> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent monitoring & analytics

> Track resolutions, customer feedback and operating spend. Use Analytics, Evaluations and Transcripts to find service issues and guide agent improvements.

## Overview

Agent monitoring & analytics helps your team see where agents resolve customer requests, where service breaks down and what it costs to operate. Use [Analytics](/docs/documentation/measure/analytics) to track outcomes and spend, [Evaluations](/docs/documentation/measure/evaluations) to assess conversations against your criteria, and [Transcripts](/docs/documentation/measure/transcripts) to investigate the messages and execution logs behind a result.

Open **Analytics**, **Evaluations** or **Transcripts** from your project sidebar.

#### Analytics

Analytics in a fictional retail project, showing conversation volume, outcome metrics and operating cost — Analytics brings conversation volume, outcomes and operating cost into one view.

#### Evaluations

Evaluations list in a fictional retail project, showing configured criteria and scoring controls — Review configured Evaluations, scored-log counts and automatic scoring toggles.

#### Transcripts

A retail conversation Transcript with customer messages, agent replies and execution logs — Compare customer and agent messages with the execution logs beside them.

## Choose a starting point

- **How is my agent performing?** [Compare trends in Analytics](/docs/documentation/measure/analytics#trends).
- **How do I build my dashboard?** [Choose and arrange dashboard cards](/docs/documentation/measure/analytics#customizing-the-dashboard).
- **Can I track my own quality criteria?** [Define an Evaluation](/docs/documentation/measure/evaluations#creating-an-evaluation), then [add its metric to Analytics](/docs/documentation/measure/analytics#custom-metrics).
- **What happened in a conversation?** [Review its Transcript and logs](/docs/documentation/measure/transcripts#reviewing-individual-transcripts).
- **What is driving operating cost?** [Inspect the spend breakdown](/docs/documentation/measure/analytics#spend-analysis).

## Explore Agent monitoring & analytics

<a id="explore-prism" />

### [Analytics](/docs/documentation/measure/analytics)

See resolution, customer feedback and operating spend together. Arrange dashboard cards and track your own quality metrics to decide what to improve.

### [Evaluations](/docs/documentation/measure/evaluations)

Check conversations against your business criteria. Define metric types, test judgments and score new or historical conversations.

### [Transcripts](/docs/documentation/measure/transcripts)

Find what happened in a customer interaction. Filter saved conversations and inspect messages, execution logs, metadata and Evaluation results.

## From a finding to a tested change

<a id="related-areas" />

### 1. Find a result to investigate

In [Analytics](/docs/documentation/measure/analytics#filtering-your-view), choose the Environment and period you want to review. Open a custom Evaluation from **Quality** to [inspect its scored conversations](/docs/documentation/measure/analytics#drilling-into-evaluation-results).

### 2. Check the conversation behind the score

In the Evaluation’s **Results** view, recheck the dates and Environment: its filters are independent of the dashboard. Compare the [score and reasoning](/docs/documentation/measure/evaluations#viewing-evaluation-results) with the [Transcript’s messages and execution logs](/docs/documentation/measure/transcripts#reviewing-individual-transcripts) to identify the request, reply or tool result that needs attention.

### 3. Make and test a change

Use [Agent studio](/docs/platform/studio) to edit the relevant instructions, Playbook, Workflow or tool. Use [Agent testing & QA](/docs/platform/rehearsal) to exercise the same situation in a Test or Simulation and review the result before publishing the change.
