- Getting started
- Host administration
- Organizations
- Tenants and services
- Authentication and security
- Licensing
- Accounts and roles
- External applications
- Testing in your organization
- AI Trust Layer
- About AI Trust Layer
- Managing AI Trust Layer
- Notifications
- Logging
- Troubleshooting
Automation Suite admin guide
The Usage Summary tab on the AI Trust Layer page provides an overview of the model usage and restrictions across different regions. It represents the historical data from your audit log and reflects the settings of your governance policies.
You can view data displayed on the following criteria:
- Total LLM Actions per Status: Enables you to monitor the status of different models across regions. To customize the data visualization, you can filter by region, model, status, and source.
- Total LLM Actions per Product: Allows you to monitor the AI feature adoption within your organization. To customize the data visualization, you can filter by tenant and product.
The Audit tab on the AI Trust Layer page offers a comprehensive view of AI-related operations, with details about requests and actions, the products and features initiating requests, as well as the used models and their location. You can monitor all AI-related operations and ensure their compliance with your established guidelines and policies. Audit logs also provide visibility into the inputs and outputs for products using generative features. Note that you can view log entries created in the last 60 days.
The audit data is displayed as a table, with each of its columns providing a specific information about the AI-related operations:
- Date (UTC): This displays the exact date and time,when each operation was requested. It allows for accurate tracking of requests according to their chronological order, facilitating timely audits.
- Product: The specific product that initiated each operation. This visibility allows tracing any operation back to its originating product for enhanced understanding and accountability.
- Feature: The specific product feature that initiated the operation, facilitating issue traceability to particular features, if any occurred.
- Tenant: The specific tenant within your organization that initiated the operation. This insight enables a more detailed overview and helps recognize patterns or issues at the tenant level.
- User: The individual user within the tenant who initiated the operation. It allows for tracing activities at a granular user level, enhancing the oversight capabilities. For GenAI Activities, the user is represented by the person who created the connection. An N/A value indicates a service-to-service communication where a user is not available.
- Model Used: The specific AI model employed to process each operation. This insight provides a better understanding of which models are handling which types of requests.
- Model Location: The location where the used model is hosted. This information can assist potential troubleshooting or audit requirements that could arise from model performance in specific locations.
- Status: The status of each operation—showing if it was successful, failed, or blocked. This quick way of identifying operational issues is crucial for maintaining a smooth, efficient environment.
Additionally, the filtering capability allows you to narrow down your audit based on criteria such as the date, product, used model, status, or source. The Source filter allows you to choose between viewing all calls, only UiPath-managed calls, or exclusively custom connection calls (using customer-managed subscriptions, as defined in Configuring LLMs).
Furthermore, when you select an entry from the Audit table, you can access a Details section for a more in-depth review, which includes all data available in the Audit table, as well as the LLM call source and the exact deployment associated with the call.
Exporting audit logs
This feature is available on the Enterprise licensing
plan.
The Export option enables you to export audit logs.
Exporting logs
Triggering and downloading an export
- Go to Admin > AI Trust Layer and select the Audit tab.
- Select Export.
- Choose to export with or
without inputs and outputs. Only one export can be processed at a time. You
must wait for the current export to complete before initiating a new one.
Note: The system processes exports asynchronously, with those including inputs and outputs requiring additional time.
- Upon export completion, you receive notifications via email and in the Notifications panel.
- Exported files are accessible through the View Exports option in the AI Trust Layer > Audit tab for a period of seven days.
The interface displays the number of remaining exports with inputs and outputs for the current month. Please note that once you reach the monthly limit, exporting with inputs and outputs will be suspended until the next month.
Filtering data for exports
Use the available filter options to narrow down the data you wish to export:
- Product – Select the products you want to export data from.
- Model Used – Choose specific models to filter the export.
- Status – Filter by Failed or Successful requests. A Failed status appears when an Automation Ops policy blocks a model, product, or feature.
- Date – Select a time range (e.g., Last day, Last week, Last 30 days) and choose between local or UTC time zones.
Filtering allows you to bypass the size and maximum rows per export limits, by selecting only the data you want to export.
Viewing exports
The View Exports pane displays the exported data, the user who generated the request, and the status of the export. This pane is also where you can download your exports by selecting the Download action.
If an error occurs, your monthly export limit is not affected, and you can generate a new export.
| Status | Definition |
|---|---|
| Pending | The request is being processed. The status transitions to Completed or Failed once processing is complete. |
| Failed | Sometimes, a request can fail.
