Build Log

2 posts in this category

Build Log: Prompt-Injection Hardening for Household AI Agents

Four controls that make prompt injection able to influence what a household agent says but unable to change household state: delegated research, human approval gates, signed webhooks, and no execution.

July 22, 2026•5 min read

LLMOps Agentic Automation+2

Build Log

Build Log: VPN-Only SSH and the Anti-Lockout Runbook

An SSH lockout during the platform's initial build, why the fail2ban jail is disabled on purpose behind a WireGuard-only sshd, and the runbook the incident produced.

July 21, 2026•5 min read

Self-Hosted WireGuard+2

Back to Labs