company on its own.
Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported
Use case overview
Andon Labs on why they built Pion, an agent designed to run any company on its own.
Reported experience
What they did
Andon Labs built Pion to run its real businesses: vending machines, a retail store in SF, a cafe in Stockholm and radio stations. Persistent agents get email, phone, banking, browser and secure computing environments. Pion is now open as a research preview, and people with a business or idea can join a waitlist. Andon says it relies on automated monitoring to catch unwanted behavior.
How it went
Early agents made costly mistakes, and by late 2025 frontier models ran a vending machine profitably. The store and cafe lost money early and are still unprofitable, though they have improved with newer models.
Worth knowing
The store and cafe lost a lot of money early, partly from rent and the salaries of the humans they hired. Expect incidents, since Andon says unchecked agents risk them.
Example prompts
I want to test how far an AI agent can run a small business: [describe business, e.g. an online store for X]. Draft an operating plan covering sourcing, pricing, customer messages, and daily tasks, and list what you can do on your own versus what needs my approval. Do not spend money, publish anything, or contact anyone until you've shown me the exact action and I've approved it.
Related use cases
Work & Operations
Triage car repair requests and reply to customers
An n8n workflow has AI classify web-form jobs by type, urgency and summary, create an Airtable record, reply instantly and flag uncertain cases.
n8n
Work & Operations
Summarize meetings and triage support tickets with Lindy
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.
Lindy