Glossary · Phase 1 · Building with LLMs
Trace
A record of every step in one multi-step run, such as an agent's model calls and tool calls, grouped under one id.
An agent run or a prompt chain is many calls. A trace groups them under one id. Each step inside it, such as a model call, a tool call or a search, is a span with its own timing. When an agent gives a strange answer, the trace shows the exact path: which documents it found, which tool it called with what input, and where the time went.
Try it now
Without a trace, a bad answer is a mystery. With one, it's a lookup.
Learn it properly
Logging and monitoring · See what your LLM app actually did in production. About 25 minutes.
Other terms from the same lesson
- observability: Recording what your AI app did on each request (inputs, outputs, timing, cost) so you can find problems.
- percentile: The value below which a given share of results fall. The 95th percentile beats 95% of the others.
- redact: To hide sensitive parts of text before storing it, such as replacing an email address with [email].
- span: One step inside a trace, such as a single model call or search, with its own start and end time.
- tail latency: How long the slowest requests take, such as the slowest 5% (p95). Users notice these waits even when the average is fine.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.