Simon Willison introduces the term 'agentic engineering' to describe software development assisted by coding agents — tools like Claude Code, OpenAI Codex, and Gemini CLI that write and execute code in a loop to achieve goals. The core definition of an agent is: runs tools in a loop to achieve a goal. Code execution is the key capability that makes this useful. The human role shifts from writing code to specifying problems, providing the right tools, and verifying results. This is the opening chapter of a living guide on agentic engineering patterns.
Sort: