Signals

Signals are the outcomes, behaviors, and failures you want to track. Each signal is stored as a signal event tied to a trace, so you can jump back to trace context. Signals are generated from trace data by Laminar’s internal AI agent (LLM signals). Custom events emitted from your code (via Laminar.event) are stored as span events and are not associated with a signal. Signals also support two execution modes:

backfill jobs on historical traces
live triggers for new traces

Emit custom events from code

Emit structured span events directly from your code (separate from Signals).

Extract signals from traces using LLMs

Define prompts to extract structured signals from trace data.

Overview

Tracing

Evaluations

Datasets

Platform

Emit custom events from code

Extract signals from traces using LLMs

Cluster signals to identify patterns