Skip to main content
A trace records what your agent did during a call — tool calls, LLM invocations, retrieval, and other internal steps, each captured as a span with timing and attributes. Sending traces to Coval lets you evaluate behavior that isn’t visible in the transcript: whether the right tools were called in the right order, where latency comes from, and where conversations fail. Tracing works for both simulations (Coval calls your agent) and live conversations (you submit call data afterward). The instrumentation is the same; only how you identify the call differs.

​
Choose a setup path

There are four ways to get traces into Coval. Pick the one that fits your stack.

Wizard

One command (npx @coval/wizard) auto-instruments a Pipecat, LiveKit, or Vapi agent. The quickest path on a supported framework.

Tracing Skills

Give your AI coding agent a reviewable, prompt-driven workflow to add tracing and validate one real trace. Good for custom agents.

OpenTelemetry SDK

Instrument your agent by hand with the OpenTelemetry SDK. Full control, any language or framework.

Import from a platform

Already tracing with Langfuse, Arize Phoenix, or LangSmith? Connect it once and Coval imports traces automatically — no re-instrumentation.
If you…Use
run a Pipecat / LiveKit / Vapi agent and want the quickest setupWizard
have a custom agent and want a reviewable, AI-assisted setupTracing Skills
want full manual control, or use a language the wizard doesn’t coverOpenTelemetry SDK
already send traces to Langfuse, Arize Phoenix, or LangSmithImport from a platform

​
After traces are flowing

Once Coval is receiving spans:
  • View traces — inspect a single call’s spans in the waterfall and flame-graph viewer, and use Transition Hotspots to see where runs fail across a whole run.
  • Trace Search — search across every traced call with structured filters or natural language.
  • Trace metrics — turn span data into metrics for latency, tool-call counts, token usage, or any custom value.