The real setup is not MCP servers, skills, memory files, and subagents. It is the contract stack that decides what an agent may know, do, prove, escalate, and lose.
Your AI Agent Stack Is Solving The Wrong Problem
Related
The Guardrail's Failure Mode Is Always "Allow"
Guardrails get tested for what they catch, never for what happens when the guardrail service itself times out. That untested path defaults to allow.
The Path Traversal Fix Cursor Writes Ignores Symlinks (CWE-22)
TL;DR Ask Cursor to fix a path traversal bug and you get path.basename, path.resolve, and...
AI Agentic Memory for beginners.
Hello there, it's been long since I posted my last blog. I have recently been learning a lot about AI...