Writing about Agentic Engineering Patterns for Real Work

I’m using Agentic Engineering to refer to building software using coding agents—tools like Claude Code and OpenAI Codex, where the defining feature is that they can both generate and execute code—allowing them to test that code and iterate on it independently of turn-by-turn guidance from their human supervisor.

This lands for me because it is about operating model, not branding. The meaningful shift is that the agent can act, verify, and keep going, which changes how much structure you need around tasks, documentation, and feedback loops.