Simon Willison defines 'agentic engineering' as the practice of developing software with coding agents—AI systems that can both write and execute code in a loop to achieve a goal. He explains that these agents use LLMs to generate code, run tools, and iterate until the objective is met, shifting the human role from writing code to defining problems and evaluating solutions. The article serves as an introductory guide to this emerging engineering paradigm.
Background
The rise of large language models (LLMs) capable of generating code has led to the development of 'coding agents' that can autonomously write and execute software. This shifts the traditional software engineering workflow, prompting discussions about new development methodologies.
- Source
- Simon Willison
- Published
- Mar 16, 2026 at 06:41 AM
- Score
- 6.0 / 10