Work Smarter,
Not Harder

A multi-agent system runs most of a one-person company. These are the measured results, failures included.

Latest Articles

What it costs to have an AI agent system build and ship a client app

A client asked for an app. A multi-agent system built a throwaway proof of concept, then rebuilt it into a hardened product, deployed it, and ran it at a live event. The measured economics: ~$1,350 of model usage and ~12–33 hours of operator attention, against a rough ~160-hour guess for a solo developer.

Docker isolation held against 86 AI escape trials

86 controlled container escape trials with Claude Opus and Sonnet. Default Docker held, but the agent queried its own API for zero-days, spawned remote agents from isolation, and attacked the measurement harness. Independent data complementing Anthropic’s Mythos System Card.

Infrastructure Security Report: Q1 2026

Security audit of a multi-server production fleet: SSH brute-force analysis, web threat landscape, AI crawler patterns, honeypot findings, and hardening assessment. 27 months of data.