> ## Documentation Index
> Fetch the complete documentation index at: https://watermelon.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# AI Agent Analytics
> AI Agent Analytics help you understand how your AI Agent is performing and where you can improve. By regularly analysing your data, you can keep optimising conversations, increasing automation, and improving your customers’ experience.
## **Where to find AI Agent Analytics**
In your Watermelon workspace, navigate to **Analytics** on the left-hand menu.
## Select date range
First, select the date range you want to analyse. Use the dropdown and select the date range, or manually select the data.
## **Key metrics**
You’ll see key metrics that summarise your conversations and automation performance:
### All conversations
The total number of conversations in the selected period. This helps you understand your overall volume.
### Handed off conversations
The number of conversations handed over from the AI Agent to a human agent. Use this to see how often live support is needed.
### Automation degree
The percentage of conversations that were fully handled by the AI Agent, without needing a human handover.
### Average speed of pick up time
How long it takes on average for a conversation to be picked up by a human agent after handover.
### Average handling time
The time it takes to fully complete a conversation from start to finish.
### Office hours vs. out of office
A breakdown of conversations during and outside office hours.
### All conversations and handed off conversations
A visual of the amount of all conversations and handed off conversations per period for the selected date range.
### Conversation topics
What tags were used and the count of those tags.