方寸 Portal

AI Engineer Portal

Your personal operating system for career transition.

Private mode

Exercise

Build a cost and latency dashboard aggregator

Build a Cost and Latency Dashboard Aggregator

Without visibility into cost per feature and per model, you cannot make rational optimization decisions for production LLM services.

What to build

Implement CostLatencyDashboard:

  1. record(feature, model, input_tokens, output_tokens, latency_ms, success) — Ingests one request event.

  2. cost_by_feature(model_prices: dict) -> dictmodel_prices: {model: {"input_per_1k": float, "output_per_1k": float}}. Returns {feature: {"total_cost_usd", "request_count", "avg_cost_per_request"}}.

  3. latency_summary(feature: str | None = None) -> dict — Returns {"p50_ms", "p95_ms", "p99_ms", "avg_ms", "error_rate"}. None = global.

  4. top_cost_drivers(model_prices, n=5) -> list[dict] — Top n (feature, model) pairs by cost. Each: {"feature", "model", "total_cost_usd", "request_count"}, sorted descending.

Constraints

  • Standard library only. Nearest-rank percentile: index = ceil(p/100 * len(data)) - 1.

Evaluation / medium / Step 26 of 36

Practice stage

Evaluation and review loops

Hint

Separate the scoring logic from the interpretation logic. Your goal is not just a number; it is a useful next action.

Success criteria
  • - Produces a useful signal, not decorative output
  • - Makes regression review easier
  • - Would support a benchmark or observability loop
Review checklist
  • - Would this output help decide what to fix next?
  • - Are important failure modes visible?
  • - Does the score hide any ambiguity I should record?

Practice

Generate a variation

Generate a new exercise variation to deepen understanding or practice a related concept.

Attempt history

Recent submissions

Before you submit, decide what a strong answer should make obvious to the reviewer.

No attempts yet.