What we learn shipping AI systems, computer vision, and automation into production — written for the engineers and operators who have to run them.
Confidence, sources, and the moment a system should admit it does not know — interface patterns for products whose output is probabilistic.
The demo works, the pilot stalls, the rollout quietly dies. Four failure modes we see in almost every agent project — and what a system that survives contact with real users looks like.
Chunk, embed, search, stuff into a prompt. That pipeline gets you a convincing prototype and a support queue full of confidently wrong answers. Here is what we build instead.
Lighting changes, cameras drift, and the operators will move the mount. What we learned deploying defect detection into a plant that runs three shifts a day.
Where machine learning genuinely helps inside an ERP, where it absolutely should not go, and how to keep an auditable trail through both.