A failed request does not count towards your monthly export allowance if you are exporting with inputs and outputs. |
| Completed | The processing is complete, and the file is ready for download. |
| Downloaded | The file was downloaded. |
| Expired | The file has reached the end of its 7-day availability window and can no longer be downloaded. |
CSV structure
Audit logs consist of the following columns:
| Column name | Type | Description |
|---|---|---|
| Date | DateTime | When the action was registered. |
| ActionId | String/UUID | A unique identifier for the specific action. Can be used to further trace information across the UiPath platform and get more insights. |
| Product | String | Name of the product where the action took place. |
| Feature | String | Name of the feature that triggered the action. |
| User | String | The user who triggered the action. |
| Tenant | String | The tenant where the action took place. |
| Model | String | The model that processed the input. |
| ModelLocalization | String | The region of the model. |
| Status | String | Status for the action which can be failed or succeeded. |
Export limitations
Inputs and outputs longer than 32,767 characters are truncated from the end. A message is automatically added to the truncated row to inform you the truncation of the information took place.
Inputs and outputs are processed to remove commas (”,”) so that you can easily process information without CSV malfunctions.
License duration and grace period
During the grace period, previously stored data remains accessible. However, no new data is saved in either Warm or Cold storage during this time. It's important to note that the data in Cold storage will eventually expire. The expiration timeline is calculated based on your license duration plus an additional two or three years, depending on your previous license type. This approach ensures that you have ample time to access your historical data even after your license has expired.
Data retention and storage
| Feature | Enterprise Standard | Enterprise Advanced |
|---|---|---|
| Active storage (UI Visible) | 60 days | 60 days |
| Warm storage (Export available) | 90 days | 180 days |
| Cold storage (Archived) | 2 years | 3 years |
| Maximum rows per export | 200K | 200K |
| Maximum export size | 1 GB | 1 GB |
| Exports with inputs and outputs | 4 per month | 4 per month |
| Exports without inputs and outputs | Unlimited | Unlimited |
Disabling the storage of inputs and outputs
You can disable saving inputs and outputs in exports by deploying an Automation Ops policy applicable at tenant, group, or user level. For details, refer to Settings for AI Trust Layer Policies.
Once this feature is disabled, the inputs and outputs are no longer saved and cannot be recovered.
Handling PII and PHI data in audit logs
When using Gen AI features in UiPath, it's important to understand that audit logs may include Personally Identifiable Information (PII) or Protected Health Information (PHI). These details can appear in both the input prompts sent to Large Language Models (LLMs) and in the responses they generate. This applies to interactions executed through both attended and unattended automations.
The Details section of each audit log entry displays the full input and output content when prompts saving is enabled. This includes metadata such as:
- Action ID
- Tenant
- Product
- Feature
- User
- Timestamp
Hiding sensitive data for compliance
If your compliance rules require hiding PII and PHI data in audit logs, you can configure the AI Trust Layer policy to control visibility:
- Go to Automation Ops™ > Governance and select or create an AI Trust Layer policy.
- In the Feature Toggles tab, make sure to set the Enable prompts saving for Audit? option to No.
With this setting, neither prompts nor LLM outputs are retained in the audit logs. The log will display the entry metadata, but the input/output content will appear as “Blocked by policy.”
This configuration allows you to hide sensitive content from log entries, maintain compliance requirements, and control visibility of sensitive data while preserving audit capabilities. Once hidden, you cannot recover the prompts for further use.
The AI governance tab on the AI Trust Layer page allows you to manage third party AI models usage for your organizations, tenants, or user groups through AI Trust Layer policies. This helps you control user access to Generative AI features and ensures appropriate governance across your organization.
You get an overview of all active policies and their current statuses. In addition to this, you can view and manage policies and their deployments, as follows:
- When you select the policy name, you are redirected to the respective AI Trust Layer policy in Automation Ops™ > Governance. You can now view the policy details and, if necessary, make changes. For details, refer to Settings for AI Trust Layer Policies. You can also directly create an AI Trust Layer policy by selecting Add policy.
- When you select Manage deployments, you are redirected to Automation Ops™ > Governance > Deployment, where you can review all your policy deployments. For details, refer to Deploy Policies at Tenant Level.
This Autopilot for Everyone tab on the AI Trust Layer page allows you to manage Autopilot for Everyone usage across your organization.
You can perform the following actions:
- Unified Pricing: Enterprise Platform, Standard Platform, Basic Platform, App Test Platform Enterprise, App Test Platform Standard.
