Overview

Last updated Sep 26, 2025

Use of customer data with Agents

Purposes

We process the information used with our services for the following purposes:

Provide our services
Support our services
Machine learning and product improvement and development

UiPath processes customer data to deliver and improve its services, enhance product reliability, and provide a better user experience. We adhere to industry standards, legal requirements, and internal policies to ensure the responsible use and protection of customer data.

Provide our services

Agent creation and execution

During the creation and execution of agents, we process both design-time data (such as content within system and user prompts) and runtime data (such as published agent inputs and outputs). This enables agents or simulations to function as intended, in accordance with our Agent Builder documentation.

Agent reliability

To ensure agents perform reliably, and to help you build better agents over time, we process:

Agent prompts, tools, and evaluations during design time.
Information about the models used in agents, helping you avoid deprecated models and ensuring the use of the most accurate and reliable ones.

Agent health score

We process evaluations, logs, and run data to calculate agent health metrics. This helps proactively identify and address potential issues, ensuring stable and predictable performance.

Prompt optimization features

Prompts are processed to enable features like prompt optimizer and Autopilot, which improve prompt quality and agent effectiveness.

Account provisioning and telemetry

We process the following information to provision accounts and ensure secure, stable service delivery:

Account data: Cloud organization name/ID, tenant name/ID, agent IDs, evaluation IDs, and user emails.
Usage data: Error logs, agent failure rates, and robot type (attended/unattended) to support performance improvements.

Support our services

Data submitted through support channels is processed to troubleshoot issues, in accordance with our Support Terms.

Machine learning and product improvement

We do not process customer data for model training.

We process runtime errors for product improvement when you actively decide to provide feedback.

We process agent templates in order to provide you with new and improved agent templates.

We process data for product improvement unless you opt out of product improvement or if you have a Business Associate Agreement in place.

Data storage

Customer data is stored based on regional preferences and in accordance with our Data Residency page, available in the Automation Cloud admin guide.

Integration with generative AI services

Prompts are processed by available LLM models to generate outputs. Agent Builder requires generative AI functionalities.
Agents are designed to enable human escalation and oversight. You are responsible for making sure that human validation/human-in-the-loop is configured.
Agent memory data is used to support Retrieval Augmented Generation (RAG) for Gen AI features.
Third party LLMs managed by UiPath do not use customer data to train the models.
You can govern and manage UiPath-managed generative AI features through the AI Trust Layer.

Safeguards

We follow our standard Software as a Service policies and related guidelines:

Customer data is deleted in accordance with the contractual provisions or upon request.
Customer data is encrypted. Access is strictly limited, and any access is logged and audited.
Data processed for product improvement is filtered and transformed to remove sensitive data or content.
You can export data from the AI Trust Layer Audit tab. For details, refer to Exporting audit logs.