Agent TTP
For:
General, Agent Designers
Reading agent intent → Techniques, Tactics, Procedures
Research & Insights
Deep dives into AI security, policy, and the future of trustworthy AI systems
A Guardrail for Claude Code
For:
AI Security Teams & Agent Developers
So you dont have to babysit it.
Building Custom AI Guardrails, Krnel style
For:
Agent Developers & AI Safety Teams
Learn how to build faster, cheaper, and more accurate guardrails by reading your model's internal state - no separate guardrail model required.
krnel-graph: The scikit-learn of AI internals
For:
Agent Developers and MLEs
An open framework bringing representation engineering out of research notebooks and into production.
AI = Data + Biases
For:
General
Role of Bias
AI's Subtle Switch
For:
General
Simple Inputs, Complex Core → Complex Inputs, Simple(r) Core
Surveying the Precision-Recall Gap in LLM Security
For:
AI Security Teams & Agent Developers
Not all guardrails are created equal.
Into the Kernel: Decoding AI's Hidden Mind
For:
AI Leaders & Technical Founders
Model Internals Is All You Need