← Glossary / 32 of 100
n. / Tracing basics
Distributed tracing
Definition
Distributed tracing follows one request across several services, processes or machines and joins the steps into a single trace. It works by passing a trace ID and parent span ID along with each call.
In more detail
AI systems are distributed more often than they look: a web app calls an agent service, which calls a vector database, a model provider and several tools. Without distributed tracing you get a separate fragment from each service. With it, one timeline shows the full path and where the delay or failure began.
Example
A Next.js route starts a trace, calls a Python agent over HTTP, and the agent calls a search API. All three services report spans with the same trace ID, so the viewer shows one tree.
