I Built an AI Copilot That Thinks in Exploits, Not Prompts

My AI pentesting tool, RAWPA, was useful but needed to be smarter. I started by adding essential toolkits (LOLBAS, GTFOBins) based on direct community feedback. After a moment of inspiration, I designed and built the "Neural Pathway Methodology"—an AI "brain" for the app. This new feature uses a neural network trained on thousands of real-world pentest reports, combined with an LLM (Gemini), to generate custom, step-by-step attack plans. The tool evolved from a helpful but static checklist into a learning copilot that provides intelligent, context-aware guidance that improves over time.

Hey HackerNoon, it’s Kuwguap again.

A while back, I wrote about building RAWPA, my AI copilot for pentesters, and the tough decision to turn off its initial AI feature because it wasn't delivering. That was a lesson in knowing when to pivot. Today, I want to share the next chapter in that ...