> For the complete documentation index, see [llms.txt](https://docs.userlane.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.userlane.com/assistance/the-assistant/assistant-analytics.md).

# Assistant analytics

Metrics and views available in the AI Assistant analytics section of the Userlane portal.

AI Assistant analytics shows how people interact with the AI Assistant[^1]: what they ask, whether the Assistant responds with relevant content, and where gaps in coverage exist. The data appears in the Userlane portal under **Content analytics**, alongside guide, tooltip, and announcement analytics.

## Where to find it

AI Assistant analytics is in the Userlane portal under **Content analytics** > **AI Assistant**. The section appears only when the AI Assistant is enabled for the application. If the AI Assistant is not turned on, no analytics data is collected and the section is not visible.

## Analytics views

The analytics section has three views: topic clustering, chat browsing, and content coverage. Each one answers a different question about how the AI Assistant is used.

### Topic clustering

Chats are grouped into topics automatically, so recurring themes surface without manual tagging. A single chat can belong to more than one topic, because a user might cover several subjects in one conversation.

Topics improve over time as more data is collected. When a new theme emerges, it is labeled "new" until enough conversations contribute to it. Select a topic to open the list of related conversations.

### Chat browsing

Individual conversations are listed with their message count, reply type[^2], and content interaction status. Select any chat to open it in a side panel where the full exchange is visible, turn by turn.

This view is useful for spot-checking how the Assistant handled a specific question, or for reviewing conversations that the content coverage view flagged as uncovered.

### Content coverage

Content coverage shows the share of chats where the AI Assistant replied using connected content, compared with chats where no matching content was found. A topic that draws many chats but has low content coverage points to a subject that needs new or better content.

Checking this view regularly helps you decide which guides, knowledge articles, or connected documentation to create or improve next. It also shows the effect of content changes over time, because coverage should rise as gaps are filled.

## Metrics reference

<table><thead><tr><th width="207.9495849609375">Metric</th><th>What it measures</th></tr></thead><tbody><tr><td><strong>Users</strong></td><td>The number of unique users who started a chat in the selected period.</td></tr><tr><td><strong>Chats</strong></td><td>The total number of chat sessions in the selected period.</td></tr><tr><td><strong>Frequency</strong></td><td>How often users engage with the AI Assistant over the selected period.</td></tr><tr><td><strong>Chats with content</strong></td><td>The percentage of chats where the AI Assistant replied using connected content.</td></tr><tr><td><strong>Reply type</strong></td><td>How the AI Assistant generated its response: from the connected knowledge base, as a general answer, as a handoff to support, or as a clarification request.</td></tr><tr><td><strong>Content interaction</strong></td><td>Whether the user interacted with a content surface shown in the response, such as starting a guide or opening a document. Reported as Yes or No per chat.</td></tr></tbody></table>

## Privacy

User IDs are not displayed in the AI Assistant analytics views. Conversations are listed and browsable, but they are not attributed to named individuals. The analytics show what people ask and whether they find answers, without identifying who asked a specific question.

## Relevant articles

{% content-ref url="/pages/XDGntxUJimFOtJOihyow" %}
[The Assistant](/assistance/the-assistant.md)
{% endcontent-ref %}

{% content-ref url="/pages/jaGpQWjETS3dwv2yneLk" %}
[Configure the AI Assistant](/assistance/the-assistant/configure-the-ai-assistant.md)
{% endcontent-ref %}

{% content-ref url="/pages/FxcQeBasWlRhc3HVdmJT" %}
[Knowledge connectors](/assistance/the-assistant/connections/knowledge-connectors.md)
{% endcontent-ref %}

{% content-ref url="/pages/14ViydxzHwBkmZMnQj6h" %}
[AI features: what data is processed and where](/security-and-privacy/ai-features-what-data-is-processed-and-where.md)
{% endcontent-ref %}

## FAQ

<details>

<summary>What does the AI Assistant analytics section show?</summary>

Chat volume, topic patterns, content coverage, and individual conversation details for the AI Assistant in an application.

</details>

<details>

<summary>Where is AI Assistant analytics in the portal?</summary>

Under **Content analytics** > **AI Assistant**. The section is visible only when the AI Assistant is enabled for the application.

</details>

<details>

<summary>Can I see which user asked a specific question?</summary>

No. User IDs are not displayed in AI Assistant analytics. Conversations are browsable but not attributed to named individuals.

</details>

<details>

<summary>What does "chats with content" mean?</summary>

The percentage of chat sessions where the AI Assistant responded using content from connected knowledge sources, compared with sessions where no matching content was available.

</details>

<details>

<summary>How are topics created in the topic clustering view?</summary>

Automatically, by grouping chats that cover similar themes. They are not created manually. Topics improve as more data is collected, and newly emerging topics are labeled "new".

</details>

[^1]: The AI Assistant is the conversational feature inside the Userlane Assistant panel that answers questions from published and connected content, and hands off to guides or support.

[^2]: Reply type shows how the AI Assistant produced a response: from connected knowledge, as a general answer, as a support handoff, or as a clarification request.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.userlane.com/assistance/the-assistant/assistant-analytics.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.