Test whether an AI agent guardrail is still working: rerun the corpus with the gate deleted. Each bad input lands LOAD_BEARING, SHADOWED or MISSED.
Your Guardrail Test Still Passes With the Guardrail Deleted
Related
A Test Run I Aborted Came Back and Corrupted My Evidence
From the agentdrill v0.1.0 release, part of agentic-suite: open-source, harness-agnostic security...
Agents Don't Need Your Password. They Need Your Paste.
Nobody has ever stolen my password. I know this because I hand out something better than my password...
Four Evenings, One Walking Atlas: AI Agents Are Not Just for Coding
How a static BattleTech board game got animated mechs — without me becoming an artist (and avoiding...