- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access control and administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Preparing data for .CSV upload
- Uploading a CSV file into a source
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Email transform tags
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label low average precision
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining™
- Developer
- Uploading data
- Downloading data
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Migration Guide: Exchange Web Services (EWS) to Microsoft Graph API
- Fetching data for Tableau with Python
- Elasticsearch integration
- General field extraction
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
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.
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 | The extraction request, identified by the message ID | The raw LLM response, containing the predictions returned for the message |
| Generative Annotation | 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) | 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.