> For the complete documentation index, see [llms.txt](https://help.sipgate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.com/documentation/en/statistics-and-analyses/statistiken-and-analysen.md). # Statistics & analyses In the Analytics section, you get an overview of how your agent is actually being used. The statistics show when calls come in, which topics are discussed, and how usage develops over different periods. This allows you to specifically optimize your agent, adjust capacities, or improve content. ### Where can I find the statistics? You can find the analytics in the logged-in area under **Account management → AI Agents → Analytics.** ### What is evaluated? In the analytics you can see, among other things: * Call volume and conversation duration over various periods * At what times of day calls come in * Which topics and questions come up in the conversations * How often the agent answers or forwards calls itself ### Set time period and filters You can filter the statistics by different time periods and narrow them down specifically. Also by individual agents or across all of them, by certain time windows or thematic focuses.
In the section **Call volume** you can see at a glance: when and how many calls came in, how long they lasted, and how the conversation time is distributed over the selected period. The breakdown by individual days shows patterns and helps with capacity planning.
Under **Content** it's about the conversation content: Which topics were discussed, which questions were asked, how often were there transfers? This makes it possible to identify thematic focuses and assess your agents' performance in a targeted way.
In addition, calls can be evaluated by customer concerns, transfer destinations and playbooks, allowing you to specifically identify which topics are on callers' minds and where there is a need for optimization. ### What are the statistics useful for? The analytics help assess how your agent is being used and select or adjust the right package. For details about individual conversations, the conversation logs are the right place to go.
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://help.sipgate.com/documentation/en/statistics-and-analyses/statistiken-and-analysen.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.