> For the complete documentation index, see [llms.txt](https://docs.satisfilabs.com/resource-center/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.satisfilabs.com/resource-center/ai-agent-engine/reporting-and-analytics/analytics-dashboard/live-agent-escalations-report.md).

# Live Agent Escalations Report

{% hint style="success" %}

#### 🚀 A New Analytics Experience Is Coming Soon

We're evolving Analytics to provide deeper, more meaningful insights into your AI agent's performance. Over the coming weeks, you'll begin to see updates as we transition to a **conversation-based analytics experience**, designed to measure outcomes, not just messages.

The upgraded experience will feature:

* **Conversation-driven analytics** focused on user goals and outcomes
* **New visualizations and an improved UI** for easier reporting
* **Actionable insights** to better understand how your AI agent is performing
  {% endhint %}

### Live Agent Escalations Report Overview

This report covers a 30 day timeframe of conversations that were escalated from the AI agent to a live (human) team member: how many came through, how your team handled them, and how each individual agent performed. 

To access Live Agent analytics: 

1. Go to the [Agent Performance Console](https://agent.satis.fi/analytics/live-agent)
2. Log in with the same credentials you use for the Satisfi Labs Dashboard.
3. In **Analytics**, click **Live Agent**

<figure><img src="/files/2JHPrskIpOSsmvwUxEiL" alt=""><figcaption></figcaption></figure>

A Team filter lets you re-scope the entire report to a specific team rather than the full org.

<figure><img src="/files/VrxUFk5sC9yn9MehKovc" alt=""><figcaption></figcaption></figure>

### **What you'll find inside, top to bottom**

**Top KPIs**: the headline numbers: total escalations and how many were resolved, the number of distinct end users who reached a live agent, and median response and resolution times across all escalations.

<figure><img src="/files/DEcfWojYBZTYu8k2gwZ9" alt=""><figcaption></figcaption></figure>

**Escalation & Message Volume**: a daily trend comparing inbound end-user messages to the number of escalations. The gap between the two lines shows how much volume the AI agent absorbed before anything reached a human.

**Message Breakdown**: the split between messages sent by end users and messages sent by agents across all escalated conversations.

<figure><img src="/files/jVdMkYes99kG3Sh38qTc" alt=""><figcaption></figcaption></figure>

**Individual Agent Performance**: a per-agent table ranked by escalations handled, so you can see exactly who's carrying volume and how they're performing. Click any agent's name to drill into their full scorecard.

<figure><img src="/files/JE51qJyYknZOeyf4ER7D" alt=""><figcaption></figcaption></figure>

#### Agent Performance

Click any agent's name to open their full scorecard: their own escalation count, resolution rate, response and resolution times, and a resolved-vs-unresolved breakdown.&#x20;

<figure><img src="/files/I6BATydg5inYUVkqTWnU" alt=""><figcaption></figcaption></figure>

From there, scroll down to see the median number of AI messages a guest sent before reaching that agent, day by day, plus a table of every conversation that led to a live handoff: date, top intent, message counts, and conversation length.&#x20;

Click **Open** on any row to jump straight into that conversation in the Satisfi Labs Live Agent platform and see exactly what happened.

<figure><img src="/files/1T3KsfHQOohjA1p8lMPF" alt=""><figcaption></figcaption></figure>