UiPath Documentation
ixp
latest
false
Guía del usuario de Communications Mining
Importante :
La localización de contenidos recién publicados puede tardar entre una y dos semanas en estar disponible.

Auditoría de interacciones de LLM

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.

Ver entradas de auditoría

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.

Las entradas permanecen visibles durante 60 días y puedes exportarlas para períodos de retención más largos. Para obtener más información sobre la vista de auditoría, las exportaciones y la retención, consulta Ver registros de auditoría.

Audited features

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

FunciónAudited inputAudited output
Extracción generativaThe extraction request, identified by the message IDThe raw LLM response, containing the predictions returned for the message
Anotación generativaA sample of messages from the sources in the datasetThe labels returned for the sampled messages
Suggested labels from clustersThe list of message IDs in the clusterThe labels suggested for the cluster, with the reasoning behind them
Zero-shot taxonomy generation (Preview)The list of labels suggested from clustersThe generated taxonomy schema
Conversational filters (Preview)The user promptThe generated filter schema

Controlar los datos auditados

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.

  • Ver entradas de auditoría
  • Audited features
  • Controlar los datos auditados

¿Te ha resultado útil esta página?

Conectar

¿Necesita ayuda? Soporte

¿Quiere aprender? UiPath Academy

¿Tiene alguna pregunta? Foro de UiPath

Manténgase actualizado