Prompting is so yesterday...hello Loop Engineering

Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of a recursive goal where you define a purpose and the AI iterates until complete. It’s roughly five building blocks and Claude Code and Codex both have all five now.

1. Automations that go off on a schedule and do discovery and triage by themselves.
2. Worktrees so two agents working in parallel dont step on each other.
3. Skills to write down the project knowledge the agent would otherwise just guess.
4. Plugins and connectors to plug the agent into the tools you already use.
5. Sub-agents so one of them has the idea and a different one checks it.

The space moves really quickly, so don't worry about trying to "keep up" with the very latest at all times. For example, if you're just getting into using AI, then don't worry about doing Loop Engineering yet since that is a higher level of "AI Maturity"