Security & privacy
How AI Engine handles your data, what reaches the AI provider and how to lock it down.
8 articles
- How AI Engine handles your dataWhere your Salesforce data goes when someone uses AI Engine, what is stored in your org, and what is not kept.
- What is sent to the AI providerFeature by feature, the Salesforce data AI Engine includes in requests to OpenAI, Anthropic or Azure OpenAI, and what stays in your org.
- PII maskingHow AI Engine replaces personal data with placeholders before a request leaves Salesforce, what is masked, and how to configure it.
- Permissions and sharingHow AI Engine's two permission sets work, and how the agent respects each user's object permissions, field-level security and record sharing.
- API keys and Named CredentialsWhere your AI provider API key is stored, who can use it, and how to rotate it safely.
- Activity log and auditingWhat the AI Activity Log records for every AI action, who can see it, and how to use it for audits.
- Recommended security settingsA checklist of settings that keep AI Engine's access and data exposure to what your users actually need.
- Choosing a provider for complianceHow OpenAI, Anthropic and Azure OpenAI differ for data residency, contracts and web search when you use them with AI Engine.
Still stuck? Ask AI, or email contact@cloudconnected.pl with the exact error message, the page or action you used and roughly when it happened.