# Audit Tab in Power Pilot

The audit tab in Power Pilot provides a detailed view of assistant usage. It allows identifying the models and users involved, as well as tracking the input and output tokens generated in each interaction. The estimated cost of token consumption is also available for review.

The accuracy of the information depends on correctly filling out the token cost fields during model creation. The values presented are approximate estimates.

<figure><img src="/files/UJjQS3eP6zK6waLlWyR5" alt=""><figcaption></figcaption></figure>

### Type of Consumption

In Power Embedded, token consumption can be identified in the "Type" column based on the source::

* **WhatsApp**
* **Peports Portal**
* **Manager**

### Audit Functionality

Each interaction with the assistant consumes tokens. These tokens are basic units representing words, parts of words, characters, or symbols used in information processing

In the audit, tokens are divided into two categories:

* **Input Tokens**: Generated by user questions and during the processing of responses (more complex responses require more tokens).
* **Output Tokens**: Used in the final response delivered by the assistant.

The audit tab allows monitoring token consumption by model and identifying the users who use AI the most. It also enables estimating the total cost related to token usage.

### Filters and Export

To facilitate analysis, filters are available by assistant, model, user, or type of consumption.

The data can be exported to CSV or Excel for more detailed analysis.

<figure><img src="/files/j5GBMHSLrN55BpJxaIM7" 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://docs.powerembedded.com/administration-portal/audits/power-pilot-usage.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.