- In short
- Request-level tracing captures the raw material, model, tokens, latency, stop reason, and tool calls, for every individual call. Metric aggregation rolls that request-level data up into dashboard metrics: cost per request, latency p50 and p95, task success rate, and error rate by type. Aggregate metrics can look healthy overall while a small fraction of requests consumes most of the budget or produces wrong outputs, so per-request decomposition is what protects against the non-obvious failures that aggregate-only dashboards hide.
Full concept guide coming soon
We are building the in-depth, exam-aligned guide for this knowledge point. In the meantime, explore the prerequisites and related concepts below, watch the official Anthropic Academy lessons, and start an adaptive study session to master it with Archie.
Watch and learn
Official Anthropic Academy lessons first, then hand-picked walkthroughs. Videos load only when you press play.
No videos curated for this concept yet
We are still curating the best official and community videos for this topic.
References & primary sources
Adaptive study
Master this concept with Archie
Practice it inside an adaptive study session. Archie, your Socratic AI tutor, tracks your mastery with Bayesian Knowledge Tracing and schedules the perfect next review.