Letting Agents Assign Tasks to Each Other: A Practical Build from tmux to Handoff
How to turn manual copy-pasting across CLI agent terminals into auditable mutual task assignment using dynamic discovery, capacity allocation, and file-first handoffs.
All articles
Agent Workflow in Practice — a 19-part hands-on series →
Turn a Second Mac into an AI Extension: Cloudflare Tunnel + SSH Zero Trust Hands-on
Use Cloudflare Tunnel and Zero Trust to open a multi-device AI Agent channel, secure SSH into an idle iMac as a LINE Bot extension, with full setup steps and failure notes
The AI Arms Race Winner Won't Be the One With the Best Model — How Harness Became the Real Moat
In 2026, the decisive advantage in the AI industry is shifting: LangChain jumped 25 ranks on TerminalBench by changing only its Harness, OpenAI launched a $14B deployment company, and NousResearch went from 8 followers to a $1B valuation. This article dissects how model-external engineering is becoming the new center of power.
Memory Isn't a Plugin — It's the Harness: Why Your AI Agent Keeps Forgetting
The model needs the body. A brain without a harness is just floating.Imagine a superintelligent brain floating in a nutrient tank. It can reason, write poetry
The Harness Determines the Ceiling: Why the Same AI Brain Performs Wildly Differently in Different Bodies
Imagine a world-class chess grandmaster locked in a sensory deprivation chamber. They can think, analyze, and strategize at the highest level — but they can't s
Twelve Guardrails for AI Agents: The Harness Design Patterns Behind Claude Code
That impressive AI agent demo you saw on Twitter? It probably falls apart in three minutes of real-world use. Not because the model is weak — because nobody bui