This paper introduces Automated Design of Agentic Systems (ADAS), a new research area aiming to automatically invent building blocks and design powerful agentic systems, arguing that this could be a faster and more effective approach than manual design, drawing parallels to the history of machine learning where learned solutions surpassed hand-designed ones. The paper proposes and evaluates Meta Agent Search, an algorithm where a "meta" agent iteratively programs new agents in code, learns from past discoveries, and refines designs. Experiments show that agents discovered through this automated process significantly outperform state-of-the-art hand-designed agents across various domains like reading comprehension and math, and these discovered agents exhibit strong transferability across different tasks and language models. The work concludes by discussing the potential of ADAS, including safety considerations and future research directions like multi-objective optimization and higher-order ADAS.