Deny by default: fail-closed policy and human approval
🇫🇷 Version française 💻 Source code (AGPL): github.com/patlegu/cyber-agent-engine The firewall reflex, applied to an AI decision The first article in this series laid out the general thesis: an LLM that drives a production firewall must never cross, on its own, the boundary between intent and execution. The second showed how that boundary protects data — the model only ever sees tokens, never a real IP. This one tackles the other half of the problem: once the LLM has proposed an action on tokens, who decides whether it’s allowed to actually happen?
