# Auditing LLM interactions

> AI Trust Layer audit for Communications Mining generative AI features: which LLM inputs and outputs are recorded for each feature, and how to review them for compliance.

The Communications Mining capability sends the Large Language Model (LLM) requests for its generative AI features through the UiPath AI Trust Layer™, which records each operation in an audit log. The audit log gives administrators visibility into the data sent to LLMs and the responses they returned, supporting compliance, governance, and data transparency requirements.

## View audit entries

Each operation appears in the **Audit** tab of the **AI Trust Layer** page, under the **IXP** product name, including the inputs sent to the LLM and the outputs it returned.

Entries remain visible for 60 days, and you can export them for longer retention periods. For details about the audit view, exports, and retention, refer to [Viewing audit logs](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/viewing-audit-logs).

![The Audit tab of the AI Trust Layer page, displaying Communications Mining entries with their date, product, feature, tenant, user, model used, model location, and status](https://dev-assets.cms.uipath.com/assets/images/ixp/AITL-CM-c08c5374.webp)

## Audited features

The following generative AI features are recorded in the audit log, each with the input and output listed:

| Feature | Audited input | Audited output |
|---|---|---|
| [Generative Extraction](https://docs.uipath.com/ixp/automation-cloud/latest/cm-user-guide/generative-extraction-overview) | The extraction request, identified by the message ID | The raw LLM response, containing the predictions returned for the message |
| [Generative Annotation](https://docs.uipath.com/ixp/automation-cloud/latest/cm-user-guide/generative-annotation-new) | A sample of messages from the sources in the dataset | The labels returned for the sampled messages |
| Suggested labels from clusters | The list of message IDs in the cluster | The labels suggested for the cluster, with the reasoning behind them |
| Zero-shot taxonomy generation (Preview) | The list of labels suggested from clusters | The generated taxonomy schema |
| [Conversational filters (Preview)](https://docs.uipath.com/ixp/automation-cloud/latest/cm-user-guide/autopilot-for-communications-mining-conversational-filters-preview) | The user prompt | The generated filter schema |

## Control audited data

Automation Ops policies for the AI Trust Layer control how audit data is handled: you can turn off the saving of inputs and outputs, or mask personally identifiable information (PII) before requests reach the LLM. For details, refer to [Settings for AI Trust Layer policies](https://docs.uipath.com/automation-ops/automation-cloud/latest/user-guide/settings-for-ai-trust-layer-policies).