Writing
Writing about cybersecurity, AI security, and things I find interesting. Also on Substack.
2026-03-29 · 7 min read
Current static analysis tools weren't built for agentic systems where dangerous capabilities are features, not bugs. Here's a benchmark to measure what they actually catch.
2026-03-02 · 3 min read
Security review is too important for a single opinion and too noisy to tolerate false positives. xFire uses multi-agent adversarial debate to fix both.
2026-02-26 · 9 min read
We built structured skills for our AI agent and watched performance drop by 6x. Here's what we learned.
2025-10-02 · 3 min read
Choosing the right static analyzer — comparing SAST tools using precision, recall, and F1 metrics on realistic codebases.
2025-07-23 · 3 min read
Context-Aware, Agent-Driven Security Scanning That Scales Beyond Manual Reviews
