Agent capabilities & guardrails — found from sitemap — Leena AI

Cited by

Facts read from this source

• Guardrails scope Report an error

  “Guardrails are organisation-wide safety rules that validate every AI Colleague conversation — both what employees send and what the AI Colleague responds with — before execution continues. They are configured once and apply across all AI Colleagues automatically.”

• Guardrails built in Report an error

  “Three guardrails ship out of the box:”

• Pii detection applies to Report an error

  “PII Detection Personally identifiable information in conversations Employee input and AI output”

• Moderation applies to Report an error

  “Moderation Harmful, hateful, or explicit content Employee input and AI output”

• Jailbreak applies to Report an error

  “Jailbreak Prompt injection and attempts to override the assistant's safety rules Employee input only”

• Pii actions Report an error

  “Mask & continue The detected value is replaced with a redaction placeholder and the conversation continues”

• Pii entity groups Report an error

  “Entities are grouped — common identifiers such as credit card and IBAN numbers, alongside region-specific groups covering the USA, UK, Europe, and Asia-Pacific with their national identifiers, tax numbers, and health identifiers.”

• Moderation categories Report an error

  “They cover sexual content, hate and harassment, violence, self-harm, and illegal activities, each with more specific sub-categories.”

• Moderation always blocks Report an error

  “There is no action choice here. When a moderation category is triggered the request is blocked — masking and logging are not options.”

• Jailbreak readonly Report an error

  “Its detail view is read-only. Alongside the description it shows the confidence threshold range the detector operates within”

• Jailbreak blocks Report an error

  “The Jailbreak guardrail blocks attempts to manipulate the AI Colleague into bypassing its safety rules: prompt injection, role hijacking, and system prompt overrides.”

• Guardrail violations logging Report an error

  “Guardrail violations appear in Run History as their own step, so you can see exactly which guardrail fired, on which turn, and what happened next.”

• Guardrail audit trail Report an error

  “Every change is written to the audit trail.”

• Pii configurable Report an error

  “PII Detection is the one you configure and toggle independently; Moderation and Jailbreak are read-only views managed through the organisation-wide toggle.”

Scores citing this record

• The Automation Lead Admin, identity & access controls
• The Automation Lead Agent capabilities & guardrails
• The Customer-Service Director Agent capabilities & guardrails
• The Data Protection Officer Data use, training & retention
• The Data Protection Officer Admin, identity & access controls
• The Data Protection Officer Agent capabilities & guardrails
• The Head of IT Admin, identity & access controls
• The Head of IT Agent capabilities & guardrails
• The Skeptic Admin, identity & access controls
• The Skeptic Agent capabilities & guardrails
• The Works Council Member Agent capabilities & guardrails