Why is observability especially important for AI features compared to typical CRUD endpoints?

AI calls have highly variable latency and cost per request (unlike a fixed-cost DB query), can silently fail in 'soft' ways (a technically-200-OK response that's actually a bad hallucination), and their behavior can drift as providers update underlying models — without tracing token usage, latency, and cache-hit rate per call, none of that is visible until a user complains.