One owner tried to run a whole business on agents. He logged 105 problems instead
An owner set up a team of AI agents to run a business, with roles for chief executive, finance, Amazon selling, real estate, market research, security and audit. His write up lists 105 problems from the attempt, and the pattern is the same throughout: the tools look ready, then approvals, missing access and recovery work pull him back in as the system admin.
How it works
- He sets up separate agents for running the business, finance, Amazon selling, real estate, research, security, audit and engineering
- He adds least privilege access, separate secrets and independent checks
- In daily use the Gmail read path never becomes routine, the Amazon Seller integration stays unfinished, and several agents hold titles without the data their jobs need
- Approvals succeed without unlocking the tool they were meant to unlock
- He ends up doing the admin, integration and recovery work himself and logs 105 problems with the fixes he wants
Why it’s worth knowing
He did everything right on paper: roles, least privilege, independent checks. The job that landed back on him was running the system itself.
Where it’s from
Summarized from a public post on github.com. See the original ↗