# AgentQ Audit

Source: https://userguide.qualytics.io/agentq/deep-dive/audit/

The AgentQ audit is a workspace-wide record of everything AgentQ has done. It brings prompts, responses, usage, cost estimates, tool calls, and the platform actions AgentQ performed together in one view, so an administrator can see what was asked, what the model answered, and what changed as a result.

Only the **Admin** user role can open it, and it appears in the AgentQ sidebar only while AgentQ is connected. To work with it, see [Select Audit Dates](https://userguide.qualytics.io/agentq/how-tos/audit/select-dates/) and [Sort and Filter the Audit History](https://userguide.qualytics.io/agentq/how-tos/audit/sort-and-filter-the-history/).

## What the Audit Covers

The unit of the audit is the **turn**, which is one prompt a user sent and everything AgentQ did in response. The audit holds every turn in the workspace, from every invoking user, in both active and archived conversations. Archiving a conversation keeps its turns here, but deleting one removes them, so a deleted conversation leaves no trace in the audit and its turns stop counting toward the totals. See [Delete a Conversation](https://userguide.qualytics.io/agentq/how-tos/interaction/delete-a-chat/). It opens on the last 30 calendar days and the period is adjustable. Longer result sets are paged, with controls above and below the history for moving between pages and for changing how many entries each one shows.

## What an Audit Entry Contains

Each entry is one turn. Its header names the user who ran it and the time it was invoked, with a **Provider** badge for the provider that served it, a **Cost** badge for its estimate, and a **Voice** badge  when the prompt was dictated with [voice input](https://userguide.qualytics.io/agentq/deep-dive/chat-interface/#voice-input). Below the header sits the conversation the turn belongs to, marked **Archived** when that conversation has been archived, followed by four counts.

| Count | What it reports |
| --- | --- |
| **Requests** | How many calls the turn made to the AI provider. A turn that uses tools makes more than one. |
| **Tokens** | The total tokens the turn consumed, input and output together. |
| **Tool calls** | How many AgentQ tools the turn invoked. |
| **Recorded actions** | How many changes to platform records the turn produced. |

Two expandable sections hold the detail.

**Content** shows the **Prompt** exactly as it was sent and the **Response** rendered with its Markdown formatting. A turn where nothing was stored reads *No response was recorded for this turn.*

**Tool calls and recorded actions** lists each tool the turn invoked, with its name, its **Arguments** formatted as code, and its **Output**. Below the tools it lists the platform actions the turn produced, each naming the action and the record it affected, with the time and the transaction number it belongs to. The section appears only when the turn produced at least one tool call or action.

## Cost Estimates

Every cost figure in the audit is an estimate Qualytics calculates from the token counts and the model's published pricing. It is not a bill from the provider and it does not replace one.

An entry carries a **Cost** badge reading **Unavailable** when no estimate could be calculated for the turn, which happens when the model has no pricing on record, when the turn predates cost tracking, or when no assistant response was stored. A missing estimate is a state of its own rather than a zero, so those turns are reported separately instead of being counted as free.

## Selected-Period Summary

Beside the history, a summary totals the same turns the filters select. It covers the whole selection rather than the page you are looking at, so moving between pages never changes the figures, while narrowing the period or the users does.

| Metric | What it reports |
| --- | --- |
| **AgentQ turns** | How many turns fall in the selected period. Hover over the figure to see how many were dictated by voice and how many were typed. |
| **Invoking users** | How many distinct users ran those turns. |
| **LLM requests** | How many calls those turns made to the AI provider. |
| **Tool calls** | How many AgentQ tools those turns invoked. |
| **Tokens** | The total tokens consumed, with the input and output split shown below the figure. |
| **Estimated cost** | The sum of the individual turn estimates. |

When any turn in the period has no cost estimate, a note above the metrics says how many, and those turns are left out of the total rather than counted as zero.

Changing a date or applying a filter updates the entries and these totals together. Besides the invoking user, the history can be filtered by **Input**, to show only the turns that were dictated (**Voice**) or typed (**Typed**).

## See Also

- **Examples**

  Worked scenarios showing what you ask AgentQ, what it does, and the shape of the answer.

  [Examples](https://userguide.qualytics.io/agentq/deep-dive/examples/)
- **Best Practices**

  Prompt design, cost management, guardrail behavior, rate limits, and async operation patterns.

  [Best Practices](https://userguide.qualytics.io/agentq/deep-dive/best-practices/)
- **Permissions**

  The user roles behind chatting with AgentQ, configuring it, and reading the audit.

  [Permissions](https://userguide.qualytics.io/agentq/deep-dive/permissions/)
- **Introduction**

  What this section covers, and the order to read it in.

  [Introduction](https://userguide.qualytics.io/agentq/deep-dive/introduction/)
- **How It Works**

  Where AgentQ appears, how a turn runs, what it is allowed to see, and its built-in features, including description suggestions.

  [How It Works](https://userguide.qualytics.io/agentq/deep-dive/how-it-works/)
- **The Chat Interface**

  Every control in the full-page and floating chat, and what the input accepts.

  [The Chat Interface](https://userguide.qualytics.io/agentq/deep-dive/chat-interface/)
- **Conversations, Responses & Context**

  How to write prompts, read AgentQ responses, and work with context-aware chats.

  [Conversations, Responses & Context](https://userguide.qualytics.io/agentq/deep-dive/conversations/)
- **AgentQ Limits**

  Rate limits, token usage, timeouts, SQL constraints, and scope constraints.

  [AgentQ Limits](https://userguide.qualytics.io/agentq/deep-dive/limits/)
- **AgentQ in Action**

  Worked examples of AgentQ, its tools, and the steps shown in chat.

  [AgentQ in Action](https://userguide.qualytics.io/agentq/deep-dive/in-action/)
- **Tool Catalog**

  Every tool AgentQ can call, what each one does, and what it shares with the model.

  [Tool Catalog](https://userguide.qualytics.io/agentq/deep-dive/tool-catalog/)
- **Semantic Reporting**

  The structured query interface AgentQ uses to count, filter, and inspect platform resources.

  [Semantic Reporting](https://userguide.qualytics.io/agentq/deep-dive/semantic-reporting/)
- **Supported AI Providers**

  Every provider you can connect and which ones support file attachments.

  [Supported AI Providers](https://userguide.qualytics.io/agentq/deep-dive/supported-ai-providers/)
- **Amazon Bedrock Authentication**

  The three ways to authenticate to Bedrock, and what an IAM role setup expects.

  [Amazon Bedrock Authentication](https://userguide.qualytics.io/agentq/deep-dive/bedrock-authentication/)
- **Access Controls**

  How an administrator chooses what chat may share with the model, and what each level unlocks.

  [Access Controls](https://userguide.qualytics.io/agentq/deep-dive/access-controls/)

*Last updated: November 7, 2026.*
