> ## Documentation Index
> Fetch the complete documentation index at: https://polyai-mintlify-7055a538.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Performance monitoring

> Track latency, containment, and ASR accuracy – use dashboards and Wren for deep insights.

Monitor key metrics like response latency, containment rate, and ASR accuracy. Use dashboards for overview data and Wren for deep sampling across 500+ conversations to identify root causes of performance issues.

<Tip>
  Ask [Wren](/wren/analyze) to investigate performance issues at scale. Its **deep sampling** analyzes up to 500 conversations per query, helping you quickly identify root causes behind metrics like high handoff rates, low containment, or latency spikes – without manually reviewing individual calls.
</Tip>

## Quick reference

| I need to...              | Where to go                                                             |
| ------------------------- | ----------------------------------------------------------------------- |
| Check overall performance | **Analytics > Dashboards**                                              |
| Find slow responses       | **Analytics > Conversations > Voice** → filter by latency               |
| Debug ASR accuracy        | **Analytics > Conversations > Voice** → Diagnosis → check transcription |
| Find knowledge gaps       | **Analytics > Dashboards** → unhandled queries                          |
| Check function errors     | **Analytics > Conversations > Voice** → filter by errors                |
| Track version performance | Compare versions in **Deployments**                                     |

## Key metrics

### Response latency

Time from when the user stops speaking to when the agent starts responding. Target: under 2 seconds.

**Common causes of high latency:** slow function execution, external API delays, complex knowledge retrieval, overly complex prompts.

### Containment rate

Percentage of calls handled without [human handoff](/voice-channel/handoffs). Target varies by use case (typically 60-90%). The inverse — handoff rate — is the primary metric for the [human-in-the-loop](/glossary/introduction#hitl-human-in-the-loop) portion of the agent's traffic.

**Common causes of low containment:** knowledge gaps, complex queries, caller preference for humans, technical errors.

### ASR accuracy

How accurately the agent transcribes what the caller says. Target: above 95% word accuracy.

**Common causes of low accuracy:** background noise, strong accents, uncommon words or jargon, poor phone connection.

## Monitoring tools

### Dashboards

Go to **Analytics > Dashboards** for high-level metrics: call volume, average duration, handoff rate, top intents, and performance trends. Filter by date range, environment, variant, or version.

### Conversation Review

Go to **Analytics > Conversations > Voice** to drill into individual calls. Search, filter, listen to recordings, review transcriptions, and toggle layers in the **Diagnosis** toggle group on the Transcription tab for technical details (function logs, knowledge retrieval, LLM prompts, timing breakdown).

### Wren

Ask [Wren](/wren/analyze) for deeper investigation. Its **deep sampling** capability analyzes up to 500 conversations per query, surfacing patterns across your data that would take hours to find manually. Launch it directly from dashboard charts using the **Generate insights** button, or open Wren and ask questions like *"Why are calls failing containment this week?"* or *"What do low-PolyScore calls have in common?"*

### Simulation tests

Use [test sets](/testing/simulation-tests) for automated regression testing and version comparison. Run them before promoting versions.

## Diagnosing common issues

### High latency

1. Filter **Analytics > Conversations > Voice** by high latency
2. Open **Diagnosis** → check the timing breakdown
3. Identify the bottleneck: function execution, knowledge retrieval, LLM generation, or TTS

**Fixes:** optimize slow functions, cache common audio phrases, switch to a faster TTS provider, simplify knowledge sources, add [delay controls](/tools/delay-control).

### Low ASR accuracy

1. Review transcriptions in Conversation Review
2. Compare to audio recordings
3. Look for patterns (specific words, accents, noise)

**Fixes:** add custom vocabulary, adjust ASR sensitivity, add clarification prompts for ambiguous input.

### Knowledge gaps

1. Check **Analytics > Dashboards** → unhandled queries
2. Review common questions without answers in Conversation Review
3. Use [Wren's deep sampling](/wren/analyze) to identify gaps at scale – try: *"What questions are we not handling well?"* or *"Where does the agent give incorrect or incomplete answers?"*

**Fixes:** add missing topics to [FAQs](/knowledge/faqs/introduction), add [Sources](/knowledge/sources/introduction), improve topic descriptions for better retrieval.

### Function errors

1. Filter **Analytics > Conversations > Voice** by errors
2. Review **Diagnosis** → function logs

**Fixes:** fix code, update API credentials, add error handling and retries, add logging with `conv.log` for better debugging.

### High handoff rate

1. Check **Analytics > Dashboards** → handoff metrics
2. Review handoff reasons for patterns
3. Ask [Wren](/wren/analyze): *"What are the top 5 reasons conversations are transferred to a human agent?"* – deep sampling gives you a percentage breakdown across hundreds of calls

**Fixes:** add knowledge for common handoff reasons, adjust handoff rules, add self-service options before handoff.

## Optimization quick wins

| Area            | Quick wins                                                                                      |
| --------------- | ----------------------------------------------------------------------------------------------- |
| **Latency**     | Cache common audio, switch to Cartesia TTS, use Turbo interaction mode, optimize slow functions |
| **ASR**         | Add custom vocabulary, use clarification prompts, enable noise cancellation                     |
| **Containment** | Add missing knowledge, improve handoff rules, clarify agent capabilities upfront                |
| **Quality**     | Fix pronunciations, improve response clarity, test with real users                              |

## Debugging toolkit

All debugging tools available in Agent Studio:

| Tool                                                                     | Purpose                                                                    | Where to find it                                                                      |
| ------------------------------------------------------------------------ | -------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| [Diagnosis layers](/analytics/conversations/diagnosis)                   | Inspect tool calls, knowledge retrieval, LLM prompts, and latency per turn | **Analytics > Conversations > Voice** → select a call → Transcription tab → Diagnosis |
| [`conv.log`](/tools/classes/conv-log)                                    | Add structured logging (info, warning, error) from Python functions        | Function code → appears in Diagnosis                                                  |
| [`conv.log_api_response()`](/tools/classes/conv-object#log_api_response) | Log full HTTP responses from API integrations for debugging                | Function code → appears in Diagnosis                                                  |
| [Simulation tests](/testing/simulation-tests)                            | Automated regression testing across versions                               | **Testing**                                                                           |
| [Alerts API](/api-reference/alerts/introduction)                         | Automated alerts for latency, errors, and call volume anomalies            | API configuration                                                                     |
| [Wren](/wren/analyze)                                                    | AI-powered analysis across up to 500 conversations                         | **Wren**                                                                              |
| [Dashboards](/analytics/dashboards/introduction)                         | High-level metrics: call volume, latency, handoff rates, containment       | **Analytics > Dashboards**                                                            |

## Related pages

* [Analyze conversations](/wren/analyze) – AI-powered conversation analysis with deep sampling
* [Health checks](/learn/maintain/health-checks) – proactive monitoring routines
* [QA and analytics](/learn/maintain/qa-analytics) – daily dashboard and conversation review workflows
* [Function maintenance](/learn/maintain/tool-maintenance) – debugging and optimizing functions
* [Alerts API](/api-reference/alerts/introduction) – automated alerts for latency, errors, and call volume