How Cassian uses 14 specialized agents to review PRs for security regressions, with an experiment in semi-formal reasoning certificates for structured code analysis

How I built a multi-stage agentic pentest pipeline, what it found and missed, and how to use the approach in your workflows

A bring-your-own-model extension for running local and cloud LLMs inside Burp Suite

How I adapted nanochat for security vulnerability work, what the training logs actually showed, and where the model broke

How I adapted the Ralph Wiggum autonomous agent pattern for penetration testing with static analysis and dynamic validation

How I built it, why it failed, and what the data taught me