+ P Evaluate for Ultravox agents
Capture every turn of your Ultravox voice pipeline as structured trace data — the same real-time speech-to-speech run, made inspectable.
Prefactor evaluates your Ultravox agents — score outcome quality against the captured spans, track drift by comparing custom spans across versions and environments, and classify every run's risk on two axes: data sensitivity and action consequence.
How to add evaluate to Ultravox
Install the SDK
Add prefactor-core to your environment.
Register & create spans
Register the agent instance and record spans around your Ultravox run.
Spans flow to Prefactor
Structured trace data lands in Prefactor as your agent runs.
# pip install prefactor-core
import os
from prefactor_core import PrefactorCoreClient, PrefactorCoreConfig
from prefactor_http import HttpClientConfig
config = PrefactorCoreConfig(
http_config=HttpClientConfig(
api_url="https://app.prefactorai.com",
api_token=os.environ["PREFACTOR_API_TOKEN"],
)
)
client = PrefactorCoreClient(config)
await client.initialize()
# then instrument your Ultravox run with spans — see docs.prefactor.aiShown with the Prefactor SDK — a first-class, working integration today.
How the Ultravox integration actually 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.
What Prefactor captures for Ultravox agents
Outcome quality
Score agent outputs against your own criteria, task by task, using the continuous run history as the record to measure against.
Drift detection
Compare custom spans for the same operation across versions and environments — a model update or prompt change shows up as a difference between spans, before it shows up as a quality drop.
Risk classification
Every run scored on data sensitivity and action consequence, weighted into a Low / Medium / High / Critical classification.
Data tagging
Tag PII and other sensitive fields once in the schema; every run carrying that tag becomes searchable — the record enforcement acts on.
Trace anything — not just LLM calls
The SDK captures LLM, tool, and agent spans automatically. With withSpan you wrap any operation in your own span type — an API call, a database query, a quality check, a business action — each with its own payload and schema. It all flows into the same Observe, Evaluate, and cost views.
import { withSpan } from "@prefactor/core";
// Wrap ANY operation in a span you define — an API call, a quality
// check, a business action — with its own spanType, inputs and schema
await withSpan(
{
name: "research competitor",
spanType: "research_competitor",
inputs: { competitor },
},
async () => {
const results = await search(competitor); // your tool / API calls
return summarize(results); // captured as one span
},
);Nest spans to capture business-level actions, and start with permissive schemas you tighten over time. Instrumentation strategy →
An example run, span by span
Illustrative — a single Ultravox run as nested spans.
Illustrative example.
Manual logging vs DIY vs Prefactor
| Capability | Manual | DIY OpenTelemetry | Prefactor |
|---|---|---|---|
| LLM / tool / agent spans | Hand-rolled | ✓ build it | ✓ via the SDK |
| Token usage captured per call | — | Build it | ✓ |
| Configurable capture & sampling | — | Partial | ✓ |
| Hosted Admin UI (agents, instances) | — | — | ✓ |
| Risk profiles & audit trail | — | — | ✓ |
Ultravox evaluate — FAQ
Does evaluation reuse the same Ultravox integration?+
Yes — evaluation runs on the spans the SDK already records for Ultravox, so there is one integration, not a separate one for evaluation.
What is quality drift and how is it detected for Ultravox agents?+
Drift is a change in behaviour over time — after a model update, a prompt change, or a data shift. Because a custom span records the same Ultravox operation every time it runs, this week's spans can be compared directly against last week's, or against a different version or environment.
How is risk scored for Ultravox runs?+
On two axes — data sensitivity (what kind of data the run touched) and action consequence (what the agent did with it) — combined via configurable weights into a Low/Medium/High/Critical classification per run.
Can I tag and find PII across Ultravox runs?+
Yes — tag the fields that matter once in your agent's data schema, and every run carrying that tag becomes searchable across your whole Ultravox deployment, not just the run it was tagged in.
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.
Keep going
Evaluate for other frameworks
LangChain →CrewAI →LangGraph →OpenAI Agents SDK →Claude Agent SDK →Microsoft AutoGen →See it on your Ultravox agents
Book a 15-minute setup and our team gets you evaluate in production.