The New Big Ball of Mud: Why Agentic AI Systems Turn Fragile
Tanner Kohler · 2 October 2026
Read the originalA Nielsen Norman Group study by Tanner Kohler finds that people building their own AI agent setups grow them piecemeal until they can no longer explain them.
Tanner Kohler of Nielsen Norman Group, a user experience research firm, studied people without engineering backgrounds who build AI agent setups to help with daily work. Because AI makes building cheap, they kept adding and patching pieces without a plan. Several could not find, unaided, the files their own systems relied on.
- One participant's small status widget for Asana, a work-tracking app, grew, step by step, into a team-wide dashboard that predicted completion dates, although she could not write code.
- A product lead rebuilt his team's shared library of agent instructions twice because it had grown beyond what he could keep in his head.
- A participant who stored articles in an unsorted folder lost 45 minutes when the AI retrieved the wrong ones.
- Kohler recommends keeping system-wide instructions, task material and incoming streams such as email separate, and reading the system-wide instructions in full from time to time.
A team that shares an agent instruction library may need a named person to keep it short and to review changes. This is an inference and is not the author's claim. The study covers individual builders, not engineering teams.
Store the instructions every AI agent task reads, the files for one task and incoming streams such as email in three separate folders.
Read the instructions that apply to every agent task from start to finish on a schedule, and move anything task-specific out of them.
Derived by Working Surface from the article; more in the Playbook. Source line: A big ball of mud is a system scraped together for short-term functionality, not architected for long-term durability.
3 October 2026: the written material that steers AI agents has become a maintained product that needs an owner, and setups without one decay into tangles that only the AI can navigate.