Writing · Tag
4 posts tagged #agents.
Anthropic banned 832 accounts for AI-enabled attacks. What it means for teams running AI agents.
My blog repair loop chewed on a stale draft for 23 mornings and reported "blocked" every time. The fix was not a smarter retry. It was a TTL and a heal path.
Before you ship an AI agent for a client, prove budget caps, loop detection, alert proof, remote kill, and retained incident history.
A trace tells you what happened. A kill switch changes what happens next.
Real costs, real tools, no fluff. M-F when I ship, publish, or learn something worth sending.