# AI Report

This reports showcases the performance of your AI agents.

<figure><img src="/files/3y8hK8oVYMPI9jBJmLOq" alt=""><figcaption></figcaption></figure>

### Upvotes/Downvotes

This feedback helps gauge user satisfaction with the AI's performance when using AI action blocks like "Answer AI" and "AI agent", if you have enabled "Collect user feedback".

* **Downvotes** typically indicate that answers may be unsatisfactory, likely because questions are outside the AI's current training.
* **Upvotes** suggest that answers are satisfactory.

More downvotes mean AI answers are not good, probably, because questions asked are not trained yet.

### Median messages/session

The median number of messages exchanged between the user and AI agent in a single session.

### Satisfaction rate

The % of users who provided a thumbs up reaction to AI-generated responses from the total users that have provided any reaction.

### Usage&#x20;

Gives you a summary of how many AI credits are used up by your AI agents. Check how many AI credits you have by going to Settings > Billing. Or visit our [pricing page](https://www.wotnot.io/pricing).

### CSAT

Customer satisfaction score provided by users that received at least one AI-generated answer.

### Topics

This report shows the topics that were included in the conversations and mentioned by the users. You can create topics by giving a title for the topic, and describing what that topic means for the LLM to understand.

<figure><img src="/files/XNUrHmstQBlvE0wPvBky" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
Topics count are updated on a daily basis (NOT real-time).

Each new topic or changes to existing topic will require a retrain of all questions.
{% endhint %}

### Sentiment

This section describes the sentiment and emotion expressed by end-users when asking questions to the AI agent.

<figure><img src="/files/lEllBcTNAXsx4zqc4puE" alt=""><figcaption></figcaption></figure>

## Drilldown reports

Hover over any KPI and click the “Drill-down” button to view the detailed data behind that report.

<figure><img src="/files/kyy16YXv5ItwuXSLhgoA" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: 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:

```
GET https://help.wotnot.io/monitor/reporting/ai-report.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.