RESEARCH & OBSERVATIONS
Field notes.
Practical thinking on automated abuse, agent security, and the assumptions worth challenging.
Automated abuse
Why IP reputation misses coordinated abuse
A request can look ordinary in isolation and still be part of a coordinated attempt to exploit your business.
Read field noteAgent security
Limiting what an AI agent can do
An agent that can read, decide, and act needs limits enforced by the systems around it.
Read field note