2 min lesson
Tracing, metrics and observability
Start at the first move in "Tracing, metrics and observability" and carry it through to the proof.
Step 1 of 2
You can't debug what you can't see. The first thing to build after the workflow works once is the trace that records what it actually did.
A trace captures one run end to end: the inputs and context that went in, the model's output, the tool calls it made, plus tokens, latency and cost. When a customer says "it did something weird on this PR," the trace is the difference between reproducing it in two minutes and guessing for an afternoon.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
diagram: stack
Each layer rests on the one below - if the trace isn’t captured, nothing above it exists.