AI agents work fine, your workflow doesn't

"Boards everywhere are saying "we need AI agents." That pressure moves down the organization fast. Teams build a pilot and achieve good results in a sandbox. Then they try to put it in production and everything slows down. Usually, the model performed fine. What was missing was what surrounded it-monitoring, ownership, a plan for when things go wrong."

"I've been shipping software in regulated industries for 20 years. In those industries, when something hallucinates, planes don't fly or money doesn't move. So you learn to care about the process more than the tools, and realize that the model is the easy part. You can swap one for another in an afternoon. What you can't swap is the workflow underneath it, and the domain knowledge baked into how an agent actually makes decisions."

"In production, you don't release anything without a rollback plan. You collect metrics from day one because if you forget, you can't answer questions later. Every layer needs to be traceable. None of it changes just because the code is being written by an agent instead of a person."

"An agent in a regulated environment needs control on its decision logic, defined inputs and outputs, monitoring, and a way back to a safe state when something breaks. But the harder part is what comes before any of that-domain knowledge. The reason companies keep working with the same engineering teams for years is that those teams know which systems interact, which areas are fragile, and where a small change cascades."

Boards push organizations to build AI agents quickly, often starting with pilots that work in controlled sandboxes. Production deployment then slows because the model is not the only requirement. Regulated environments require process controls: decision logic control, defined inputs and outputs, monitoring from day one, traceability across layers, and rollback to a safe state. The workflow underneath the model and the domain knowledge that shapes agent decisions are harder to replace than the model itself. Long-term engineering teams provide accumulated understanding of interacting systems, fragile areas, and cascading failure risks. Without that knowledge, organizations may automate processes they do not fully understand, and most enterprise AI pilots fail to produce measurable business impact due to adoption, integration, and governance gaps.

Read at Fast Company