The Problem: Context Rot Have you ever had to stop an AI agent halfway through a task to...
Research, Plan, Implement: A Workflow That Keeps AI Agents Accurate
Related
Four green CI checks. All four blind.
Quick take A broken CI check is loud: the pipeline turns red, someone looks. A blind check is silent...
I audited six token usage trackers. They disagree with each other by 2x to 8x.
Over the past five months I took apart the folding logic in six token usage trackers and recomputed...
Read-Only Kubernetes Access for AI Agents: Why "Please Don't Delete Anything" Isn't a Security Boundary
I keep seeing the same pattern: take an LLM, give it access to kubectl or the k8s API, write...