Blog
Writing about cybersecurity, AI security, and things I find interesting.

·3 min read
xFire: AI Agents Debate Your Code So You Don't Ship Vulnerabilities and Bugs
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.
AI AgentsSecurityCode ReviewOpen Source

·9 min read
Stop Telling Your AI Agent What Not to Do
We built structured skills for our AI agent and watched performance drop by 6x. Here's what we learned.
AI AgentsSecurityLLMClaude Agent SDK

·3 min read
Benchmarking SAST
Choosing the right static analyzer — comparing SAST tools using precision, recall, and F1 metrics on realistic codebases.
SASTAppSecBenchmarking

·3 min read
SecLint: An Agentic Code Vulnerability Scanner
Context-Aware, Agent-Driven Security Scanning That Scales Beyond Manual Reviews
AI SecuritySASTRAGPython