AI SAFE² CLI 0.9.0: Run Challenge 001 with Reproducible Evidence
“Can an agent harness stop unsafe actions without blocking legitimate work?” That’s the central question of agent safety, and until now it’s […]
AI SAFE² CLI 0.8.0: Evidence-Bound AISM Remediation Decisions
Assessment without remediation is trivia. You ran the AISM scoring, you found the gaps. And then what? A spreadsheet of findings with […]
AI SAFE² CLI 0.7.0: Turn Agent Claims into Reviewable Operational Truth
Here’s a scenario that should worry you: the agent says it finished. The test passed. A receipt exists. And the three of […]
AI SAFE² CLI 0.6.0: Scope the System. Attribute the Change. Decide with Evidence.
Three questions every security team asks about every change, and three ways the answers usually go wrong: “What’s actually in scope?”: answered […]
AI SAFE² CLI 0.5.0: Find Where Agent Work Actually Failed
Something went wrong with your agent. What do you do? Most teams do the same thing: blame the model. Swap it, prompt […]
AI SAFE² CLI 0.4.0: Know What Agent System You Actually Tested
“The model passed the evaluation.” No, it didn’t. A system passed or failed. The same model behaves completely differently depending on the […]
AI SAFE² CLI 0.3.0: Show the Evidence Behind “Done”
The agent said it finished. Did it? That’s the whole problem with AI agents in one sentence. A coding agent finishes a […]