Field notes from two weeks of running an autonomous agent on real money Most writing about AI agents...
Field notes from two weeks of running an autonomous agent on real money
Most writing about AI agents is a demo. Someone connects a tool, runs one clean task, and publishes.
This is the opposite. It's a log of what broke when an agent was given real files, a real bank account, and permission to act without supervision — over two weeks, on a small construction company's books.
Every failure below actually happened. Each one has the same shape:
The agent reported success. The success was not real.
Your agent passed its tests. It ran clean in the demo. You shipped it. Two days later it's...
Six failures from the first twenty-four hours of an autonomous agent loop, including the monitor that could not detect the loop…
A practical look at the runtime of an AI agent — what actually happens between the prompt and the...
This month the front page filled up with AI agents going off the rails — one reportedly ran its...
Most "AI agent" demos die at the same place: a tweet, a screenshot, a five-minute video. Then the...
We’ve all been there. You build an AI agent, give it a sophisticated prompt, hook it up to a couple...
