A health-tech client had 99.8% accuracy on a disease that shows up in 0.2% of patients. Their agent said no to everyone. Here is how I pulled a continuous risk score out of a binary agent so the AUC comparison against their XGBoost model meant something.
An AI engineer wires up models that already exist. A machine learning engineer builds the model. Which one you hire decides whether you ship in two weeks or spend six months in a sandbox, and here is how I tell the two jobs apart.
The RTX 30-series has no hardware FP8, so I packed four FP8 values into one FP32 container and unpacked them inside a Triton kernel. On a client’s 3080s that cut the memory bottleneck and ran about 3.3x faster.
A client thought their WooCommerce recommendation engine was broken because accuracy at a 0.5 threshold read 51%. The ranking was fine, the threshold was not. This walks through checking AUC in a spreadsheet with sorted scores and the trapezoidal rule.
A WooCommerce recommendation engine kept timing out the server, and the weights oscillated instead of settling. Swapping the basic update rule for Momentum and then Adam is what fixed it, and this explains why adaptive step sizes matter on messy data.
A WooCommerce client’s GPT search assistant was inventing products and discount codes. Prompt engineering did not fix it. Confidence thresholds, source links, and honesty about the limits did.
A client’s AI-built WooCommerce analytics dashboard crashed the moment we filtered by customer lifetime value. Rebuilding it meant sketching the data model and writing a DAL spec before touching any UI.
A mid-day flash sale took down a 30k-product WooCommerce shop and cost me three hours in Nginx logs. Here is what AI-driven server management does to that hunt, and where the automation stops.
Nobody checks whether $wpdb exists before running a query. The AI team wants models treated the same way in WordPress, with hosts providing the model and developers registering Abilities instead of wiring up API keys.