Your data. Your keys. Your control.
The same controls apply on both channels — Zendesk tickets and website chat. Your customer data never passes through our AI accounts, personal information is masked before it reaches the model, and every customer's data is fully separated.
Your own AI key
You connect your own OpenAI, Anthropic, or Google Gemini account directly. Your customer data flows from Zendesk, or from your website chat widget, to your AI provider — never through our AI accounts.
Personal data masking
Before any data reaches the AI, RAUM automatically finds and masks personal information in logs and AI requests. Names, emails, phone numbers, credit card numbers, and other sensitive details are replaced with placeholders — then restored in the final reply. (This is sometimes called "PII redaction" in security reviews.)
Encryption at rest
Credentials, API keys, and other sensitive configuration are encrypted by the application with AES-256-GCM before they are written to the database. The key is derived from a secret held in Azure Key Vault, separate from the database, and the database and object storage are also encrypted at rest by Azure.
Strict data separation
Every stored record and cache entry is scoped to your organization's identifier, so your knowledge bases, decision trees, analytics, and API keys are kept separate from every other customer's. Nothing is shared or mixed across accounts.
Data Residency
RAUM is hosted on Microsoft Azure in the United States, primarily in the Central US region. Data is kept only as long as the service, analytics, audit logging, and the transcript retention you configure require. Your AI provider's data policies apply to how they process your data.
Audit Logging
Every AI operation, admin action, and data access is logged with IP tracking and change history. Full audit trail for compliance and security review.