Field notes from the work, written for teams that ship.
Five findings from a static source code analysis of an open-source AI agent orchestration platform. Mapped to OWASP LLM Top 10 (2025) and MITRE ATLAS, with prioritized remediation recommendations.
Read Article →Patterns from analyzing AI incidents, testing AI systems, and evaluating model outputs daily. Most failures aren't sophisticated attacks. They're preventable. Someone just didn't ask the right questions.
Read Article →27 questions compiled from analyzing AI incidents and observing what separates successful deployments from failures. Drawn from security research and reverse-engineering what should have been asked before launch.
Read Article →Observations from daily AI output evaluation across frontier models. What actually works, what doesn't, and what the hype misses. The reality is more nuanced than either the AI doom or the AI utopia narratives.
Read Article →