Design a fraud-detection system that uses LLMs (beyond a classic ML classifier).

The trap is replacing the classifier with an LLM. The real-time, imbalance, and adversarial constraints do not go away. The signal is a hybrid: a fast calibrated model scores inline, LLMs investigate the gray zone off the hot path.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.