- Automation Cloud and Test Cloud
- Automation Cloud Public Sector and Test Cloud Public Sector
- Automation Cloud Dedicated and Test Cloud Dedicated
October 2026
October 2026 release notes for Automation Ops in Automation Cloud and Test Cloud.
October 29, 2026
Upcoming change: low-code and coded agents share the same governance policies and LLM configurations
Starting December 2, 2026, the agents settings in AI Trust Layer policies govern both low-code and coded agents, and coded agents use the LLM configurations defined for low-code agents. The change applies to the LLM calls that coded agents make through the AI Trust Layer. Existing coded agents need no code changes or redeployment.
On that date, the coded agents settings will be hidden from AI Trust Layer policies, LLM configurations, and Model hub, and will no longer be enforced.
This can be a breaking change for coded agents. Where the agents and coded agents settings in an AI Trust Layer policy differ, coded agents switch to the agents settings on December 2, 2026. Depending on the difference, coded agents can lose access to models through the AI Trust Layer, gain access to more models, lose guardrails and personally identifiable information (PII) masking, or fail because stricter guardrails apply to them.
Wherever the two sets of settings differ, coded agents change behavior:
- Enable Agents controls both kinds of agents. In a policy where Enable Agents is disabled and Enable Coded Agents is enabled, coded agents can no longer call models through the AI Trust Layer, and coded agents that depend on those calls fail.
- The agents guardrails apply to coded agents. Guardrails and PII masking configured only for coded agents no longer apply, and where the agents guardrails are stricter, coded agents can fail.
- The Agents model controls on the Models tab decide which models coded agents can use, including the embedding models that only coded agents call. The Agent Builder in Studio Web does not list embedding models.
- Coded agents use the agents LLM configurations for Design, Evaluate & Deploy. A configuration that exists only under coded agents, including a Bring Your Own Model (BYOM) configuration, is no longer used. If the LLM configurations for coded agents are already identical to those for low-code agents, the behavior of coded agents does not change.
Before December 2, 2026, check that the agents settings in each AI Trust Layer policy are how you want coded agents to behave: compare the product toggles, guardrails, and allowed models with the coded agents settings. To keep coded agents on their current settings:
- Create an AI Trust Layer policy whose agents settings match your current coded agents settings, and deploy it to the users, groups, or tenants that use coded agents.
- Re-create under agents any LLM configuration that exists only under coded agents.
For example, if your coded agents settings allow only GPT-5 and your agents settings allow all models, coded agents can use all models after the change. To keep the restriction, create two AI Trust Layer policies and deploy them by group:
- Policy A: the agents settings allow only GPT-5. Deploy it to the groups that use coded agents.
- Policy B: the agents settings allow all models. Deploy it to the groups that use low-code agents.
Use the same approach for differences in the product toggles and guardrails.
If you take no action, your agents settings apply to coded agents as they are. You can update your policies and their deployments at any time, including after December 2. After the change takes effect, check that your coded agents behave as expected. Pricing, licensing, and stock keeping units (SKUs) do not change.
For details, refer to Settings for AI Trust Layer policies, Agents governance, Configuring LLMs in Automation Cloud or Configuring LLMs in Test Cloud, and the Deprecation timeline.
October 16, 2026
Input/output saving for audit is off by default in new AI Trust Layer policies
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.
October 14, 2026
Integration Service policies: connection types and custom connectors
Integration Service governance policies have two new settings:
- Connectivity, on the Feature toggles tab, controls whether users in a tenant create Standard connections, Relay connections, or both. Both types are allowed by default.
- The Custom connectors tab enables or disables custom connectors for each tenant, and configures their authentication types and parameters, as the Catalog connectors tab does for catalog connectors.
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.
October 13, 2026
Correction, October 13, 2026: This change was introduced on October 8, 2026, but was not included in the release notes at the time.
Minimum agent score policy for Studio Web is no longer enforced
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.
October 7, 2026
Automatic License Top-Up Grant for AI Trust Layer policies
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.
This feature is being rolled out gradually and might not yet be available for your organization.
October 6, 2026
Studio and Studio Web governance policy toggle renamed to Allow Autopilot UI
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.
October 1, 2026
Enforce your own guardrails organization-wide [Preview]
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.
- October 29, 2026
- Upcoming change: low-code and coded agents share the same governance policies and LLM configurations
- October 16, 2026
- Input/output saving for audit is off by default in new AI Trust Layer policies
- October 14, 2026
- Integration Service policies: connection types and custom connectors
- October 13, 2026
- Minimum agent score policy for Studio Web is no longer enforced
- October 7, 2026
- Automatic License Top-Up Grant for AI Trust Layer policies
- October 6, 2026
- Studio and Studio Web governance policy toggle renamed to Allow Autopilot UI
- October 1, 2026
- Enforce your own guardrails organization-wide [Preview]