automation-ops
latest
false
Automation Ops release notes
- Automation Cloud and Test Cloud
- Automation Cloud Public Sector and Test Cloud Public Sector
- Automation Cloud Dedicated and Test Cloud Dedicated
- November 2026
- February 2026
November 2026
November 2026 release notes for Automation Ops in Automation Cloud Dedicated and Test Cloud Dedicated.
November 5, 2026
Centralized guardrails in the AI Trust Layer policy
You can now enforce AI safety guardrails organization-wide from the AI Trust Layer policy. On the Centralized guardrails tab, you enable each guardrail type for the products it should cover. The guardrail then applies automatically to every LLM call those products make, in all tenants where the policy is deployed, without reconfiguring individual agents or automations.
The following guardrail types are available:
- Harmful content – Detects hate speech, self-harm, sexual content, and violence in model interactions.
- Prompt injection – Detects jailbreak and prompt injection attempts that try to bypass system instructions.
- In Flight PII – Masks personally identifiable information (PII) in prompts before they reach the LLM.
- IP protection – Detects intellectual property leakage in model-generated text and code.
For details, refer to Centralized guardrails.