Claude Code Plan mode의 Prompt 기반 제어 한계와 Runtime Enforcement의 필요성
Claude Code's plan mode is prompt engineering, not hard enforcement
Claude Code's plan mode is prompt engineering, not hard enforcement
Execution Governance, AI Drift, and the Security Paradox of Runtime Enforcement
The Agent's Word Is Not Enough: External Validation in the Agentic Governance Stack
Day 27: How Explaining Solana's Account Model Made Me Finally Understand It
What the Pocket OS Incident Tells Us About Agentic Security
Compliance as Code: Why the EU AI Act Will Force Runtime Enforcement in 2026
I Tried to Break My AI System with Real Attacks — Here’s What Happened
SafeBrowse: A Trust Layer for AI Browser Agents (Prevent Prompt Injection & Data Exfiltration)