> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usetuner.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction to Pre-defined Metrics
> Tuner automatically computes 30+ pre-defined metrics and evals for every call — no configuration required. Voice metrics, performance data, and a full library of AI-powered evals are available out of the box.
## Voice Metrics
Voice metrics measure how quickly your agent responds, broken down by the stage of the pipeline where the time was spent. They're captured automatically for every call. For how each stage is measured and how to read the p50/p90 breakdown, see [Call Latency & Voice Metrics](/docs/getting-started/core-concepts/call-latency-and-voice-metrics).
| Metric | Description | What to Look For |
| -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| **TTFB** | The end-to-end delay a customer feels — from the moment they stop speaking to the moment they hear the agent's first audio. Reported at p50 and p90. | A good p50 with a bad p90 means most turns are fine but a fraction are badly slow — usually a few long tool calls or model-reasoning turns. |
| **EOU** | End of Utterance delay: how long the system waits after the customer stops speaking before deciding the turn is complete. | Consistently high EOU points at conservative endpointing config — the agent feels slow to respond even when the rest of the pipeline is fast. |
| **STT** | Time from the end of the customer's speech to when the transcript is ready for the LLM. | Consistently high STT suggests the STT provider or network path is the bottleneck; high STT on isolated turns often means a long or noisy utterance. |
| **LLM** | Time attributed to the model on this turn, including any tool calls made during generation. | LLM time climbing across a call signals context accumulation; a single spike usually means a tool call or a long prompt. |
| **TTS** | Time from the first token of the response to the first audio chunk playing back to the customer. | High TTS is uncommon and usually indicates TTS provider or network latency. |
These stages are measured independently and overlap in real time — they do **not** sum to TTFB. Not every provider reports every stage; EOU in particular is only available from stacks that emit it, such as the LiveKit and Pipecat SDKs. When a stage isn't reported, Tuner omits it rather than showing zero.
## Performance Metrics
Performance metrics focus on the overall success of the call.
| Metric | Description | What to Look For |
| -------------------------- | ------------------------------------------------------------------ | ------------------------------------------------------------------ |
| **Success Rate** | Percentage of calls classified as successful. | A drop in success rate is a clear sign something is wrong. |
| **Failed Calls** | Number of calls classified as failed. | A high number points to systemic issues. |
| **Hallucination Failures** | Calls where the agent provided incorrect information. | Any hallucination is a critical issue that should be investigated. |
| **Missed Intent Rate** | Percentage of calls where the agent failed to understand the user. | A high rate indicates problems with your agent's understanding. |
| **Duration** | Total length of the call. | Unusually long or short calls may warrant investigation. |
| **Cost** | Cost of the call, if provided by your voice AI provider. | Helps you monitor operational expenses. |
## Predefined Evals
Evals go deeper than metrics — each one runs a purpose-built AI judge against the transcript to score a specific behavior. Tuner ships with 21 predefined evals across four categories, optimized using patterns from real-world voice AI deployments. You can enable any combination with a single click, or [create your own custom evals](#setting-up-evals).
### Accuracy
Checks that the agent captured and confirmed information correctly.
| Eval | Description | Scoring |
| ------------------------- | ------------------------------------------------------ | ----------- |
| **Confirmation accuracy** | Final confirmation matches the actual completed action | PASS / FAIL |
| **Data capture accuracy** | Dates, numbers, and key details captured correctly | PASS / FAIL |
| **Hallucination** | No invented facts or unsupported claims | PASS / FAIL |
### Actions & Tools
Validates that tools and workflows were invoked correctly.
| Eval | Description | Scoring |
| ---------------------------------- | --------------------------------------------------------- | ----------- |
| **Structured intake completeness** | All required fields collected before workflow completes | PASS / FAIL |
| **Tool args mismatch** | Tool called with correct parameters from the conversation | PASS / FAIL |
| **Tool call missing** | Required tool is actually invoked, not just claimed | PASS / FAIL |
| **Tool response mismatch** | Agent reports what the tool actually returned | PASS / FAIL |
| **Transfer handling** | Transfers executed via tool, not just verbally claimed | PASS / FAIL |
### Conversation Quality
Measures how well the agent communicates throughout the call.
| Eval | Description | Scoring |
| ------------------------------------- | ---------------------------------------------------- | ----------- |
| **Answer relevance** | Each response directly addresses the user's message | SCORE 1–5 |
| **Conciseness** | Responses are well-sized with no unnecessary filler | SCORE 1–5 |
| **Conversation flow and turn taking** | Logical progression without loops or abrupt shifts | SCORE 1–5 |
| **Dead air handling** | Pauses handled without silence or over-explaining | SCORE 1–5 |
| **Escalation handling** | Escalates to a human when the situation calls for it | PASS / FAIL |
| **Missed intent** | User's goal correctly identified and pursued | PASS / FAIL |
| **Politeness** | Respectful and courteous tone throughout | SCORE 1–5 |
| **Unnecessary repetition** | No restating of information already covered | SCORE 1–5 |
### Safety & Compliance
Ensures the agent stays within required guardrails.
| Eval | Description | Scoring |
| ------------------------------------ | --------------------------------------------------------- | ----------- |
| **Identity verification compliance** | Identity verified before any sensitive info is shared | PASS / FAIL |
| **Manipulation resistance** | Holds its ground against pressure or social engineering | PASS / FAIL |
| **Prohibited content** | Stays within content boundaries, no off-limits topics | PASS / FAIL |
| **Prompt injection resistance** | Ignores embedded instructions that try to hijack behavior | PASS / FAIL |
| **Required disclosures** | All mandatory notices and disclaimers delivered | PASS / FAIL |
## Setting Up Evals
Getting started with evals takes seconds — no prompt engineering required.
Open the evals panel, browse by category, and add any predefined eval to your agent with one click. Each eval ships with a prompt optimized on real voice AI use cases.
Every predefined eval is backed by an AI judge tuned on patterns from actual deployments — not generic LLM prompts. That means fewer false positives and scores you can act on immediately.
Have a behavior specific to your use case? Write your own eval in plain language and Tuner runs it as a first-class judge alongside the predefined ones.
***
## How to Use Pre-defined Metrics
Key metrics are displayed for a high-level summary. See [Best Practices for Agent Monitoring](/user-guide/quick-start/best-practices-for-agent-monitoring).
All metrics are available as columns for sorting and filtering. See [Best Practices for Agent Monitoring](/user-guide/quick-start/best-practices-for-agent-monitoring#3-use-call-logs-to-spot-patterns).
Use metrics as conditions to create custom labels and red flags. See [Introduction to Evaluations & Guardrails](/docs/getting-started/core-concepts/introduction-to-evaluations-and-guardrails).
***
### Next Steps
Learn about real-time alerts and how to set them up.
An overview of real-time alerts, their benefits, and how they help you catch issues early.