Series

Building Correlic

The real engineering story behind building kernel-level security monitoring for AI coding agents — from userspace failures to eBPF breakthroughs, detection engines, behavioral baselines, and an AI investigation system that never hallucinates. Three parts, every wall hit along the way.

[Part 1] Building Correlic: Capturing Every Action Your AI Agent Tries to Hide
Four failed attempts, one kernel breakthrough, and the real cost of making AI agents transparent
Apr 4, 202619 min read16
[Part 2] Building Correlic: Your AI Agent Made 70 System Calls Per Second. Here's How I Taught My System Which Ones Matter.
Four failed attempts at teaching a machine what matters — and the baseline system that finally got it right.
Apr 9, 202615 min read4

Command Palette