Active Directory is where most internal compromises happen and where most AI tools give up. Darkmoon runs the AD attack path autonomously and shows every step.
Why AD is hard for AI
AD attack paths are stateful and multi step. A single prompt cannot hold the whole graph. You need an agent loop that enumerates, reasons and pivots while keeping state.
Playbooks as the state engine
In Darkmoon the AD methodology is a Markdown playbook you can read and fork. The agent follows it, the proxy keeps the state, and every tool call is explicit.
