October 2026 release notes for Automation Ops in Automation Cloud and Test Cloud.

Prompt inputs and LLM-generated outputs are no longer saved for audit by default in new AI Trust Layer policies. Input/output saving is disabled when you create a policy, and you can enable it in the Feature Toggles tab. Existing policies keep their current setting.

For details, see Settings for AI Trust Layer policies.

Integration Service governance policies have two new settings:

In a tenant where the policy is deployed, custom connectors that are not enabled on the Custom connectors tab are disabled. Existing policies have no custom connector settings, so custom connectors stay disabled in the tenants where those policies are deployed until they are enabled on the new tab.

For details, refer to Settings for Integration Service policies.

Correction, October 13, 2026: This change was introduced on October 8, 2026, but was not included in the release notes at the time.

The Enforce minimum agent score before publishing policy for agent design in Studio Web is no longer enforced.

The Agent reviewer, powered by Autopilot, has replaced the agent score, so agents no longer have a score for the policy to check. The policy will be removed from the Studio Web policy settings in a future release.

For details, refer to Settings for Studio Web policies and the Deprecation timeline.

You can now enable Automatic License Top-Up Grant as a feature toggle within an AI Trust Layer policy. When enabled, an AI and Agentic usage top-up request is automatically granted for a configured number of packs instead of requiring manual approval from an Organization Administrator. For details, see Settings for AI Trust Layer Policies.

This setting applies to the AI and Agentic usage top-up flows in Automation Cloud and Test Cloud. For the platform release notes, refer to the Automation Cloud October 2026 release notes and the Test Cloud October 2026 release notes.

The Allow Autopilot toggle in Studio and Studio Web governance policies is now Allow Autopilot UI. The new name clarifies that the toggle governs access to the Autopilot user interface specifically, to accurately reflect the permission it controls. For Studio policies, this affects the toggle available since the 24.10.0 policy template version, unchanged through 25.10.0.

For details, refer to Settings for Studio policies and Settings for Studio Web policies.

Correction: This change was delivered on October 1, 2026.

Your organization can now bring its own subscription to a supported safety vendor into the AI Trust Layer, and enforce that vendor's guardrails organization-wide through an AI Trust Layer policy, alongside the UiPath-managed guardrail types. Policies now list your own guardrails in the Bring your own guardrails section of the Centralized guardrails tab. Azure AI Language, Azure Content Safety, and Noma are the vendors supported during preview.

This means the safety checks your security team has already approved do not depend on each agent author remembering to add them. As a governance administrator, you decide centrally which of your own guardrails are mandatory, and whether each one covers every LLM call in the organization or only the products that need it.

For details, refer to Settings for AI Trust Layer policies.