> For the complete documentation index, see [llms.txt](https://docs.infraon.io/infraon-help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.infraon.io/infraon-help/infinity-user-guide/infraon-configuration/general-settings/ai-audit.md).

# AI Audit

The **AI Audit** module provides visibility into all **AI-driven operations** performed within the system. It captures detailed logs of AI feature usage, including the model used, execution time, request and response data, token consumption, and status.

## **What you see on the screen**

The AI Audit page displays a consolidated list of all **AI interactions** performed across the platform. Each record represents a single AI request, including its execution details, such as feature, model, time taken, and response status.

Users can search, filter, and analyze audit records using multiple parameters to identify specific AI operations or performance insights.

![](/files/4cf9486c8fd8a4fd1eee521be222990f941897f1)

AI Audit **| Basic Details**

<table><thead><tr><th width="135.4000244140625">Label</th><th width="175.60003662109375">Action</th><th>Description / Example</th></tr></thead><tbody><tr><td><strong>Search</strong></td><td>Input text</td><td>Allows users to search audit records using keywords such as feature name, message content, or user.</td></tr><tr><td><strong>Filter</strong></td><td>Apply conditions</td><td>Enables filtering of audit data based on selected fields and conditions.<br><br><strong>Available Fields:</strong> Feature, Model, Request Time, Message, Response Time, Status, Settings, User, Provider, Request Token, and Response Token.</td></tr><tr><td><strong>Date Range</strong></td><td>Select from the dropdown</td><td>Filters audit records based on a selected time period (e.g., Last 60 Days).</td></tr></tbody></table>

**Audit Data Fields |** AI Audit

The following columns are available in the audit table:

<table><thead><tr><th width="187.39996337890625">Label</th><th width="118.59991455078125">Action</th><th>Description / Example</th></tr></thead><tbody><tr><td><strong>Feature</strong></td><td>View</td><td>Displays the AI feature used (e.g., KB Creation, Service Classification).</td></tr><tr><td><strong>Model</strong></td><td>View</td><td>Shows the AI model used for execution (e.g., GPT-5.4-mini).</td></tr><tr><td><strong>Request Time</strong></td><td>View</td><td>Indicates when the AI request was initiated.</td></tr><tr><td><strong>Response Time</strong></td><td>View</td><td>Indicates when the AI response was generated.</td></tr><tr><td><strong>Time Taken (sec)</strong></td><td>View</td><td>Total execution time for the request.</td></tr><tr><td><strong>Request Token</strong></td><td>View</td><td>Number of tokens used in the request.</td></tr><tr><td><strong>Response Token</strong></td><td>View</td><td>Number of tokens generated in the response.</td></tr><tr><td><strong>Total Token</strong></td><td>View</td><td>Combined token usage (request + response).</td></tr><tr><td><strong>Message</strong></td><td>View</td><td>Displays the input sent to the AI model.</td></tr><tr><td><strong>Response Message</strong></td><td>View</td><td>Displays the AI model's output.</td></tr><tr><td><strong>Status</strong></td><td>View</td><td>Shows execution status (e.g., success, error).</td></tr><tr><td><strong>LLM Settings</strong></td><td>View</td><td>Displays configuration details used for the AI request.</td></tr><tr><td><strong>User</strong></td><td>View</td><td>Indicates the user/system that triggered the AI action.</td></tr><tr><td><strong>Error</strong></td><td>View</td><td>Displays error details if the execution fails.</td></tr><tr><td><strong>Key Type</strong></td><td>View</td><td>Indicates the type of API key used (e.g., External).</td></tr><tr><td><strong>Key Name</strong></td><td>View</td><td>Displays the configured key name.</td></tr><tr><td><strong>Provider</strong></td><td>View</td><td>Shows the AI provider (e.g., OpenAI, Azure).</td></tr></tbody></table>