Skip to main content
Metrics are how you measure what happens in every voice AI conversation. Roark collects some metrics automatically — like response time, talk time, and sentiment — and lets you define your own using LLM prompts for things like compliance checks, task completion, or custom business KPIs. Metrics

​
What’s a Metric?

A metric is a single measurement collected from a call. It has:
  • An output type — boolean, numeric, scale, text, classification, count, or offset
  • A scope — global (one value per call) or per-participant (separate values for agent and customer)
  • A context — call-level, segment-level (single utterance), or segment-range (span of conversation)
For example, response_time is a numeric, per-participant, segment-range metric that measures how long each speaker takes to respond. identity_verified might be a boolean, global, call-level metric powered by an LLM prompt.

​
Types of Metrics

​
System Metrics (Built-in)

Roark automatically collects deterministic and voice-analysis metrics for every call — no configuration needed. Voice-analysis metrics are powered by Roark’s custom voice analysis models, purpose-built to extract signal from conversational audio:
  • Performance — Response time, talk time, silence duration, overlap/interruptions, latency
  • Emotion & Sentiment — Sentiment tracking, 64+ emotion detection, vocal cues (raised voice, frustration), stress indicators
  • Speech — Interruption detection, pause analysis, repetition detection
These are always available in Call History and can be used in reports.

​
Custom Metrics (LLM-Powered)

Define your own metrics using natural language prompts. Custom metrics are evaluated by Roark Prism — our purpose-built evaluation model optimized for scoring voice AI conversations. You write a prompt describing what to measure, and Prism evaluates each call against it to return a typed result:
  • “Did the agent verify the caller’s identity?” → Boolean
  • “Rate the agent’s empathy on a scale of 1-10” → Scale
  • “What was the primary reason for the call?” → Classification
  • “How many times did the agent attempt to upsell?” → Count
Custom metrics are created in the dashboard or via the SDK.

​
How It All Fits Together

Here’s the typical sequence from defining a metric to seeing results:
1

Define or Choose a Metric

Use a built-in system metric, enable one from the marketplace, or create your own custom metric with an LLM prompt.
2

Test in the Playground

Run your metric against a real call in the Playground to validate it produces the results you expect. Iterate on the prompt until you’re satisfied.
3

Add Thresholds (Optional)

Set pass/fail criteria on your metric — for example, Customer Satisfaction >= 7 or Response Time < 1000ms. Thresholds turn raw values into actionable outcomes.
4

Decide When to Collect

Choose how and when your metric runs:
  • Metric Policies — Automate collection on incoming calls (monitoring). Set conditions to target specific agents, sources, or call properties.
  • Simulation Run Plans — Attach metrics with thresholds to simulation tests to validate agent behavior before deployment.
  • Collection Jobs — Run metrics on demand against existing calls via the SDK, useful for backfilling or re-processing.
5

Analyze Results

View metric values per call in Call History, aggregate them in Reports, and organize everything in Dashboards.

​
Quick Start Examples

System metrics like response_time are already collected for every call. To set a quality bar, create a metric policy with a threshold:
const policy = await client.metricPolicy.create({
  name: 'Agent Response Time SLA',
  status: 'ACTIVE',
  conditions: [
    {
      conditions: [
        {
          conditionType: 'AGENT',
          conditionKey: 'your-agent-id',
        },
      ],
    },
  ],
  metrics: [
    {
      id: 'response-time-metric-id',
      threshold: {
        operator: 'LESS_THAN',
        value: 1000,
        aggregationMode: 'P95',
        participantRole: 'AGENT',
      },
    },
  ],
})
Calls where the agent’s P95 response time exceeds 1 second are automatically flagged as failures.

​
Sections

Metric Definitions

Types, scopes, output formats, and how to create custom metrics

Playground

Test metrics interactively against real calls

Metric Policies

Automate metric collection with conditions-based rules

Thresholds

Define pass/fail criteria for your metrics

Collection Jobs

Run metrics on demand for existing calls via the SDK