> For the complete documentation index, see [llms.txt](https://docs.cekat.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cekat.ai/en/chat/new-analytics-session-based/ai-agent-analytics.md).

# AI Agent Analytics

AI Analytics gives you a summary of how your AI agents are performing when replying to customers: how many messages they send, how many credits they use, and how often they resolve a session or hand off to a human agent. The data is shown in easy-to-read charts and tables, and you can filter it by date or inbox. You can also compare how effective each AI agent is, and export the report for deeper analysis.

<figure><img src="https://3693109682-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FZNZlvyOVkZXyd3pz2Cql%2Fuploads%2FwOMzjvbgF9RmWXB8FuRG%2FScreenshot%202025-11-13%20at%204.37.14%E2%80%AFPM.png?alt=media&#x26;token=c234ed9f-4898-425a-9e5b-20ae004d8049" alt="" width="563"><figcaption></figcaption></figure>

***

**1. AI Message Sent**

Shows the total messages sent by AI in the selected period, as a line chart. You can see how AI message volume changes by hour, for example when it peaks and when it's quiet.

**2. AI Credit Use**

Shows the total AI credits used in a given period. This chart helps you understand your overall AI usage. You can filter it by date or inbox.

**3. AI Performance Comparison**

Compares your AI agents side by side in a table. You can see messages sent, total credits used, how many sessions each AI handled on its own, and how many needed to be passed to a human agent. Handoff and resolution percentages are shown too, giving you a picture of how effective each AI agent is. It's useful for evaluating and deciding how your team uses AI.