- Flex: Advanced Platform, Flex Standard Platform.
The LLM configurations tab allows you to integrate your existing AI subscriptions while maintaining the governance framework provided by UiPath. You can:
- Add your own LLM: Use any LLM that meets the product's compatibility criteria. To ensure smooth integration, your chosen LLM must pass a series of tests initiated through a probe call before it can be used within the UiPath ecosystem.
Configuring LLMs preserves most of the governance benefits of the AI Trust Layer, including policy enforcement via Automation Ops and detailed audit logs. However, model governance policies are specifically designed for UiPath-managed LLMs. This means that if you disable a particular model through an AI Trust Layer policy, the restriction only applies to the UiPath-managed version of that model. Your own configured models of the same type remain unaffected.
When leveraging the option to use your own LLM or subscription, keep the following points in mind:
- Compatibility requirements: Your chosen LLM or subscription must align with the model family and version currently supported by the UiPath product.
-
Setup: Make sure you properly configure and maintain all required LLMs in the custom setup. If any component is missing, outdated, or incorrectly configured, your custom setup may cease to function. In such cases, the system will automatically revert to a UiPath-managed LLM to ensure continuity of service, unless UiPath LLMs are turned off through an Automation Ops policy.
-
Cost-saving: If your custom LLM setup is complete, correct, and meets all necessary requirements, you may be eligible for a Reduced Consumption Rate.
Setting up an LLM connection
LLM connections rely on Integration Service to establish the connection to your own models.
You can create connections to the following providers:
- Azure Open AI
- Open AI
- Amazon Bedrock
- Google Vertex
- Open AI V1 Compliant LLM – Use this option to connect to any LLM provider whose API follows the OpenAI V1 standard. For details, refer to the OpenAI V1 Compliant LLM connector documentation.
To set up a new connection, follow these steps:
Managing existing LLM connections
You can perform the following actions on your existing connections:
- Check status – Verify the status of your Integration Service connection. This action ensures that the connection is active and functioning correctly.
- Edit – Modify any parameters of your existing connection.
- Disable – Temporarily suspend the connection. When disabled, the connection remains visible in your list but doesn't route any calls. You can re-enable the connection when needed.
- Delete – Permanently remove the connection from your system. This action disables the connection and removes it from your list.
Configuring LLMs for your product
Each product supports specific large language models (LLMs) and versions. Use the table below to identify the supported models and versions for your product.
You can connect your own LLM using one of the following providers: Amazon Web Services, Google Vertex, Microsoft Azure OpenAI, or OpenAI V1 Compliant. Follow the steps outlined in the previous section to create a connection.
| Product | Feature | LLM provider | Version |
|---|---|---|---|
| Autopilot for everyone | Chat | Anthropic |
anthropic.claude-3.5-sonnet-20240620-v1:0 anthropic.claude-3.7-sonnet-20250219-v1:0 |
| OpenAI | gpt-4o-mini-2024-07-18 | ||
| Coded agents | Call LLM | Anthropic |
anthropic.claude-3.5-sonnet-20240620-v1:0 anthropic.claude-3.5-sonnet-20241022-v2:0 anthropic.claude-3.7-sonnet-20250219-v1:0 anthropic.claude-3-haiku-20240307-v1:0 |
| Gemini |
gemini-1.5-pro-001 gemini-2.0-flash-001 | ||
| OpenAI |
gpt-4o-2024-05-13 gpt-4o-2024-08-06 gpt-4o-2024-11-20 gpt-4o-mini-2024-07-18 o3-mini-2025-01-31 | ||
| Context Grounding | Advanced Extractions | Gemini | gemini-2.5-flash |
| Embeddings | OpenAI | text-embedding-3-large
gemini-embedding-001 | |
| GenAI Activities | Build, Test & Deploy | Anthropic |
anthropic.claude-3.5-sonnet-20241022-v2:0 anthropic.claude-3.7-sonnet-20250219-v1:0 |
| Gemini |
gemini-2.5-pro gemini-2.5-flash | ||
| OpenAI |
gpt-5-2025-08-07 gpt-5-mini-2025-08-07 gpt-5-nano-2025-0807 | ||
| Test Manager | Autopilot (generate and manage tests) | Anthropic | anthropic.claude-3.7-sonnet-20250219-v1:0 |
| Gemini |
gemini-2.5-pro gemini-2.5-flash | ||
| OpenAI | gpt-4o-2024-11-20 |
