The New Big Ball of Mud: Why Agentic AI Systems Turn Fragile
This article explores the phenomenon of 'big ball of mud' systems emerging in the era of agentic AI, where users with limited technical backgrounds build complex, fragile systems relying on large context libraries. It highlights the parallels between traditional software fragility and the new challenges posed by AI, emphasizing the need for architects to prioritize architecture and maintainability despite abundant resources.
Original reporting · nngroup.com
Read “The New Big Ball of Mud: Why Agentic AI Systems Turn Fragile” at Nielsen Norman Group →How this was written. 1to1 wrote this article with a language model from Nielsen Norman Group’s reporting (model: @cf/ibm-granite/granite-4.0-h-micro); it describes that reporting rather than adding to it. The original, linked above, is the full story.
Key points from Nielsen Norman Group’s report
- A 'big ball of mud' system is a hastily built, short-term solution lacking long-term durability
- AI has turned resource scarcity into abundance, leading to overbuilding and increased fragility
- Five common patterns contribute to the formation and persistence of big ball of mud systems
From the source
AI makes building nearly free, so users grow agentic systems piecemeal into fragile messes they no longer understand.