- latency and errors
- data and concept drift
- LLM metrics
- logs and traces
MLOps / monitoring
Monitoring
Service metrics, ML metrics, data drift, concept drift, calibration, LLM cost/tokens/latency/tool success/retrieval quality, alerts, dashboards, logs, traces, and OpenTelemetry.
shellbackend needed later
Service, ML, and LLM metric dashboard with drift, calibration, retrieval quality, traces, and alerts.
- What is the core job of "Monitoring"?
- Which common mistake would break a production implementation of this topic?
- Which inputs or limits must be validated before the interactive feature ships?
- What is the smallest test that proves the future implementation behaves correctly?
- When does this module really need backend compute, and when is a UI simulation enough?
- Start with one focused feature, not a full course inside one page.
- All public inputs must be typed, bounded, and covered by reject-case tests.
- If a model, dataset, or job is added, document source, license, limits, and fallback.
- The interaction must explain the topic rather than serve as decoration.