Skip to main content
The Chat Analytics page gives you a concise, data-rich view of how your AI agent is handling chat conversations. It combines five headline KPI cards with interactive charts so you can monitor chat performance, resolution trends, and escalation patterns at a glance.

​
Headline Metrics

Total Chats

Total number of chat conversations handled by the workspace in the selected period.

Unique Users

Count of distinct users who initiated a chat conversation with your agent.

Avg Turns

Average number of message exchanges per conversation, giving a sense of chat depth and complexity.

Resolution Rate

Percentage of conversations resolved entirely by the AI without requiring a human escalation.

User Satisfaction

Aggregate satisfaction score derived from user sentiment signals across conversations.
Each metric displays the value for the selected time window alongside a % change compared with the equivalent prior period, so you can quickly identify positive or negative trends.

​
Charts

​
Chat Volume by Day

​
chart
A stacked bar chart plotting the number of chat conversations for every calendar day in the selected period. Each bar is segmented by outcome type (Contained, Transferred, User-Abandoned, Error), making it easy to see both total volume and the composition of outcomes on any given day. Hover over a segment to inspect its exact count.

​
Chat Outcomes

​
chart
A pie chart that breaks down the final disposition of each conversation:
  • Contained – the AI agent handled the conversation through to the end without escalating it to a person. This includes a visitor who read the answer and then simply closed the tab, which for chat is ordinary self-service.
  • Transferred – the conversation was escalated and reached a human agent. A handoff that failed and fell back to the AI is not counted here; the conversation is classified on how it actually ended.
  • User-Abandoned – the visitor walked away from the conversation mid-thread rather than finishing it — for example, abandoning it and starting a fresh one instead. The abandoned thread’s transcript ends with the chat end message configured on the agent.
  • Error – the conversation ended due to a system or processing error
Each segment is labelled with its percentage share and absolute count.
Reclassified in release 2.5.0 — chat conversations used to be judged by the rules written for phone calls, so a visitor who closed the tab was recorded under a caller-hangup outcome and displayed as Hangup. Those conversations now display as Contained, both here and in the Disposition column of your chat conversation history, and because they are no longer treated as escalations they have also been removed from the Transfer Dispositions breakdown below.This applies to historical conversations as well as new ones, so both charts can look different for periods you have already reviewed.

​
Transfer Dispositions

​
chart
A secondary pie chart that breaks down transferred conversations by the disposition (Freshchat channel) the AI selected when escalating. This helps you understand which channels are receiving the most escalations and whether your disposition descriptions are routing correctly.The percentages here are calculated over genuinely transferred conversations only. Visitors who closed the tab no longer appear in this chart at all, and a successful escalation keeps the disposition the agent chose rather than having it overwritten.

​
Containment Management

The Transfer Dispositions chart is paired with a containment management panel that lets you reclassify disposition outcomes:
  • Mark as Contained — if a transfer to a particular channel is considered a successful self-service outcome in your workflow, you can mark that disposition as “contained” so it is counted toward your Resolution Rate rather than against it.
  • Mark as Transferred — revert a disposition back to its default “transferred” classification.
Changes apply immediately to the analytics view and persist across sessions. The dispositions listed in this panel now cover genuinely transferred conversations only — see Chat Outcomes.
Handoffs now expire. A chat handed to a human closes itself after four hours with no messages, or twenty-four hours from the handoff, whichever comes first. Conversations that previously sat open indefinitely therefore start appearing as completed, timed-out conversations — see Chat Escalation.In the agent’s Handoff → Chat editor the abandon outcome is now labelled User Abandoned. That is a display name only: exports and downstream reporting still record the stored Caller-Hungup value, so keep matching on that.
Chat conversation history refreshes in place when you change a filter, auto-updates conversations that are still running every fifteen seconds, and labels its filter toggle In-progress Only.

​
Real-Time Updates

The Chat Analytics dashboard updates live as new conversations complete. A green pulse indicator in the top-right of the page confirms that live updates are active.
  • Pause — click the pause button to freeze the view. This is useful when reviewing a specific snapshot without the numbers shifting.
  • Resume — click resume to reload with the latest data and re-enable live updates.

​
Time Range Filtering

Use the date range selector to focus on a specific window: All charts and headline metrics update together when the range changes.

​
Where to go next

Call Analytics

View the equivalent analytics dashboard for your voice channel.

Chat Escalation

Configure how and when your AI agent escalates to Freshchat.