subtopic

Trace every LLM request

10 min applied15 min research2 curated resources

Add tracing to the deployed chat API: every request becomes a trace with steps (retrieval, LLM call, tools), inputs/outputs, tokens, cost, latency, model and prompt version, user id (hashed) and feedback score. Open the dashboard and find the 5 slowest and 5 most expensive requests.

Builds on: 2.7 Evaluate

Notes, key code, what to skip and 2 curated resources are inside the platform.Join the waitlist and we'll build you a roadmap that includes this topic only if your goal needs it.

Get my roadmap