+ P Observe, evaluate, and improve your Ultravox agents
Capture every turn of your Ultravox voice pipeline as structured trace data — the same real-time speech-to-speech run, made inspectable.
What Prefactor records from Ultravox
Ultravox + Prefactor
Observe for Ultravox
Prefactor observes your Ultravox agents in real time — every LLM call, tool invocation, and custom span captured as stru
Open → EvaluateEvaluate for Ultravox
Prefactor evaluates your Ultravox agents — score outcome quality against the captured spans, track drift by comparing cu
Open → ObserveAct for Ultravox
Prefactor acts on your Ultravox agents at runtime — block, throttle, sandbox, or escalate a tool call or data access bef
Open →How the Ultravox integration works
- User turns, assistant turns, tool calls, and end-of-utterance events each become spans in the conversation timeline.
- Beyond auto-captured spans, use withSpan to record any custom step you define — a background agent handoff, a quality check, a business action.
Ultravox integration FAQ
Do I need a dedicated package for Ultravox?
You can instrument Ultravox today with the framework-agnostic prefactor-core SDK; a dedicated package can be added on request.
What does Prefactor capture from Ultravox?
Prefactor records user turns, assistant turns, tool calls, and end-of-utterance events as structured, timestamped spans — so every Ultravox run is captured as trace data you can reconstruct, search and export end to end.
Does Prefactor add latency or change how Ultravox runs?
No. Observability capture is designed to stay off your agent's critical path, so it doesn't alter your Ultravox pipeline or your callers' experience. The only part that acts inline is the optional runtime guardrails you enable per agent — by design, so a high-risk or low-confidence action can be held for human approval before it executes.
Can I evaluate agents built with Ultravox and catch regressions?
Yes. Once runs are captured, eval suites score quality and groundedness on real traffic, drift detection flags behaviour changes after deployment, and versioned eval history catches regressions before they ship — the observe → evaluate → improve loop applied to your Ultravox agents.
Related guides
See it on your Ultravox agents
Book a 15-minute setup and our team gets you tracing in production.